[gcc r17-2954] Revert "forwprop, widening_mul: Fold longhand wide-multiply idioms [PR107090]"
Philipp Tomsich via Gcc-cvs <[email protected]> Tue, 4 Aug 2026 17:00:53 +0000 (GMT)
| Newsgroups | gmane.comp.gcc.cvs |
|---|---|
| Message-ID | <[email protected]> |
https://gcc.gnu.org/g:8642ff206ae282b5521b2e22a27e0c80384b1bf3 commit r17-2954-g8642ff206ae282b5521b2e22a27e0c80384b1bf3 Author: Philipp Tomsich <[email protected]> Date: Tue Aug 4 19:00:13 2026 +0200 Revert "forwprop, widening_mul: Fold longhand wide-multiply idioms [PR107090]" This reverts commit f1ea3d58f0caf819042b0ca3981af1219a8fb461. Diff: --- gcc/match.pd | 198 ---- gcc/testsuite/gcc.dg/long-mul-128-Og.c | 26 - gcc/testsuite/gcc.dg/torture/long-mul-128.c | 121 -- gcc/testsuite/gcc.dg/torture/long-mul-64-run.c | 180 --- .../gcc.dg/tree-ssa/long-mul-boundary-64.c | 417 ------- gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary.c | 394 ------- gcc/testsuite/gcc.dg/tree-ssa/long-mul-carry.c | 385 ------- .../gcc.dg/tree-ssa/long-mul-chain-cse-128.c | 52 - .../gcc.dg/tree-ssa/long-mul-chain-trunc-128.c | 80 -- .../gcc.dg/tree-ssa/long-mul-extra-addend.c | 63 -- gcc/testsuite/gcc.dg/tree-ssa/long-mul-ladder.c | 333 ------ gcc/testsuite/gcc.dg/tree-ssa/long-mul-low-plus.c | 54 - gcc/testsuite/gcc.dg/tree-ssa/long-mul-partial.c | 193 ---- gcc/testsuite/gcc.dg/tree-ssa/long-mul-two-carry.c | 140 --- gcc/testsuite/gcc.target/aarch64/long_mul.c | 100 -- .../gcc.target/arm/long-mul-thumb1-inline.c | 47 - gcc/testsuite/gcc.target/arm/long-mul-umull.c | 73 -- gcc/testsuite/gcc.target/i386/long_mul.c | 100 -- .../gcc.target/i386/widen_mult_high_chain.c | 32 - gcc/testsuite/lib/target-supports.exp | 20 - gcc/tree-ssa-forwprop.cc | 1197 +------------------- gcc/tree-ssa-math-opts.cc | 492 +------- gcc/tree-ssa-math-opts.h | 2 - 23 files changed, 9 insertions(+), 4690 deletions(-) diff --git a/gcc/match.pd b/gcc/match.pd index 4d47317b95e2..344883d6ea4c 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -6450,31 +6450,6 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (lshift (convert (bit_xor (convert:boolean_type_node @0) { boolean_true_node; })) { shift; }))))))) -/* Recognize a 2-arg PHI of the form - PHI<base + pow2, base> - guarded by an unsigned compare on (@0, @1). @1 is captured without - further structure; the long-mul fold in tree-ssa-forwprop.cc - classifies it to drive a PHI-form carry summand. The consumer - treats the carry as strict @0 > @1, so each polarity's compare - must encode that same condition: - cond_carry_add: true edge selects (base + pow2), so the - compare itself must be @0 > @1. - cond_carry_add_neg: true edge selects base, so the compare's - negation must be @0 > @1, i.e. the - compare itself must be @0 <= @1. - Matches the 2-arg PHI form via cond^. */ -(if (INTEGRAL_TYPE_P (type) - && TYPE_UNSIGNED (type) - && type_has_mode_precision_p (type)) - (match (cond_carry_add @0 @1 @2 @3) - (cond^ (gt @0 @1) (plus @2 integer_pow2p@3) @2)) - (match (cond_carry_add @0 @1 @2 @3) - (cond^ (lt @1 @0) (plus @2 integer_pow2p@3) @2)) - (match (cond_carry_add_neg @0 @1 @2 @3) - (cond^ (le @0 @1) @2 (plus @2 integer_pow2p@3))) - (match (cond_carry_add_neg @0 @1 @2 @3) - (cond^ (ge @1 @0) @2 (plus @2 integer_pow2p@3)))) - /* (a > 1) ? 0 : (cast)a is the same as (cast)(a == 1) for unsigned types. */ (simplify @@ -12272,179 +12247,6 @@ and, INTEGER_CST@2) INTEGER_CST@3) (if (compare_tree_int (@sub1, 1) == 0))) -#if GIMPLE -/* Match low and high parts of longhand multiplication. - Given a 2N-bit unsigned type, x = xh*2^N + xl and y = yh*2^N + yl, - where xh, xl, yh, yl are N-bit halves extracted via shifts and masks. */ - -/* High half: op >> N. */ -(match (mul_hi @op @0) - (rshift @op INTEGER_CST@0) - (with { - tree op_type = TREE_TYPE (@op); } - (if (INTEGRAL_TYPE_P (op_type) - && TYPE_UNSIGNED (op_type) - && TYPE_PRECISION (op_type) % 2 == 0 - && tree_fits_uhwi_p (@0) - && tree_to_uhwi (@0) == TYPE_PRECISION (op_type) / 2)))) -/* Low half: op & mask. */ -(match (mul_lo @op @0) - (bit_and @op INTEGER_CST@0) - (with { - tree op_type = TREE_TYPE (@op); } - (if (INTEGRAL_TYPE_P (op_type) - && TYPE_UNSIGNED (op_type) - && TYPE_PRECISION (op_type) % 2 == 0 - && tree_fits_uhwi_p (@0) - && tree_to_uhwi (@0) == wi::mask ( - TYPE_PRECISION (op_type) / 2, - false, - TYPE_PRECISION (op_type)))))) -/* Cross product: high(op0) * low(op1). */ -(match (mul_hilo @op0 @op1 @0 @1) - (mult:c - (mul_hi @op0 INTEGER_CST@0) - (mul_lo @op1 INTEGER_CST@1))) -/* Low-low product: low(op0) * low(op1). */ -(match (mul_lolo @op0 @op1 @0) - (mult:c - (mul_lo @op0 INTEGER_CST@0) - (mul_lo @op1 INTEGER_CST@0))) -/* High-high product: high(op0) * high(op1). */ -(match (mul_hihi @op0 @op1 @0) - (mult:c - (mul_hi @op0 INTEGER_CST@0) - (mul_hi @op1 INTEGER_CST@0))) -/* Cross sum: xh*yl + xl*yh. - Note: matches any PLUS; operands are validated as actual cross - products by the forwprop consumer (long_mul_check_consistency). */ -(match (mul_cross_sum @mul_hilo0 @mul_hilo1) - (plus:c @mul_hilo0 @mul_hilo1)) -/* Low sum: cross_sum + (xl*yl >> N). */ -(match (mul_low_sum @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (mul_cross_sum @mul_hilo0 @mul_hilo1) - (mul_hi - (mul_lolo @op0 @op1 INTEGER_CST@1) - INTEGER_CST@0))) -/* Carry from low-sum overflow: (cast?) (hilo > low_sum) << N. - No explicit type/width guard needed: mul_low_sum delegates to - mul_cross_sum + mul_hi + mul_lolo, which provide deep structural - constraints, and @0 ties the shift amount to the inner constants. */ -(match (mul_carry_low_sum @op0 @op1 @mul_hilo0 @mul_hilo1 @mul_hilo2 @0 @1) - (lshift - (convert? (gt - @mul_hilo0 - (mul_low_sum @op0 @op1 @mul_hilo1 @mul_hilo2 INTEGER_CST@0 - INTEGER_CST@1))) - INTEGER_CST@0)) -/* Carry from cross-sum overflow: (cast?) (hilo > cross_sum) << N. - Explicit guard required because mul_cross_sum is just (plus:c @0 @1) - with no inherent type or halfwidth constraint. */ -(match (mul_carry_cross_sum @mul_hilo0 @mul_hilo1 @mul_hilo2 @0) - (lshift - (convert? (gt - @mul_hilo0 - (mul_cross_sum @mul_hilo1 @mul_hilo2))) - INTEGER_CST@0) - (with { - tree op_type = TREE_TYPE (@mul_hilo0); } - (if (INTEGRAL_TYPE_P (op_type) - && TYPE_UNSIGNED (op_type) - && TYPE_PRECISION (op_type) % 2 == 0 - && tree_fits_uhwi_p (@0) - && tree_to_uhwi (@0) == TYPE_PRECISION (op_type) / 2)))) -/* Carry from addition overflow: (cast?) (a > a + b). - :c on gt also matches the LT form: (cast?) (a + b < a). */ -(match (mul_carry_low @0 @1) - (convert? - (gt:c @0 (plus:c @1 @0))) - (with { tree op_type = TREE_TYPE (@0); } - (if (INTEGRAL_TYPE_P (op_type) && TYPE_UNSIGNED (op_type))))) -/* Low accumulate: (xl*yl >> N) + (cross_sum & mask). */ -(match (mul_low_accum @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (mul_hi - (mul_lolo @op0 @op1 INTEGER_CST@0) - INTEGER_CST@1) - (mul_lo (mul_cross_sum @mul_hilo0 @mul_hilo1) INTEGER_CST@0))) -/* Ladder sum form 1: (hilo0 & mask) + hilo1 + (xl*yl >> N). - First variant: @mul_hilo1 is inside the inner plus:c alongside - (mul_lo ...). */ -(match (mul_ladder_sum1 @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (plus:c - (mul_lo - @mul_hilo0 - INTEGER_CST@0) - @mul_hilo1) - (mul_hi (mul_lolo @op0 @op1 INTEGER_CST@0) INTEGER_CST@1))) -/* Second variant: @mul_hilo1 is the outermost addend and could match - anything, so guard that its definition is a MULT_EXPR. */ -(match (mul_ladder_sum1 @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (plus:c - (mul_lo @mul_hilo0 INTEGER_CST@0) - (mul_hi (mul_lolo @op0 @op1 INTEGER_CST@0) INTEGER_CST@1)) - @mul_hilo1) - (with { - tree_code mul_hilo_code = TREE_CODE (@mul_hilo1); - tree_code rhs_code = ERROR_MARK; - if (mul_hilo_code == SSA_NAME) - { - gimple *def = SSA_NAME_DEF_STMT (@mul_hilo1); - if (def && gimple_code (def) == GIMPLE_ASSIGN) - rhs_code = gimple_assign_rhs_code (def); - } } - (if (rhs_code == MULT_EXPR)))) -/* Partial ladder sum: (xl*yl >> N) + hilo. */ -(match (mul_ladder_part_sum @op0 @op1 @mul_hilo0 @0 @1) - (plus:c - (mul_hi (mul_lolo @op0 @op1 INTEGER_CST@0) INTEGER_CST@1) - @mul_hilo0)) -/* Ladder sum form 2: (ladder_part_sum & mask) + hilo. */ -(match (mul_ladder_sum2 @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (mul_lo - (mul_ladder_part_sum @op0 @op1 @mul_hilo0 INTEGER_CST@0 INTEGER_CST@1) - INTEGER_CST@0) - @mul_hilo1)) -/* Ladder sum form 3: (hilo0 & mask) + (hilo1 & mask) + (xl*yl >> N). */ -(match (mul_ladder_sum3 @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (plus:c - (mul_lo @mul_hilo0 INTEGER_CST@0) - (mul_lo @mul_hilo1 INTEGER_CST@0)) - (mul_hi (mul_lolo @op0 @op1 INTEGER_CST@0) INTEGER_CST@1))) -(match (mul_ladder_sum3 @op0 @op1 @mul_hilo0 @mul_hilo1 @0 @1) - (plus:c - (plus:c - (mul_lo @mul_hilo0 INTEGER_CST@0) - (mul_hi (mul_lolo @op0 @op1 INTEGER_CST@0) INTEGER_CST@1)) - (mul_lo @mul_hilo1 INTEGER_CST@0))) -/* Long-multiply high-part emit chain produced by forwprop's recognizer: - - (N) ((2N) op1 * (2N) op2) >> N - - `(convert? @X)` accepts a bare operand (PRE may hoist the (T_2N) cast - out into a PHI on a shared slot). The lowering splits an operand - wider than T_N into T_N halves rather than truncating it. Wide type - must be unsigned mode-precision integer of even width; BITINT_TYPE is - refused. */ -(match (long_mul_high_chain @0 @1) - (convert (rshift (mult:c@3 (convert? @0) (convert? @1)) INTEGER_CST@2)) - (with { - tree wide_type = TREE_TYPE (@3); } - (if (INTEGRAL_TYPE_P (wide_type) - && TYPE_UNSIGNED (wide_type) - && type_has_mode_precision_p (wide_type) - && TREE_CODE (wide_type) != BITINT_TYPE - && TYPE_PRECISION (wide_type) >= 8 - && (TYPE_PRECISION (wide_type) & 3) == 0 - && tree_fits_uhwi_p (@2) - && tree_to_uhwi (@2) * 2 == TYPE_PRECISION (wide_type))))) -#endif - /* Floatint point/integer comparison and integer->integer or floating point -> float point conversion. */ (match (cond_expr_convert_p @0 @2 @3 @6) diff --git a/gcc/testsuite/gcc.dg/long-mul-128-Og.c b/gcc/testsuite/gcc.dg/long-mul-128-Og.c deleted file mode 100644 index 3a9bd703c116..000000000000 --- a/gcc/testsuite/gcc.dg/long-mul-128-Og.c +++ /dev/null @@ -1,26 +0,0 @@ -/* { dg-do compile { target int128 } } */ -/* { dg-options "-Og -fexpensive-optimizations" } */ - -/* The -Og pipeline does not run pass_optimize_widening_mul, so the - long-multiply fold must not emit a 2N wide-multiply chain here: - nothing would lower it before expansion. */ - -typedef __uint128_t u128; - -u128 -mulh (u128 x, u128 y) -{ - u128 x_hi = x >> 64; - u128 x_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - u128 y_hi = y >> 64; - u128 y_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 mulhilo = x_hi * y_lo; - u128 mullohi = x_lo * y_hi; - u128 cross_sum = mulhilo + mullohi; - u128 mullolo = x_lo * y_lo; - u128 shrlolo = mullolo >> 64; - u128 add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - u128 cond = ((u128) carry << 64) + x_hi * y_hi; - return cond + (add_cross_sum >> 64); -} diff --git a/gcc/testsuite/gcc.dg/torture/long-mul-128.c b/gcc/testsuite/gcc.dg/torture/long-mul-128.c deleted file mode 100644 index 1be4dec1141c..000000000000 --- a/gcc/testsuite/gcc.dg/torture/long-mul-128.c +++ /dev/null @@ -1,121 +0,0 @@ -/* { dg-do run { target int128 } } */ - -/* Runtime correctness for the full 128-bit pipeline: forwprop folds the - longhand to (u256) x * (u256) y >> 128 and widening_mul lowers it back - to a 128-bit longhand. mulh_reference stays unfolded via volatiles. */ - -typedef __uint128_t u128; - -/* The recognized longhand high-part multiply, shared by the callers below. - static inline so each caller inlines a copy, exposing its own chain to - forwprop. */ -static inline u128 -mulh_inline (u128 x, u128 y) -{ - u128 x_hi = x >> 64; - u128 x_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - u128 y_hi = y >> 64; - u128 y_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 mulhilo = x_hi * y_lo; - u128 mullohi = x_lo * y_hi; - u128 cross_sum = mulhilo + mullohi; - u128 mullolo = x_lo * y_lo; - u128 shrlolo = mullolo >> 64; - u128 add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - u128 cond = ((u128) carry << 64) + x_hi * y_hi; - return cond + (add_cross_sum >> 64); -} - -/* Standalone folded instance (noipa keeps it distinct from the inline - copies), validated against the unfolded reference. */ -__attribute__((noipa)) u128 -mulh_folded (u128 x, u128 y) -{ - return mulh_inline (x, y); -} - -__attribute__((noipa)) u128 -mulh_reference (u128 x, u128 y) -{ - volatile u128 x_hi = x >> 64; - volatile u128 x_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - volatile u128 y_hi = y >> 64; - volatile u128 y_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 mulhilo = x_hi * y_lo; - u128 mullohi = x_lo * y_hi; - u128 cross_sum = mulhilo + mullohi; - u128 mullolo = x_lo * y_lo; - u128 shrlolo = mullolo >> 64; - u128 add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - u128 cond = ((u128) carry << 64) + x_hi * y_hi; - return cond + (add_cross_sum >> 64); -} - -/* Two mulh calls sharing an operand: inlining exposes both chains and - VN CSEs the shared (u256) cast. Guard that lowering the first chain - does not free a cast the second still references. */ -__attribute__((noipa)) u128 -mulh_shared_xor (u128 x, u128 y, u128 z) -{ - return mulh_inline (x, y) ^ mulh_inline (x, z); -} - -/* One chain's high half feeding the next, first high part also live. After - recognition the second chain multiplies by the first product shifted down; - truncating that shift would leave the product live past its own lowering. */ -__attribute__((noipa)) u128 -mulh_chain_high (u128 x, u128 y, u128 z, u128 *first) -{ - u128 h1 = mulh_inline (x, y); - *first = h1; - return mulh_inline (h1, z); -} - -/* Squaring: VN CSEs the two (u256) casts of x, so lowering sees the - same stmt on both operand-cast slots. */ -__attribute__((noipa)) u128 -mulh_square (u128 x) -{ - return mulh_inline (x, x); -} - -int -main (void) -{ - static const u128 vals[] = { - 0, - 1, - (u128)0xFFFFFFFFFFFFFFFF, /* low half all-ones */ - ((u128)1 << 64), /* 2^64 */ - ((u128)1 << 127), /* high bit */ - ~(u128)0, /* all-ones */ - ((u128)0xDEADBEEFCAFEBABE << 64) | 0x0123456789ABCDEF, - ((u128)0x8000000000000001 << 64) | 0xFFFFFFFFFFFFFFFE, - }; - const unsigned n = sizeof (vals) / sizeof (vals[0]); - - for (unsigned i = 0; i < n; i++) - for (unsigned j = 0; j < n; j++) - { - u128 x = vals[i], y = vals[j]; - if (mulh_folded (x, y) != mulh_reference (x, y)) - __builtin_abort (); - for (unsigned k = 0; k < n; k++) - { - u128 z = vals[k]; - u128 want = mulh_reference (x, y) ^ mulh_reference (x, z); - if (mulh_shared_xor (x, y, z) != want) - __builtin_abort (); - u128 first = 0; - u128 h1 = mulh_reference (x, y); - if (mulh_chain_high (x, y, z, &first) != mulh_reference (h1, z) - || first != h1) - __builtin_abort (); - } - if (mulh_square (x) != mulh_reference (x, x)) - __builtin_abort (); - } - return 0; -} diff --git a/gcc/testsuite/gcc.dg/torture/long-mul-64-run.c b/gcc/testsuite/gcc.dg/torture/long-mul-64-run.c deleted file mode 100644 index 0824f453630a..000000000000 --- a/gcc/testsuite/gcc.dg/torture/long-mul-64-run.c +++ /dev/null @@ -1,180 +0,0 @@ -/* { dg-do run { target int128 } } */ - -/* Runtime behavior of the recognizer on the longhand 64x64 high-part - idiom. Two groups: shapes that must fold, checked against a 128-bit - reference multiply, and near misses that must not fold (each violates - one recognizer guard: low mask value, carry shift tie, cross-half - orientation, operand consistency), checked against their literal - meaning computed behind volatiles. Either way a misfold aborts. */ - -typedef __UINT64_TYPE__ uint64_t; -typedef unsigned __int128 uint128_t; - -/* The genuine idiom. */ -__attribute__((noipa)) uint64_t -mulh_good (uint64_t x, uint64_t y) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - uint64_t carry = (uint64_t) (hilo > low_sum) << 32; - return xh * yh + (low_sum >> 32) + carry; -} - -/* The idiom with an extra addend appended after the full chain: the - folded form must keep the addend on top of the wide multiply. */ -__attribute__((noipa)) uint64_t -mulh_acc (uint64_t x, uint64_t y, uint64_t acc) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - int carry_out = hilo > low_sum; - uint64_t carry = (uint64_t) carry_out << 32; - return xh * yh + (low_sum >> 32) + carry + acc; -} - -/* Same, with the extra addend interleaved into the middle of the - chain. */ -__attribute__((noipa)) uint64_t -mulh_acc_interleaved (uint64_t x, uint64_t y, uint64_t acc) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - int carry_out = hilo > low_sum; - uint64_t carry = (uint64_t) carry_out << 32; - return ((xh * yh + acc) + (low_sum >> 32)) + carry; -} - -/* Wrong low mask (0xFFFF, not the half mask). */ -__attribute__((noipa)) uint64_t -mulh_wrong_mask (uint64_t x, uint64_t y) -{ - uint64_t xl = x & 0xFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - uint64_t carry = (uint64_t) (hilo > low_sum) << 32; - return xh * yh + (low_sum >> 32) + carry; -} - -/* Wrong carry position (<< 16, not the half width). */ -__attribute__((noipa)) uint64_t -mulh_wrong_carry_shift (uint64_t x, uint64_t y) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - uint64_t carry = (uint64_t) (hilo > low_sum) << 16; - return xh * yh + (low_sum >> 32) + carry; -} - -/* Doubled cross term (hilo + hilo, same orientation). */ -__attribute__((noipa)) uint64_t -mulh_doubled_cross (uint64_t x, uint64_t y) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t cross = hilo + hilo; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - uint64_t carry = (uint64_t) (hilo > low_sum) << 32; - return xh * yh + (low_sum >> 32) + carry; -} - -/* Third operand sneaks into one cross term. */ -__attribute__((noipa)) uint64_t -mulh_mixed_ops (uint64_t x, uint64_t y, uint64_t z) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t zh = z >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * zh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - uint64_t carry = (uint64_t) (hilo > low_sum) << 32; - return xh * yh + (low_sum >> 32) + carry; -} - -/* What each (mis)shaped source literally means, computed behind - volatiles so no folding applies. */ -__attribute__((noipa)) uint64_t -ref_eval (uint64_t x, uint64_t y, uint64_t z, int variant) -{ - volatile uint64_t vx = x, vy = y, vz = z; - uint64_t xh = vx >> 32, yl0 = vy & 0xFFFFFFFF, yh = vy >> 32, zh = vz >> 32; - uint64_t xl, yl; - switch (variant) - { - case 1: xl = vx & 0xFFFF; yl = vy & 0xFFFF; break; - default: xl = vx & 0xFFFFFFFF; yl = yl0; break; - } - uint64_t hilo = xh * yl; - uint64_t lohi; - switch (variant) - { - case 3: lohi = hilo; break; - case 4: lohi = xl * zh; break; - default: lohi = xl * yh; break; - } - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - uint64_t shift = (variant == 2) ? 16 : 32; - uint64_t carry = (uint64_t) (hilo > low_sum) << shift; - return xh * yh + (low_sum >> 32) + carry; -} - -int -main (void) -{ - static const uint64_t vals[] = { - 0, 1, 0xFFFFFFFFULL, 0x100000000ULL, 0xFFFFFFFFFFFFFFFFULL, - 0xDEADBEEFCAFEBABEULL, 0x8000000080000000ULL, 0x00000001FFFFFFFFULL - }; - const int n = sizeof (vals) / sizeof (vals[0]); - for (int i = 0; i < n; i++) - for (int j = 0; j < n; j++) - { - uint64_t x = vals[i], y = vals[j], z = vals[(i + j) % n]; - uint64_t hi = (uint64_t) (((uint128_t) x * y) >> 64); - if (mulh_good (x, y) != hi) - __builtin_abort (); - if (mulh_acc (x, y, z) != hi + z) - __builtin_abort (); - if (mulh_acc_interleaved (x, y, z) != hi + z) - __builtin_abort (); - if (mulh_wrong_mask (x, y) != ref_eval (x, y, z, 1)) - __builtin_abort (); - if (mulh_wrong_carry_shift (x, y) != ref_eval (x, y, z, 2)) - __builtin_abort (); - if (mulh_doubled_cross (x, y) != ref_eval (x, y, z, 3)) - __builtin_abort (); - if (mulh_mixed_ops (x, y, z) != ref_eval (x, y, z, 4)) - __builtin_abort (); - } - return 0; -} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary-64.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary-64.c deleted file mode 100644 index d191f2217afb..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary-64.c +++ /dev/null @@ -1,417 +0,0 @@ -/* { dg-do run } */ -/* { dg-require-effective-target int128 } */ -/* { dg-options "-O3" } */ - -typedef __UINT64_TYPE__ uint64_t; -typedef unsigned __int128 uint128_t; - -/* Reference: high part of 64x64 -> 128 multiply. */ -__attribute__((noipa)) -uint64_t mulh_ref (uint64_t x, uint64_t y) -{ - return (uint64_t)(((uint128_t)x * y) >> 64); -} - -/* Carry pattern for high part. */ -__attribute__((noipa)) -uint64_t mulh_carry (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t mulhilo = x_hi * y_lo; - uint64_t mullohi = x_lo * y_hi; - uint64_t cross_sum = mulhilo + mullohi; - uint64_t mullolo = x_lo * y_lo; - uint64_t shrlolo = mullolo >> 32; - uint64_t add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - uint64_t cond = ((uint64_t) carry << 32) + x_hi * y_hi; - uint64_t add = cond + (add_cross_sum >> 32); - - return add; -} - -/* Ladder pattern for high part. */ -__attribute__((noipa)) -uint64_t mulh_ladder (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t t0 = y_lo * x_lo; - uint64_t t1 = y_lo * x_hi; - uint64_t t2 = y_hi * x_lo; - uint64_t t3 = y_hi * x_hi; - uint64_t t0_hi = t0 >> 32; - uint64_t u0 = t0_hi + t1; - uint64_t u0_lo = u0 & 0xFFFFFFFFUL; - uint64_t u0_hi = u0 >> 32; - uint64_t u1 = u0_lo + t2; - uint64_t u1_hi = u1 >> 32; - uint64_t u2 = u0_hi + t3; - uint64_t hw = u2 + u1_hi; - - return hw; -} - -/* Ladder-long full multiply (both high and low parts). */ -__attribute__((noipa)) -void full_mul (uint64_t x, uint64_t y, uint64_t *p) -{ - uint64_t xl = x & 0xFFFFFFFFUL; - uint64_t xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFFUL; - uint64_t yh = y >> 32; - uint64_t mulll = xl * yl; - uint64_t mullh = xl * yh; - uint64_t mulhl = xh * yl; - uint64_t mulhh = xh * yh; - uint64_t shr8 = mulll >> 32; - uint64_t conv10 = mullh & 0xFFFFFFFFUL; - uint64_t add = shr8 + conv10; - uint64_t conv12 = mulhl & 0xFFFFFFFFUL; - uint64_t add13 = add + conv12; - uint64_t shr14 = add13 >> 32; - uint64_t shr15 = mullh >> 32; - uint64_t add16 = mulhh + shr15; - uint64_t shr17 = mulhl >> 32; - uint64_t add18 = add16 + shr17; - uint64_t add19 = add18 + shr14; - p[1] = add19; - uint64_t add_13_shl = add13 << 32; - uint64_t and17 = mulll & 0xFFFFFFFFUL; - uint64_t or_val = add_13_shl | and17; - p[0] = or_val; -} - -/* Two-carry pattern for high part. */ -__attribute__((noipa)) -uint64_t mulh_two_carry (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = hilo + lohi; - uint64_t cross_carry = (uint64_t)(cross_sum < hilo) << 32; - - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = lolo + cross_shifted; - uint64_t low_carry = (uint64_t)(low_result < cross_shifted); - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry + low_carry; - - return high; -} - -/* Two-carry full multiply (both high and low parts). */ -__attribute__((noipa)) -void full_mul_two_carry (uint64_t x, uint64_t y, uint64_t *p) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = hilo + lohi; - uint64_t cross_carry = (uint64_t)(cross_sum < hilo) << 32; - - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = lolo + cross_shifted; - uint64_t low_carry = (uint64_t)(low_result < cross_shifted); - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry + low_carry; - - p[0] = low_result; - p[1] = high; -} - -/* Carry-long pattern for high part. */ -__attribute__((noipa)) -uint64_t mulh_carry_long (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t x_hi = x >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFFUL; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint64_t interm = cross_sum_hi + y_hi_x_hi; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t interm_plus_carry = interm + carry; - return interm_plus_carry + low_accum_hi; -} - -/* Carry-long full multiply (both high and low parts). */ -__attribute__((noipa)) -void full_mul_carry_long (uint64_t x, uint64_t y, uint64_t *p) -{ - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t x_hi = x >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFFUL; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint64_t upper_mid = y_hi_x_hi + carry; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t upper_mid_with_cross = upper_mid + cross_sum_hi; - p[1] = upper_mid_with_cross + low_accum_hi; - uint64_t low_accum_shifted = low_accum << 32; - uint64_t y_lo_x_lo_lo = y_lo_x_lo & 0xFFFFFFFFUL; - p[0] = low_accum_shifted | y_lo_x_lo_lo; -} - -/* Ladder-long pattern for high part. */ -__attribute__((noipa)) -uint64_t mulh_ladder_long (uint64_t x, uint64_t y) -{ - uint64_t xl = x & 0xFFFFFFFFUL; - uint64_t xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFFUL; - uint64_t yh = y >> 32; - uint64_t mulll = xl * yl; - uint64_t mullh = xl * yh; - uint64_t mulhl = xh * yl; - uint64_t mulhh = xh * yh; - uint64_t shr8 = mulll >> 32; - uint64_t conv10 = mullh & 0xFFFFFFFFUL; - uint64_t add = shr8 + conv10; - uint64_t conv12 = mulhl & 0xFFFFFFFFUL; - uint64_t add13 = add + conv12; - uint64_t shr14 = add13 >> 32; - uint64_t shr15 = mullh >> 32; - uint64_t add16 = mulhh + shr15; - uint64_t shr17 = mulhl >> 32; - uint64_t add18 = add16 + shr17; - return add18 + shr14; -} - -/* PHI-form, cond_carry_add (strict carry-on-true). */ -__attribute__((noipa)) -uint64_t mulh_carry_phi (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t mulhilo = x_hi * y_lo; - uint64_t mullohi = x_lo * y_hi; - uint64_t cross_sum = mulhilo + mullohi; - uint64_t mullolo = x_lo * y_lo; - uint64_t add_cross_sum = cross_sum + (mullolo >> 32); - uint64_t add = x_hi * y_hi + (add_cross_sum >> 32); - if (add_cross_sum < mulhilo) - add += (uint64_t)1 << 32; - return add; -} - -/* PHI-form, cond_carry_add_neg (negated branch, carry-on-false). */ -__attribute__((noipa)) -uint64_t mulh_carry_phi_neg (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t mulhilo = x_hi * y_lo; - uint64_t mullohi = x_lo * y_hi; - uint64_t cross_sum = mulhilo + mullohi; - uint64_t mullolo = x_lo * y_lo; - uint64_t add_cross_sum = cross_sum + (mullolo >> 32); - uint64_t add = x_hi * y_hi + (add_cross_sum >> 32); - if (add_cross_sum >= mulhilo) - ; - else - add += (uint64_t)1 << 32; - return add; -} - -/* PHI-form, cond_carry_add written as gt (operand-swapped from lt). */ -__attribute__((noipa)) -uint64_t mulh_carry_phi_gt (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t mulhilo = x_hi * y_lo; - uint64_t mullohi = x_lo * y_hi; - uint64_t cross_sum = mulhilo + mullohi; - uint64_t mullolo = x_lo * y_lo; - uint64_t add_cross_sum = cross_sum + (mullolo >> 32); - uint64_t add = x_hi * y_hi + (add_cross_sum >> 32); - if (mulhilo > add_cross_sum) - add += (uint64_t)1 << 32; - return add; -} - -/* PHI-form, cond_carry_add_neg written as le (operand-swapped from ge). */ -__attribute__((noipa)) -uint64_t mulh_carry_phi_le (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t mulhilo = x_hi * y_lo; - uint64_t mullohi = x_lo * y_hi; - uint64_t cross_sum = mulhilo + mullohi; - uint64_t mullolo = x_lo * y_lo; - uint64_t add_cross_sum = cross_sum + (mullolo >> 32); - uint64_t add = x_hi * y_hi + (add_cross_sum >> 32); - if (mulhilo <= add_cross_sum) - ; - else - add += (uint64_t)1 << 32; - return add; -} - -/* Low part via PLUS: lolo + (cross_sum << 32) with no comparison. */ -__attribute__((noipa)) -uint64_t mul_low_plus (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t cross_sum = hilo + lohi; - uint64_t cross_shifted = cross_sum << 32; - return lolo + cross_shifted; -} - -/* PHI-form, two-carry shape with the low carry as the PHI - (LMK_CARRY_LOW path in match_long_mul_phi). */ -__attribute__((noipa)) -uint64_t mulh_two_carry_low_phi (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = hilo + lohi; - uint64_t cross_carry = (uint64_t)(cross_sum < hilo) << 32; - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = lolo + cross_shifted; - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry; - if (low_result < cross_shifted) - high += 1; - - return high; -} - -int main () -{ - /* Boundary inputs: zero, one, half-word mask, half-word+1, signed max, - unsigned max. */ - uint64_t vals[] = { - 0, 1, 0xFFFFFFFFUL, 0x100000000ULL, - 0x7FFFFFFFFFFFFFFFULL, 0xFFFFFFFFFFFFFFFFULL - }; - int n = sizeof (vals) / sizeof (vals[0]); - - for (int i = 0; i < n; i++) - for (int j = 0; j < n; j++) - { - uint64_t x = vals[i], y = vals[j]; - uint64_t expected_hi = mulh_ref (x, y); - uint64_t expected_lo = x * y; - - if (mulh_carry (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_ladder (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_two_carry (x, y) != expected_hi) - __builtin_abort (); - - uint64_t p[2]; - full_mul (x, y, p); - if (p[1] != expected_hi) - __builtin_abort (); - if (p[0] != expected_lo) - __builtin_abort (); - - uint64_t q[2]; - full_mul_two_carry (x, y, q); - if (q[1] != expected_hi) - __builtin_abort (); - if (q[0] != expected_lo) - __builtin_abort (); - - if (mulh_carry_long (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_ladder_long (x, y) != expected_hi) - __builtin_abort (); - - uint64_t r[2]; - full_mul_carry_long (x, y, r); - if (r[1] != expected_hi) - __builtin_abort (); - if (r[0] != expected_lo) - __builtin_abort (); - - if (mulh_carry_phi (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_carry_phi_neg (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_carry_phi_gt (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_carry_phi_le (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_two_carry_low_phi (x, y) != expected_hi) - __builtin_abort (); - - if (mul_low_plus (x, y) != expected_lo) - __builtin_abort (); - } - - return 0; -} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary.c deleted file mode 100644 index 498481a01932..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-boundary.c +++ /dev/null @@ -1,394 +0,0 @@ -/* { dg-do run } */ -/* { dg-options "-O3" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; - -/* Reference: high part of 32x32 -> 64 multiply. */ -__attribute__((noipa)) -uint32_t mulh_ref (uint32_t x, uint32_t y) -{ - return (uint32_t)(((uint64_t)x * y) >> 32); -} - -/* Carry pattern for high part. */ -__attribute__((noipa)) -uint32_t mulh_carry (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t shrlolo = mullolo >> 16; - uint32_t add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - uint32_t cond = ((uint32_t) carry << 16) + x_hi * y_hi; - uint32_t add = cond + (add_cross_sum >> 16); - - return add; -} - -/* Ladder pattern for high part. */ -__attribute__((noipa)) -uint32_t mulh_ladder (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = y_hi * x_lo; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_lo = u0 & 0xFFFF; - uint32_t u0_hi = u0 >> 16; - uint32_t u1 = u0_lo + t2; - uint32_t u1_hi = u1 >> 16; - uint32_t u2 = u0_hi + t3; - uint32_t hw = u2 + u1_hi; - - return hw; -} - -/* Ladder-long pattern for full multiplication (both high and low parts). */ -__attribute__((noipa)) -void full_mul (uint32_t x, uint32_t y, uint32_t *p) -{ - uint32_t xl = x & 0xFFFF; - uint32_t xh = x >> 16; - uint32_t yl = y & 0xFFFF; - uint32_t yh = y >> 16; - uint32_t mulll = xl * yl; - uint32_t mullh = xl * yh; - uint32_t mulhl = xh * yl; - uint32_t mulhh = xh * yh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mullh & 0xFFFF; - uint32_t add = shr8 + conv10; - uint32_t conv12 = mulhl & 0xFFFF; - uint32_t add13 = add + conv12; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mullh >> 16; - uint32_t add16 = mulhh + shr15; - uint32_t shr17 = mulhl >> 16; - uint32_t add18 = add16 + shr17; - uint32_t add19 = add18 + shr14; - p[1] = add19; - uint32_t add_13_shl = add13 << 16; - uint32_t and17 = mulll & 0xFFFF; - uint32_t or_val = add_13_shl | and17; - p[0] = or_val; -} - -/* Two-carry pattern for high part (32-bit). */ -__attribute__((noipa)) -uint32_t mulh_two_carry (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - - uint32_t lolo = x_lo * y_lo; - uint32_t hilo = x_hi * y_lo; - uint32_t lohi = x_lo * y_hi; - uint32_t hihi = x_hi * y_hi; - - uint32_t cross_sum = hilo + lohi; - uint32_t cross_carry = (uint32_t)(cross_sum < hilo) << 16; - - uint32_t cross_shifted = cross_sum << 16; - uint32_t low_result = lolo + cross_shifted; - uint32_t low_carry = (uint32_t)(low_result < cross_shifted); - - uint32_t high = hihi + (cross_sum >> 16) + cross_carry + low_carry; - - return high; -} - -/* Two-carry full multiply (32-bit, both high and low parts). */ -__attribute__((noipa)) -void full_mul_two_carry (uint32_t x, uint32_t y, uint32_t *p) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - - uint32_t lolo = x_lo * y_lo; - uint32_t hilo = x_hi * y_lo; - uint32_t lohi = x_lo * y_hi; - uint32_t hihi = x_hi * y_hi; - - uint32_t cross_sum = hilo + lohi; - uint32_t cross_carry = (uint32_t)(cross_sum < hilo) << 16; - - uint32_t cross_shifted = cross_sum << 16; - uint32_t low_result = lolo + cross_shifted; - uint32_t low_carry = (uint32_t)(low_result < cross_shifted); - - uint32_t high = hihi + (cross_sum >> 16) + cross_carry + low_carry; - - p[0] = low_result; - p[1] = high; -} - -/* Carry-long pattern for high part. */ -__attribute__((noipa)) -uint32_t mulh_carry_long (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo_x_hi = y_lo * x_hi; - uint32_t y_hi_x_hi = y_hi * x_hi; - uint32_t y_hi_x_lo = y_hi * x_lo; - uint32_t y_lo_x_lo = y_lo * x_lo; - uint32_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint32_t carry = (uint32_t) carry_out << 16; - uint32_t y_lo_x_lo_hi = y_lo_x_lo >> 16; - uint32_t cross_sum_lo = cross_sum & 0xFFFF; - uint32_t cross_sum_hi = cross_sum >> 16; - uint32_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint32_t interm = cross_sum_hi + y_hi_x_hi; - uint32_t low_accum_hi = low_accum >> 16; - uint32_t interm_plus_carry = interm + carry; - return interm_plus_carry + low_accum_hi; -} - -/* Carry-long full multiply (both high and low parts). */ -__attribute__((noipa)) -void full_mul_carry_long (uint32_t x, uint32_t y, uint32_t *p) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo_x_hi = y_lo * x_hi; - uint32_t y_hi_x_hi = y_hi * x_hi; - uint32_t y_hi_x_lo = y_hi * x_lo; - uint32_t y_lo_x_lo = y_lo * x_lo; - uint32_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint32_t carry = (uint32_t) carry_out << 16; - uint32_t y_lo_x_lo_hi = y_lo_x_lo >> 16; - uint32_t cross_sum_lo = cross_sum & 0xFFFF; - uint32_t cross_sum_hi = cross_sum >> 16; - uint32_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint32_t upper_mid = y_hi_x_hi + carry; - uint32_t low_accum_hi = low_accum >> 16; - uint32_t upper_mid_with_cross = upper_mid + cross_sum_hi; - p[1] = upper_mid_with_cross + low_accum_hi; - uint32_t low_accum_shifted = low_accum << 16; - uint32_t y_lo_x_lo_lo = y_lo_x_lo & 0xFFFF; - p[0] = low_accum_shifted | y_lo_x_lo_lo; -} - -/* Ladder-long pattern for high part. */ -__attribute__((noipa)) -uint32_t mulh_ladder_long (uint32_t x, uint32_t y) -{ - uint32_t xl = x & 0xFFFF; - uint32_t xh = x >> 16; - uint32_t yl = y & 0xFFFF; - uint32_t yh = y >> 16; - uint32_t mulll = xl * yl; - uint32_t mullh = xl * yh; - uint32_t mulhl = xh * yl; - uint32_t mulhh = xh * yh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mullh & 0xFFFF; - uint32_t add = shr8 + conv10; - uint32_t conv12 = mulhl & 0xFFFF; - uint32_t add13 = add + conv12; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mullh >> 16; - uint32_t add16 = mulhh + shr15; - uint32_t shr17 = mulhl >> 16; - uint32_t add18 = add16 + shr17; - return add18 + shr14; -} - -/* PHI-form, cond_carry_add (strict carry-on-true). */ -__attribute__((noipa)) -uint32_t mulh_carry_phi (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum < mulhilo) - add += (uint32_t)1 << 16; - return add; -} - -/* PHI-form, cond_carry_add_neg (negated branch, carry-on-false). */ -__attribute__((noipa)) -uint32_t mulh_carry_phi_neg (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum >= mulhilo) - ; - else - add += (uint32_t)1 << 16; - return add; -} - -/* PHI-form, cond_carry_add written as gt (operand-swapped from lt). */ -__attribute__((noipa)) -uint32_t mulh_carry_phi_gt (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (mulhilo > add_cross_sum) - add += (uint32_t)1 << 16; - return add; -} - -/* PHI-form, cond_carry_add_neg written as le (operand-swapped from ge). */ -__attribute__((noipa)) -uint32_t mulh_carry_phi_le (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (mulhilo <= add_cross_sum) - ; - else - add += (uint32_t)1 << 16; - return add; -} - -/* PHI-form, two-carry shape with the low carry as the PHI - (LMK_CARRY_LOW path in match_long_mul_phi). */ -__attribute__((noipa)) -uint32_t mulh_two_carry_low_phi (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - - uint32_t lolo = x_lo * y_lo; - uint32_t hilo = x_hi * y_lo; - uint32_t lohi = x_lo * y_hi; - uint32_t hihi = x_hi * y_hi; - - uint32_t cross_sum = hilo + lohi; - uint32_t cross_carry = (uint32_t)(cross_sum < hilo) << 16; - uint32_t cross_shifted = cross_sum << 16; - uint32_t low_result = lolo + cross_shifted; - - uint32_t high = hihi + (cross_sum >> 16) + cross_carry; - if (low_result < cross_shifted) - high += 1; - - return high; -} - -int main () -{ - /* Boundary inputs: zero, one, half-word mask, half-word+1, signed max, - unsigned max. */ - uint32_t vals[] = { 0, 1, 0xFFFF, 0x10000, 0x7FFFFFFFU, 0xFFFFFFFFU }; - int n = sizeof (vals) / sizeof (vals[0]); - - for (int i = 0; i < n; i++) - for (int j = 0; j < n; j++) - { - uint32_t x = vals[i], y = vals[j]; - uint32_t expected_hi = mulh_ref (x, y); - uint32_t expected_lo = x * y; - - if (mulh_carry (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_ladder (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_two_carry (x, y) != expected_hi) - __builtin_abort (); - - uint32_t p[2]; - full_mul (x, y, p); - if (p[1] != expected_hi) - __builtin_abort (); - if (p[0] != expected_lo) - __builtin_abort (); - - uint32_t q[2]; - full_mul_two_carry (x, y, q); - if (q[1] != expected_hi) - __builtin_abort (); - if (q[0] != expected_lo) - __builtin_abort (); - - if (mulh_carry_long (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_ladder_long (x, y) != expected_hi) - __builtin_abort (); - - uint32_t r[2]; - full_mul_carry_long (x, y, r); - if (r[1] != expected_hi) - __builtin_abort (); - if (r[0] != expected_lo) - __builtin_abort (); - - if (mulh_carry_phi (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_carry_phi_neg (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_carry_phi_gt (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_carry_phi_le (x, y) != expected_hi) - __builtin_abort (); - - if (mulh_two_carry_low_phi (x, y) != expected_hi) - __builtin_abort (); - } - - return 0; -} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-carry.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-carry.c deleted file mode 100644 index 99165656918f..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-carry.c +++ /dev/null @@ -1,385 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3 -fdump-tree-forwprop-details -fdump-tree-widening_mul-details" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; -typedef struct { uint32_t v[2]; } v2i32; - -/* High part follows the long form - xh*yh + carry + (cross_sum >> N) + (low_accum >> N). */ - -uint64_t mulh_carry (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = cross_sum < y_lo_x_hi; - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFF; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint64_t interm = cross_sum_hi + y_hi_x_hi; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t interm_plus_carry = interm + carry; - uint64_t hw64 = interm_plus_carry + low_accum_hi; - - return hw64; -} - -uint64_t mulh_carry_comm (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = x_hi * y_lo; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = x_lo * y_hi; - uint64_t y_lo_x_lo = x_lo * y_lo; - uint64_t cross_sum = y_lo_x_hi + y_hi_x_lo; - int carry_out = (cross_sum < y_lo_x_hi); - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFF; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = y_lo_x_lo_hi + cross_sum_lo; - uint64_t inter = y_hi_x_hi + cross_sum_hi; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t interm_plus_carry = carry + inter; - uint64_t hw64 = low_accum_hi + interm_plus_carry; - - return hw64; -} - -uint32_t mulh_carry_32 (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo_x_hi = y_lo * x_hi; - uint32_t y_hi_x_hi = y_hi * x_hi; - uint32_t y_hi_x_lo = y_hi * x_lo; - uint32_t y_lo_x_lo = y_lo * x_lo; - uint32_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint32_t carry = (uint32_t) carry_out << 16; - uint32_t y_lo_x_lo_hi = y_lo_x_lo >> 16; - uint32_t cross_sum_lo = cross_sum & 0xFFFF; - uint32_t cross_sum_hi = cross_sum >> 16; - uint32_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint32_t interm = cross_sum_hi + y_hi_x_hi; - uint32_t low_accum_hi = low_accum >> 16; - uint32_t interm_plus_carry = interm + carry; - uint32_t hw64 = interm_plus_carry + low_accum_hi; - - return hw64; -} - -/* The 128-bit variant lowers to longhand in pass_optimize_widening_mul; - no target provides a 256-bit multiply. */ -#ifdef __SIZEOF_INT128__ -__uint128_t mulh_carry_128 (__uint128_t x, __uint128_t y) -{ - __uint128_t x_lo = x & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t x_hi = x >> 64; - __uint128_t y_lo = y & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t y_hi = y >> 64; - __uint128_t y_lo_x_hi = y_lo * x_hi; - __uint128_t y_hi_x_hi = y_hi * x_hi; - __uint128_t y_hi_x_lo = y_hi * x_lo; - __uint128_t y_lo_x_lo = y_lo * x_lo; - __uint128_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = cross_sum < y_lo_x_hi; - __uint128_t carry = (__uint128_t) carry_out << 64; - __uint128_t y_lo_x_lo_hi = y_lo_x_lo >> 64; - __uint128_t cross_sum_lo = cross_sum & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t cross_sum_hi = cross_sum >> 64; - __uint128_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - __uint128_t interm = cross_sum_hi + y_hi_x_hi; - __uint128_t low_accum_hi = low_accum >> 64; - __uint128_t interm_plus_carry = interm + carry; - __uint128_t hw64 = interm_plus_carry + low_accum_hi; - - return hw64; -} -#endif - -void full_mul_carry (uint64_t x, uint64_t y, uint64_t* p) { - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFF; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint64_t upper_mid = y_hi_x_hi + carry; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t upper_mid_with_cross = upper_mid + cross_sum_hi; - uint64_t hw64 = upper_mid_with_cross + low_accum_hi; - p[1] = hw64; - uint64_t low_accum_shifted = low_accum << 32; - uint64_t y_lo_x_lo_lo = y_lo_x_lo & 0xFFFFFFFF; - uint64_t lw64 = low_accum_shifted | y_lo_x_lo_lo; - p[0] = lw64; -} - -/* This will be optimized during the second forwprop run. - Disable SLP so the expected fold count is target-independent. */ -__attribute__((optimize("no-tree-slp-vectorize"))) -v2i32 mulh_carry_v2i32 (v2i32 x, v2i32 y) -{ - v2i32 result; - for (int i = 0; i < 2; i++) - { - uint32_t x_lo = x.v[i] & 0xFFFF; - uint32_t y_lo = y.v[i] & 0xFFFF; - uint32_t x_hi = x.v[i] >> 16; - uint32_t y_hi = y.v[i] >> 16; - - uint32_t y_lo_x_hi = y_lo * x_hi; - uint32_t y_hi_x_hi = y_hi * x_hi; - uint32_t y_hi_x_lo = y_hi * x_lo; - uint32_t y_lo_x_lo = y_lo * x_lo; - - uint32_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = cross_sum < y_lo_x_hi; - uint32_t carry = (uint32_t) carry_out << 16; - - uint32_t y_lo_x_lo_hi = y_lo_x_lo >> 16; - uint32_t cross_sum_lo = cross_sum & 0xFFFF; - uint32_t cross_sum_hi = cross_sum >> 16; - - uint32_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint32_t interm = cross_sum_hi + y_hi_x_hi; - uint32_t low_accum_hi = low_accum >> 16; - uint32_t interm_plus_carry = interm + carry; - - result.v[i] = interm_plus_carry + low_accum_hi; - } - - return result; -} - -/* High part collapses the cross sum and (xl*yl >> N) into a single - low_sum carrying the overflow compare: - xh*yh + (low_sum >> N) + ((hilo > low_sum) << N). */ - -uint32_t mulh_carry_low_sum (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t shrlolo = mullolo >> 16; - uint32_t low_sum = cross_sum + shrlolo; - int carry = low_sum < mulhilo; - uint32_t cond = ((uint32_t) carry << 16) + x_hi * y_hi; - uint32_t add = cond + (low_sum >> 16); - - return add; -} - -void full_mul_carry_low_sum (uint32_t x, uint32_t y, uint32_t* p) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t shrlolo = mullolo >> 16; - uint32_t low_sum = cross_sum + shrlolo; - int carry = low_sum < mulhilo; - uint32_t cond = ((uint32_t) carry << 16) + x_hi * y_hi; - uint32_t add = cond + (low_sum >> 16); - p[1] = add; - uint32_t low_sum_shr = low_sum << 16; - uint32_t mullololo = mullolo & 0xFFFF; - uint32_t low = low_sum_shr | mullololo; - p[0] = low; -} - -uint32_t mulh_carry_low_sum_comm (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = y_lo * x_hi; - uint32_t mullohi = y_hi * x_lo; - uint32_t cross_sum = mullohi + mulhilo; - uint32_t mullolo = x_lo * y_lo; - uint32_t shrlolo = mullolo >> 16; - uint32_t low_sum = shrlolo + cross_sum; - int carry = low_sum < mulhilo; - uint32_t cond = ((uint32_t) carry << 16) + x_hi * y_hi; - uint32_t add = cond + (low_sum >> 16); - - return add; -} - -uint32_t mulh_carry_low_sum_lohi (uint32_t x, uint32_t y) { - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t low_sum = cross_sum + (mullolo >> 16); - int carry_occurred = (low_sum < mullohi); - uint32_t cond = (uint32_t) carry_occurred << 16; - uint32_t add = x_hi * y_hi + cond + (low_sum >> 16); - - return add; -} - -/* The 128-bit variant will fail during the high sequence generation - (no target provides a 256-bit multiply) and is excluded from the - expected fold counts below. */ -#ifdef __SIZEOF_INT128__ -__uint128_t mulh_carry_low_sum_128 (__uint128_t x, __uint128_t y) -{ - __uint128_t x_hi = x >> 64; - __uint128_t x_lo = x & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t y_hi = y >> 64; - __uint128_t y_lo = y & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t mulhilo = x_hi * y_lo; - __uint128_t mullohi = x_lo * y_hi; - __uint128_t cross_sum = mulhilo + mullohi; - __uint128_t mullolo = x_lo * y_lo; - __uint128_t shrlolo = mullolo >> 64; - __uint128_t low_sum = cross_sum + shrlolo; - int carry = low_sum < mulhilo; - __uint128_t cond = ((__uint128_t) carry << 64) + x_hi * y_hi; - __uint128_t add = cond + (low_sum >> 64); - - return add; -} -#endif - -/* This will be optimized during the second forwprop run. - Disable SLP so the expected fold count is target-independent. */ -__attribute__((optimize("no-tree-slp-vectorize"))) -v2i32 mulh_carry_low_sum_v2i32 (v2i32 x, v2i32 y) -{ - v2i32 result; - for (int i = 0; i < 2; i++) - { - uint32_t x_hi = x.v[i] >> 16; - uint32_t x_lo = x.v[i] & 0xFFFF; - uint32_t y_hi = y.v[i] >> 16; - uint32_t y_lo = y.v[i] & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t shrlolo = mullolo >> 16; - uint32_t low_sum = cross_sum + shrlolo; - int carry = low_sum < mulhilo; - uint32_t cond = ((uint32_t) carry << 16) + x_hi * y_hi; - uint32_t add = cond + (low_sum >> 16); - result.v[i] = add; - } - - return result; -} - -/* PHI-form coverage: the carry summand is the join of a 2-arg PHI - guarded by an unsigned compare, recognized by cond_carry_add / - cond_carry_add_neg and folded by match_long_mul_phi. */ - -uint32_t mulh_carry_phi (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum < mulhilo) - add += (uint32_t)1 << 16; - return add; -} - -uint64_t mulh_carry_long_phi (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFF; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + (y_lo_x_lo >> 32); - uint64_t hw64 = y_hi_x_hi + cross_sum_hi + (low_accum >> 32); - if (cross_sum < y_lo_x_hi) - hw64 += (uint64_t)1 << 32; - return hw64; -} - -/* PHI-form, cond_carry_add_neg (negated branch, carry-on-false). */ -uint32_t mulh_carry_phi_neg (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum >= mulhilo) - ; - else - add += (uint32_t)1 << 16; - return add; -} - -/* On targets with __int128 support the two 128-bit highparts also - fold; without it they are elided by #ifdef and the count drops - by 2. */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 10 "forwprop1" { target { oi_mode && int128 } } } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 8 "forwprop1" { target { ! { oi_mode && int128 } } } } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 2 "forwprop2" } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication low part folded\\." 2 "forwprop1" } } */ -/* Three PHI-form highparts, one per polarity pair (gt via mulh_carry_phi - and mulh_carry_long_phi, le via mulh_carry_phi_neg). */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded \\(carry PHI\\)" 3 "forwprop1" } } */ -/* Only the two 128-bit (OImode) chains are lowered. sparc64 and hppa64 - have OImode and __int128 but no native DImode high part, so their u64 - chains lower too and the count would exceed 2; exclude them. */ -/* { dg-final { scan-tree-dump-times "Lowered long-mul high-part chain" 2 "widening_mul" { target { { oi_mode && int128 } && { ! { sparc*-*-* hppa*-*-* } } } } } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-chain-cse-128.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-chain-cse-128.c deleted file mode 100644 index 53b5eba9e2db..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-chain-cse-128.c +++ /dev/null @@ -1,52 +0,0 @@ -/* { dg-do compile { target { oi_mode && int128 } } } */ -/* { dg-options "-O3 -fdump-tree-forwprop1-details -fdump-tree-optimized" } */ - -/* Two differently-spelled high-part longhands of the same 128x128 - product both fold to the canonical (u256) x * (u256) y >> 128, so - value numbering proves them equal and the function folds to 0. */ - -typedef __uint128_t u128; - -u128 both_spellings (u128 x, u128 y) -{ - /* Spelling 1: overflow-compare carry form. */ - u128 x_hi = x >> 64; - u128 x_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - u128 y_hi = y >> 64; - u128 y_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 mulhilo = x_hi * y_lo; - u128 mullohi = x_lo * y_hi; - u128 cross_sum = mulhilo + mullohi; - u128 mullolo = x_lo * y_lo; - u128 shrlolo = mullolo >> 64; - u128 add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - u128 cond = ((u128) carry << 64) + x_hi * y_hi; - u128 h1 = cond + (add_cross_sum >> 64); - - /* Spelling 2: ladder form. */ - u128 a_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - u128 b_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 a_hi = x >> 64; - u128 b_hi = y >> 64; - u128 t0 = b_lo * a_lo; - u128 t1 = b_lo * a_hi; - u128 t2 = b_hi * a_lo; - u128 t3 = b_hi * a_hi; - u128 t0_hi = t0 >> 64; - u128 u0 = t0_hi + t1; - u128 u0_lo = u0 & (u128)0xFFFFFFFFFFFFFFFF; - u128 u0_hi = u0 >> 64; - u128 u1 = u0_lo + t2; - u128 u1_hi = u1 >> 64; - u128 u2 = u0_hi + t3; - u128 h2 = u2 + u1_hi; - - return h1 ^ h2; -} - -/* Both spellings are recognized. */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded." 2 "forwprop1" } } */ -/* Once canonical, VN proves them equal and the function folds to 0. */ -/* { dg-final { scan-tree-dump "return 0;" "optimized" } } */ -/* { dg-final { scan-tree-dump-not " \\* " "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-chain-trunc-128.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-chain-trunc-128.c deleted file mode 100644 index 00f0338df5e2..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-chain-trunc-128.c +++ /dev/null @@ -1,80 +0,0 @@ -/* { dg-do run { target int128 } } */ -/* { dg-options "-O3" } */ - -/* A user cast of the recognized 128-bit high part merges with the - chain's final truncation, so widening_mul lowering sees an outermost - convert to a type narrower than 128 bits. Checks it builds the - longhand at narrow precision and converts to the lhs type. */ - -typedef __uint128_t u128; -typedef unsigned long long u64; -typedef unsigned int u32; - -static inline u128 -mulh128 (u128 x, u128 y) -{ - u128 x_hi = x >> 64; - u128 x_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - u128 y_hi = y >> 64; - u128 y_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 mulhilo = x_hi * y_lo; - u128 mullohi = x_lo * y_hi; - u128 cross_sum = mulhilo + mullohi; - u128 mullolo = x_lo * y_lo; - u128 shrlolo = mullolo >> 64; - u128 add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - u128 cond = ((u128) carry << 64) + x_hi * y_hi; - return cond + (add_cross_sum >> 64); -} - -__attribute__((noipa)) u64 -trunc64 (u128 x, u128 y) { return (u64) mulh128 (x, y); } - -__attribute__((noipa)) u32 -trunc32 (u128 x, u128 y) { return (u32) mulh128 (x, y); } - -__attribute__((noipa)) u128 -mulh_reference (u128 x, u128 y) -{ - volatile u128 x_hi = x >> 64; - volatile u128 x_lo = x & (u128)0xFFFFFFFFFFFFFFFF; - volatile u128 y_hi = y >> 64; - volatile u128 y_lo = y & (u128)0xFFFFFFFFFFFFFFFF; - u128 mulhilo = x_hi * y_lo; - u128 mullohi = x_lo * y_hi; - u128 cross_sum = mulhilo + mullohi; - u128 mullolo = x_lo * y_lo; - u128 shrlolo = mullolo >> 64; - u128 add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - u128 cond = ((u128) carry << 64) + x_hi * y_hi; - return cond + (add_cross_sum >> 64); -} - -int -main (void) -{ - static const u128 vals[] = { - 0, - 1, - (u128)0xFFFFFFFFFFFFFFFF, - ((u128)1 << 64), - ((u128)1 << 127), - ~(u128)0, - ((u128)0xDEADBEEFCAFEBABE << 64) | 0x0123456789ABCDEF, - ((u128)0x8000000000000001 << 64) | 0xFFFFFFFFFFFFFFFE, - }; - const unsigned n = sizeof (vals) / sizeof (vals[0]); - - for (unsigned i = 0; i < n; i++) - for (unsigned j = 0; j < n; j++) - { - u128 ref = mulh_reference (vals[i], vals[j]); - if (trunc64 (vals[i], vals[j]) != (u64) ref) - __builtin_abort (); - if (trunc32 (vals[i], vals[j]) != (u32) ref) - __builtin_abort (); - } - return 0; -} diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-extra-addend.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-extra-addend.c deleted file mode 100644 index 5e36a1592ec2..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-extra-addend.c +++ /dev/null @@ -1,63 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3 -fdump-tree-forwprop-details" } */ - -/* Chains carrying addends that are not part of the long-multiply idiom - (an accumulator merged in by reassociation, a foreign shifted term) - must still fold, with the extra addends preserved on top of the wide - multiply. A leaf that classifies as a long-mul summand but breaks - operand consistency kills the match instead (no subset retry). */ - -typedef __UINT64_TYPE__ uint64_t; - -/* Extra addend appended after the full high-part chain. Folds. */ -uint64_t -mulh_acc (uint64_t x, uint64_t y, uint64_t acc) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - int carry_out = hilo > low_sum; - uint64_t carry = (uint64_t) carry_out << 32; - return xh * yh + (low_sum >> 32) + carry + acc; -} - -/* Extra addend interleaved into the middle of the chain. Folds. */ -uint64_t -mulh_acc_interleaved (uint64_t x, uint64_t y, uint64_t acc) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - int carry_out = hilo > low_sum; - uint64_t carry = (uint64_t) carry_out << 32; - return ((xh * yh + acc) + (low_sum >> 32)) + carry; -} - -/* Foreign leaf that classifies as a summand (a second high-high - product of different operands): consumed by the multiset, operand - consistency fails, no fold. */ -uint64_t -mulh_foreign_hihi (uint64_t x, uint64_t y, uint64_t a, uint64_t b) -{ - uint64_t xl = x & 0xFFFFFFFF, xh = x >> 32; - uint64_t yl = y & 0xFFFFFFFF, yh = y >> 32; - uint64_t ah = a >> 32, bh = b >> 32; - uint64_t hilo = xh * yl; - uint64_t lohi = xl * yh; - uint64_t cross = hilo + lohi; - uint64_t lolo = xl * yl; - uint64_t low_sum = cross + (lolo >> 32); - int carry_out = hilo > low_sum; - uint64_t carry = (uint64_t) carry_out << 32; - return xh * yh + (low_sum >> 32) + carry + ah * bh; -} - -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded" 2 "forwprop1" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-ladder.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-ladder.c deleted file mode 100644 index 7b7384d86455..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-ladder.c +++ /dev/null @@ -1,333 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3 -fdump-tree-forwprop-details -fdump-tree-widening_mul-details" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; -typedef struct { uint32_t v[2]; } v2i32; -typedef struct { uint64_t v[2]; } v2i64; - -uint64_t mulh_ladder (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t t0 = y_lo * x_lo; - uint64_t t1 = y_lo * x_hi; - uint64_t t2 = y_hi * x_lo; - uint64_t t3 = y_hi * x_hi; - uint64_t t0_hi = t0 >> 32; - uint64_t u0 = t0_hi + t1; - uint64_t u0_lo = u0 & 0xFFFFFFFF; - uint64_t u0_hi = u0 >> 32; - uint64_t u1 = u0_lo + t2; - uint64_t u1_hi = u1 >> 32; - uint64_t u2 = u0_hi + t3; - uint64_t hw64 = u2 + u1_hi; - - return hw64; -} - -uint64_t mulh_ladder_comm (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t t0 = x_lo * y_lo; - uint64_t t1 = x_lo * y_hi; - uint64_t t2 = x_hi * y_lo; - uint64_t t3 = x_hi * y_hi; - uint64_t t0_hi = t0 >> 32; - uint64_t u0 = t1 + t0_hi; - uint64_t u0_lo = u0 & 0xFFFFFFFF; - uint64_t u0_hi = u0 >> 32; - uint64_t u1 = t2 + u0_lo; - uint64_t u1_hi = u1 >> 32; - uint64_t u2 = u1_hi + u0_hi; - uint64_t hw64 = t3 + u2; - - return hw64; -} - -uint32_t mulh_ladder_32 (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = y_hi * x_lo; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_lo = u0 & 0xFFFF; - uint32_t u0_hi = u0 >> 16; - uint32_t u1 = u0_lo + t2; - uint32_t u1_hi = u1 >> 16; - uint32_t u2 = u0_hi + t3; - uint32_t hw64 = u2 + u1_hi; - - return hw64; -} - -/* The 128-bit variant lowers to longhand in pass_optimize_widening_mul; - no target provides a 256-bit multiply. */ -#ifdef __SIZEOF_INT128__ -__uint128_t umulh_variant_i128 (__uint128_t x, __uint128_t y) -{ - __uint128_t x_lo = x & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t y_lo = y & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t x_hi = x >> 64; - __uint128_t y_hi = y >> 64; - __uint128_t t0 = y_lo * x_lo; - __uint128_t t1 = y_lo * x_hi; - __uint128_t t2 = y_hi * x_lo; - __uint128_t t3 = y_hi * x_hi; - __uint128_t t0_hi = t0 >> 64; - __uint128_t u0 = t0_hi + t1; - __uint128_t u0_lo = u0 & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t u0_hi = u0 >> 64; - __uint128_t u1 = u0_lo + t2; - __uint128_t u1_hi = u1 >> 64; - __uint128_t u2 = u0_hi + t3; - __uint128_t hw64 = u2 + u1_hi; - - return hw64; -} -#endif - -v2i64 full_mul_ladder (uint64_t x, uint64_t y) -{ - uint64_t and_x = x & 0xFFFFFFFF; - uint64_t and_y = y & 0xFFFFFFFF; - uint64_t mul_i = and_y * and_x; - uint64_t shr_x = x >> 32; - uint64_t mul_i27 = and_y * shr_x; - uint64_t shr_y = y >> 32; - uint64_t mul_i28 = shr_y * and_x; - uint64_t mul_i29 = shr_y * shr_x; - uint64_t shr10 = mul_i >> 32; - uint64_t and11 = mul_i27 & 0xFFFFFFFF; - uint64_t add = and11 + mul_i28; - uint64_t add12 = add + shr10; - uint64_t shr13 = mul_i27 >> 32; - uint64_t shr14 = add12 >> 32; - uint64_t add15 = shr13 + mul_i29; - uint64_t add16 = add15 + shr14; - uint64_t shl = add12 << 32; - uint64_t and17 = mul_i & 0xFFFFFFFF; - uint64_t or_val = shl | and17; - v2i64 result; - result.v[0] = or_val; - result.v[1] = add16; - return result; -} - -/* This will be optimized during the second forwprop run. - Disable SLP so the expected fold count is target-independent. */ -__attribute__((optimize("no-tree-slp-vectorize"))) -v2i32 mulh_ladder_v2i32 (v2i32 x, v2i32 y) -{ - v2i32 result; - for(int i=0; i<2; ++i) - { - uint32_t x_lo = x.v[i] & 0xFFFF; - uint32_t y_lo = y.v[i] & 0xFFFF; - uint32_t x_hi = x.v[i] >> 16; - uint32_t y_hi = y.v[i] >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = y_hi * x_lo; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_lo = u0 & 0xFFFF; - uint32_t u0_hi = u0 >> 16; - uint32_t u1 = u0_lo + t2; - uint32_t u1_hi = u1 >> 16; - uint32_t u2 = u0_hi + t3; - result.v[i] = u2 + u1_hi; - } - - return result; -} - -/* Ladder-long variants: hi-part sum uses the long form - (xh*yh + cross_hi_a + cross_hi_b + mid_hi). */ - -uint32_t mulh_ladder_long (uint32_t x, uint32_t y) -{ - uint32_t xl = x & 0xFFFF; - uint32_t xh = x >> 16; - uint32_t yl = y & 0xFFFF; - uint32_t yh = y >> 16; - uint32_t mulll = xl * yl; - uint32_t mullh = xl * yh; - uint32_t mulhl = xh * yl; - uint32_t mulhh = xh * yh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mullh & 0xFFFF; - uint32_t add = shr8 + conv10; - uint32_t conv12 = mulhl & 0xFFFF; - uint32_t add13 = add + conv12; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mullh >> 16; - uint32_t add16 = mulhh + shr15; - uint32_t shr17 = mulhl >> 16; - uint32_t add18 = add16 + shr17; - uint32_t add19 = add18 + shr14; - - return add19; -} - -void full_mul_ladder_long (uint32_t x, uint32_t y, uint32_t *p) -{ - uint32_t xl = x & 0xFFFF; - uint32_t xh = x >> 16; - uint32_t yl = y & 0xFFFF; - uint32_t yh = y >> 16; - uint32_t mulll = xl * yl; - uint32_t mullh = xl * yh; - uint32_t mulhl = xh * yl; - uint32_t mulhh = xh * yh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mullh & 0xFFFF; - uint32_t add = shr8 + conv10; - uint32_t conv12 = mulhl & 0xFFFF; - uint32_t add13 = add + conv12; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mullh >> 16; - uint32_t add16 = mulhh + shr15; - uint32_t shr17 = mulhl >> 16; - uint32_t add18 = add16 + shr17; - uint32_t add19 = add18 + shr14; - p[1] = add19; - uint32_t add_13_shl = add13 << 16; - uint32_t and17 = mulll & 0xFFFF; - uint32_t or_val = add_13_shl | and17; - p[0] = or_val; -} - -uint32_t mulh_ladder_long_comm (uint32_t x, uint32_t y) -{ - uint32_t xl = x & 0xFFFF; - uint32_t xh = x >> 16; - uint32_t yl = y & 0xFFFF; - uint32_t yh = y >> 16; - uint32_t mulll = yl * xl; - uint32_t mullh = yh * xl; - uint32_t mulhl = yl * xh; - uint32_t mulhh = yh * xh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mullh & 0xFFFF; - uint32_t add = conv10 + shr8; - uint32_t conv12 = mulhl & 0xFFFF; - uint32_t add13 = conv12 + add; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mullh >> 16; - uint32_t shr17 = mulhl >> 16; - uint32_t add16 = shr14 + shr17; - uint32_t add18 = add16 + shr15; - uint32_t add19 = mulhh + add18; - - return add19; -} - -/* The 128-bit variant lowers to longhand in pass_optimize_widening_mul; - no target provides a 256-bit multiply. */ -#ifdef __SIZEOF_INT128__ -__uint128_t mulh_ladder_long_128 (__uint128_t x, __uint128_t y) -{ - __uint128_t xl = x & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t xh = x >> 64; - __uint128_t yl = y & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t yh = y >> 64; - __uint128_t mulll = xl * yl; - __uint128_t mullh = xl * yh; - __uint128_t mulhl = xh * yl; - __uint128_t mulhh = xh * yh; - __uint128_t shr8 = mulll >> 64; - __uint128_t conv10 = mullh & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t add = shr8 + conv10; - __uint128_t conv12 = mulhl & (__uint128_t)0xFFFFFFFFFFFFFFFF; - __uint128_t add13 = add + conv12; - __uint128_t shr14 = add13 >> 64; - __uint128_t shr15 = mullh >> 64; - __uint128_t add16 = mulhh + shr15; - __uint128_t shr17 = mulhl >> 64; - __uint128_t add18 = add16 + shr17; - __uint128_t add19 = add18 + shr14; - - return add19; -} -#endif - -uint32_t mulh_ladder_long_hllh (uint32_t x, uint32_t y) -{ - uint32_t xl = x & 0xFFFF; - uint32_t xh = x >> 16; - uint32_t yl = y & 0xFFFF; - uint32_t yh = y >> 16; - uint32_t mulll = xl * yl; - uint32_t mullh = xl * yh; - uint32_t mulhl = xh * yl; - uint32_t mulhh = xh * yh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mulhl & 0xFFFF; - uint32_t add = shr8 + conv10; - uint32_t conv12 = mullh & 0xFFFF; - uint32_t add13 = add + conv12; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mulhl >> 16; - uint32_t add16 = mulhh + shr15; - uint32_t shr17 = mullh >> 16; - uint32_t add18 = add16 + shr17; - uint32_t add19 = add18 + shr14; - - return add19; -} - -/* This will be optimized during the second forwprop run. - Disable SLP so the expected fold count is target-independent. */ -__attribute__((optimize("no-tree-slp-vectorize"))) -v2i32 mul_ladder_long_v2i32 (v2i32 x, v2i32 y) -{ - v2i32 result; - for (int i = 0; i < 2; i++) - { - uint32_t xl = x.v[i] & 0xFFFF; - uint32_t xh = x.v[i] >> 16; - uint32_t yl = y.v[i] & 0xFFFF; - uint32_t yh = y.v[i] >> 16; - uint32_t mulll = xl * yl; - uint32_t mullh = xl * yh; - uint32_t mulhl = xh * yl; - uint32_t mulhh = xh * yh; - uint32_t shr8 = mulll >> 16; - uint32_t conv10 = mullh & 0xFFFF; - uint32_t add = shr8 + conv10; - uint32_t conv12 = mulhl & 0xFFFF; - uint32_t add13 = add + conv12; - uint32_t shr14 = add13 >> 16; - uint32_t shr15 = mullh >> 16; - uint32_t add16 = mulhh + shr15; - uint32_t shr17 = mulhl >> 16; - uint32_t add18 = add16 + shr17; - result.v[i] = add18 + shr14; - } - - return result; -} - -/* On targets with __int128 support the 128-bit highpart also folds; - without it it is elided by #ifdef and the count drops by 2. */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 10 "forwprop1" { target { oi_mode && int128 } } } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 8 "forwprop1" { target { ! { oi_mode && int128 } } } } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 2 "forwprop2" } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication low part folded\\." 2 "forwprop1" } } */ -/* Only the two 128-bit (OImode) chains are lowered. sparc64 and hppa64 - have OImode and __int128 but no native DImode high part, so their u64 - chains lower too and the count would exceed 2; exclude them. */ -/* { dg-final { scan-tree-dump-times "Lowered long-mul high-part chain" 2 "widening_mul" { target { { oi_mode && int128 } && { ! { sparc*-*-* hppa*-*-* } } } } } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-low-plus.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-low-plus.c deleted file mode 100644 index 37c0193ece09..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-low-plus.c +++ /dev/null @@ -1,54 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3 -fdump-tree-forwprop-details" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; - -/* Low part via PLUS form: lolo + (cross_sum << halfwidth). - No GT/LT comparison on the result, so long_mul_check_low_plus_defer - should fold without deferring. */ -uint32_t mul_low_plus_32 (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t lolo = x_lo * y_lo; - uint32_t hilo = x_hi * y_lo; - uint32_t lohi = x_lo * y_hi; - uint32_t cross_sum = hilo + lohi; - uint32_t cross_shifted = cross_sum << 16; - return lolo + cross_shifted; -} - -/* 64-bit variant. */ -uint64_t mul_low_plus_64 (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t cross_sum = hilo + lohi; - uint64_t cross_shifted = cross_sum << 32; - return lolo + cross_shifted; -} - -/* Commuted operand order. */ -uint32_t mul_low_plus_comm (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t lolo = y_lo * x_lo; - uint32_t hilo = y_lo * x_hi; - uint32_t lohi = y_hi * x_lo; - uint32_t cross_sum = lohi + hilo; - uint32_t cross_shifted = cross_sum << 16; - return cross_shifted + lolo; -} - -/* { dg-final { scan-tree-dump-times "Long multiplication low part folded." 3 "forwprop1" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-partial.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-partial.c deleted file mode 100644 index 7b239e2439e1..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-partial.c +++ /dev/null @@ -1,193 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3 -fdump-tree-optimized" } */ - -typedef __UINT32_TYPE__ uint32_t; - -/* Only one cross-product (xh*yl), missing xl*yh. - Should NOT be folded. */ -uint32_t partial_one_cross (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_hi = u0 >> 16; - return t3 + u0_hi; -} - -/* Only xl*yl and xh*yh, no cross-products at all. - Should NOT be folded. */ -uint32_t partial_no_cross (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t3 = y_hi * x_hi; - return t3 + (t0 >> 16); -} - -/* Only cross-products, missing xl*yl and xh*yh. - Should NOT be folded. */ -uint32_t partial_only_cross (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = y_hi * x_lo; - return (t1 + t2) >> 16; -} - -/* Full ladder structure but one cross-product uses z instead of y. - long_mul_check_consistency should reject the mismatched operand. - Should NOT be folded. */ -uint32_t partial_mismatched_op (uint32_t x, uint32_t y, uint32_t z) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t z_lo = z & 0xFFFF; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = z_lo * x_lo; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_lo = u0 & 0xFFFF; - uint32_t u0_hi = u0 >> 16; - uint32_t u1 = u0_lo + t2; - uint32_t u1_hi = u1 >> 16; - uint32_t u2 = u0_hi + t3; - return u2 + u1_hi; -} - -/* Uses conditionals in the computation. - Should NOT be folded. */ -unsigned mulhu_conditional (unsigned u, unsigned v) { - unsigned a, b, c, d, p, q, rlow, rhigh; - - a = u >> 16; - b = u & 0xFFFF; - c = v >> 16; - d = v & 0xFFFF; - - p = a*c; - q = b*d; - rlow = (-a + b)*(c - d); - rhigh = (int)((-a + b)^(c - d)) >> 31; - if (rlow == 0) rhigh = 0; - - q = q + (q >> 16); - rlow = rlow + p; - if (rlow < p) rhigh = rhigh + 1; - rlow = rlow + q; - if (rlow < q) rhigh = rhigh + 1; - - return p + (rlow >> 16) + (rhigh << 16); -} - -/* Signed operands. - Should NOT be folded. */ -int mulhs_signed (int u, int v) { - unsigned u0, v0, w0; - int u1, v1, w1, w2, t; - - u0 = u & 0xFFFF; - u1 = u >> 16; - v0 = v & 0xFFFF; - v1 = v >> 16; - w0 = u0*v0; - t = u1*v0 + (w0 >> 16); - w1 = t & 0xFFFF; - w2 = t >> 16; - w1 = u0*v1 + w1; - return u1*v1 + w2 + (w1 >> 16); -} - -/* PHI-form near-miss: non-power-of-two carry increment. - match.pd rejects via integer_pow2p@3. - Should NOT be folded. */ -uint32_t partial_phi_nonpow2 (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16, x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16, y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum < mulhilo) - add += (uint32_t)3 << 16; - return add; -} - -/* PHI-form near-miss: carry increment shifted by less than halfwidth. - match_long_mul_phi rejects via shift_amt == halfwidth. - Should NOT be folded. */ -uint32_t partial_phi_wrong_shift (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16, x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16, y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum < mulhilo) - add += (uint32_t)1 << 15; - return add; -} - -/* PHI-form near-miss: equality compare in place of the strict carry - predicate. cond_carry_add and cond_carry_add_neg only encode - gt / lt / le / ge. - Should NOT be folded. */ -uint32_t partial_phi_wrong_compare (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16, x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16, y_lo = y & 0xFFFF; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * y_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum == mulhilo) - add += (uint32_t)1 << 16; - return add; -} - -/* PHI-form near-miss: one cross-product uses z instead of y. - long_mul_check_consistency rejects the inconsistent (op0, op1). - Should NOT be folded. */ -uint32_t partial_phi_wrong_cross (uint32_t x, uint32_t y, uint32_t z) -{ - uint32_t x_hi = x >> 16, x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16, y_lo = y & 0xFFFF; - uint32_t z_hi = z >> 16; - uint32_t mulhilo = x_hi * y_lo; - uint32_t mullohi = x_lo * z_hi; - uint32_t cross_sum = mulhilo + mullohi; - uint32_t mullolo = x_lo * y_lo; - uint32_t add_cross_sum = cross_sum + (mullolo >> 16); - uint32_t add = x_hi * y_hi + (add_cross_sum >> 16); - if (add_cross_sum < mulhilo) - add += (uint32_t)1 << 16; - return add; -} - -/* Verify no fold in any forwprop pass by checking the optimized IR - for MULT_HIGHPART_EXPR (h*) and WIDEN_MULT_EXPR (w*). */ -/* { dg-final { scan-tree-dump-not " h\\* " "optimized" } } */ -/* { dg-final { scan-tree-dump-not " w\\* " "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-two-carry.c b/gcc/testsuite/gcc.dg/tree-ssa/long-mul-two-carry.c deleted file mode 100644 index effed8262469..000000000000 --- a/gcc/testsuite/gcc.dg/tree-ssa/long-mul-two-carry.c +++ /dev/null @@ -1,140 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3 -fdump-tree-forwprop-details" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; - -/* High part using two separate carries (cross carry + low carry). */ -uint64_t mulh_two_carry (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = hilo + lohi; - uint64_t cross_carry = (uint64_t)(cross_sum < hilo) << 32; - - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = lolo + cross_shifted; - uint64_t low_carry = (uint64_t)(low_result < cross_shifted); - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry + low_carry; - - return high; -} - -/* Commuted operand order. */ -uint64_t mulh_two_carry_comm (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hilo = x_hi * y_lo; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = lohi + hilo; - uint64_t cross_carry = (uint64_t)(cross_sum < lohi) << 32; - - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = cross_shifted + lolo; - uint64_t low_carry = (uint64_t)(low_result < lolo); - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry + low_carry; - - return high; -} - -/* 32-bit variant. */ -uint32_t mulh_two_carry_32 (uint32_t x, uint32_t y) -{ - uint32_t x_hi = x >> 16; - uint32_t x_lo = x & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo = y & 0xFFFF; - - uint32_t lolo = x_lo * y_lo; - uint32_t hilo = x_hi * y_lo; - uint32_t lohi = x_lo * y_hi; - uint32_t hihi = x_hi * y_hi; - - uint32_t cross_sum = hilo + lohi; - uint32_t cross_carry = (uint32_t)(cross_sum < hilo) << 16; - - uint32_t cross_shifted = cross_sum << 16; - uint32_t low_result = lolo + cross_shifted; - uint32_t low_carry = (uint32_t)(low_result < cross_shifted); - - uint32_t high = hihi + (cross_sum >> 16) + cross_carry + low_carry; - - return high; -} - -/* Full multiply: both high and low parts. */ -uint64_t full_mul_two_carry (uint64_t x, uint64_t y, uint64_t *lo) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = hilo + lohi; - uint64_t cross_carry = (uint64_t)(cross_sum < hilo) << 32; - - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = lolo + cross_shifted; - uint64_t low_carry = (uint64_t)(low_result < cross_shifted); - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry + low_carry; - - *lo = low_result; - return high; -} - -/* Low carry written as an if-branch + 2-arg PHI. Exercises - match_long_mul_phi's LMK_CARRY_LOW path (shift = 0). */ -uint64_t mulh_two_carry_low_phi (uint64_t x, uint64_t y) -{ - uint64_t x_hi = x >> 32; - uint64_t x_lo = x & 0xFFFFFFFFUL; - uint64_t y_hi = y >> 32; - uint64_t y_lo = y & 0xFFFFFFFFUL; - - uint64_t lolo = x_lo * y_lo; - uint64_t hilo = x_hi * y_lo; - uint64_t lohi = x_lo * y_hi; - uint64_t hihi = x_hi * y_hi; - - uint64_t cross_sum = hilo + lohi; - uint64_t cross_carry = (uint64_t)(cross_sum < hilo) << 32; - uint64_t cross_shifted = cross_sum << 32; - uint64_t low_result = lolo + cross_shifted; - - uint64_t high = hihi + (cross_sum >> 32) + cross_carry; - if (low_result < cross_shifted) - high += 1; - - return high; -} - -/* The LOW fold for full_mul_two_carry lands in forwprop4 because - `lolo + cross_shifted' also feeds the HIGH fold's low-carry - compare; long_mul_check_low_plus_defer holds it until the HIGH - fold has consumed the compare. */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded\\." 4 "forwprop3" } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication high part folded \\(carry PHI\\)" 1 "forwprop3" } } */ -/* { dg-final { scan-tree-dump-times "Long multiplication low part folded\\." 1 "forwprop4" } } */ diff --git a/gcc/testsuite/gcc.target/aarch64/long_mul.c b/gcc/testsuite/gcc.target/aarch64/long_mul.c deleted file mode 100644 index f9c765380d8c..000000000000 --- a/gcc/testsuite/gcc.target/aarch64/long_mul.c +++ /dev/null @@ -1,100 +0,0 @@ -/* { dg-do compile } */ -/* { dg-options "-O3" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; - -/* 64-bit ladder pattern for high part. */ -uint64_t mulh_ladder (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t t0 = y_lo * x_lo; - uint64_t t1 = y_lo * x_hi; - uint64_t t2 = y_hi * x_lo; - uint64_t t3 = y_hi * x_hi; - uint64_t t0_hi = t0 >> 32; - uint64_t u0 = t0_hi + t1; - uint64_t u0_lo = u0 & 0xFFFFFFFF; - uint64_t u0_hi = u0 >> 32; - uint64_t u1 = u0_lo + t2; - uint64_t u1_hi = u1 >> 32; - uint64_t u2 = u0_hi + t3; - return u2 + u1_hi; -} - -/* 64-bit carry pattern for high part. */ -uint64_t mulh_carry (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = cross_sum < y_lo_x_hi; - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFF; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint64_t interm = cross_sum_hi + y_hi_x_hi; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t interm_plus_carry = interm + carry; - return interm_plus_carry + low_accum_hi; -} - -/* 32-bit ladder pattern for high part. */ -uint32_t mulh_ladder_32 (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = y_hi * x_lo; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_lo = u0 & 0xFFFF; - uint32_t u0_hi = u0 >> 16; - uint32_t u1 = u0_lo + t2; - uint32_t u1_hi = u1 >> 16; - uint32_t u2 = u0_hi + t3; - return u2 + u1_hi; -} - -/* 32-bit carry pattern for high part. */ -uint32_t mulh_carry_32 (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo_x_hi = y_lo * x_hi; - uint32_t y_hi_x_hi = y_hi * x_hi; - uint32_t y_hi_x_lo = y_hi * x_lo; - uint32_t y_lo_x_lo = y_lo * x_lo; - uint32_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint32_t carry = (uint32_t) carry_out << 16; - uint32_t y_lo_x_lo_hi = y_lo_x_lo >> 16; - uint32_t cross_sum_lo = cross_sum & 0xFFFF; - uint32_t cross_sum_hi = cross_sum >> 16; - uint32_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint32_t interm = cross_sum_hi + y_hi_x_hi; - uint32_t low_accum_hi = low_accum >> 16; - uint32_t interm_plus_carry = interm + carry; - return interm_plus_carry + low_accum_hi; -} - -/* 64-bit patterns should emit umulh. */ -/* { dg-final { scan-assembler-times "umulh\t" 2 } } */ -/* 32-bit patterns should emit umull (32x32->64 widening multiply). */ -/* { dg-final { scan-assembler-times "umull\t" 2 } } */ diff --git a/gcc/testsuite/gcc.target/arm/long-mul-thumb1-inline.c b/gcc/testsuite/gcc.target/arm/long-mul-thumb1-inline.c deleted file mode 100644 index f36b4739d3a6..000000000000 --- a/gcc/testsuite/gcc.target/arm/long-mul-thumb1-inline.c +++ /dev/null @@ -1,47 +0,0 @@ -/* { dg-do compile } */ -/* { dg-require-effective-target arm_thumb1_ok } */ -/* { dg-options "-O2 -mthumb -mcpu=cortex-m0 -fdump-tree-forwprop1-details -fdump-tree-widening_mul-details" } */ - -/* Thumb-1 (cortex-m0) has no umull and no DImode multiply, so a DImode - multiply would expand to the __aeabi_lmul libcall. widening_mul - re-synthesizes the recognized u32 high part from the HImode widening - multiply Thumb-1 does have, so no libcall is emitted. */ - -typedef __INT32_TYPE__ i32; -typedef __UINT32_TYPE__ u32; -typedef __UINT64_TYPE__ u64; - -u32 mulh32 (u32 x, u32 y) -{ - u32 x_hi = x >> 16, x_lo = x & 0xFFFF; - u32 y_hi = y >> 16, y_lo = y & 0xFFFF; - u32 mulhilo = x_hi * y_lo; - u32 mullohi = x_lo * y_hi; - u32 cross_sum = mulhilo + mullohi; - u32 mullolo = x_lo * y_lo; - u32 shrlolo = mullolo >> 16; - u32 acs = cross_sum + shrlolo; - int carry = acs < mulhilo; - u32 cond = ((u32) carry << 16) + x_hi * y_hi; - return cond + (acs >> 16); -} - -/* Signed operands sign-extended into the unsigned wide type. The atom - accepts them via `(convert? @X)'; long_mul_split_operand must sign- - extend the narrow operand into the high half (arithmetic shift by - N-1 on the signed narrow) -- a broken sign-extend branch would - zero the high and miscompile any negative input. */ -u32 mulhs_split (i32 a, i32 b) -{ - return (u32) (((u64) a * (u64) b) >> 32); -} - -/* Recognizer canonicalizes; widening_mul re-synthesizes the longhand. */ -/* { dg-final { scan-tree-dump "Long multiplication high part folded" "forwprop1" } } */ -/* { dg-final { scan-tree-dump-times "Lowered long-mul high-part chain" 2 "widening_mul" } } */ -/* No multiplication libcall: the longhand stays inline. */ -/* { dg-final { scan-assembler-not "__aeabi_lmul" } } */ -/* Split's signed branch emits an arithmetic shift by narrow_prec-1 on - each signed narrow source of mulhs_split -- once per operand, - absent when broken. */ -/* { dg-final { scan-tree-dump-times "\\(D\\) >> 31" 2 "widening_mul" } } */ diff --git a/gcc/testsuite/gcc.target/arm/long-mul-umull.c b/gcc/testsuite/gcc.target/arm/long-mul-umull.c deleted file mode 100644 index 721b640f7b70..000000000000 --- a/gcc/testsuite/gcc.target/arm/long-mul-umull.c +++ /dev/null @@ -1,73 +0,0 @@ -/* { dg-do compile } */ -/* { dg-require-effective-target arm_arm_ok } */ -/* { dg-options "-O2 -marm -fdump-tree-widening_mul-details" } */ - -/* With umull available, the recognizer folds the u32 high-part longhand - to a DImode multiply that becomes a single umull, while the u64 - longhand becomes a TImode chain that widening_mul re-synthesizes as - four umull. No libcalls. */ - -typedef __UINT64_TYPE__ u64; -typedef __UINT32_TYPE__ u32; - -u32 mulh32 (u32 x, u32 y) -{ - u32 x_hi = x >> 16, x_lo = x & 0xFFFF; - u32 y_hi = y >> 16, y_lo = y & 0xFFFF; - u32 mulhilo = x_hi * y_lo; - u32 mullohi = x_lo * y_hi; - u32 cross_sum = mulhilo + mullohi; - u32 mullolo = x_lo * y_lo; - u32 shrlolo = mullolo >> 16; - u32 acs = cross_sum + shrlolo; - int carry = acs < mulhilo; - u32 cond = ((u32) carry << 16) + x_hi * y_hi; - return cond + (acs >> 16); -} - -u64 mulh64 (u64 x, u64 y) -{ - u64 x_hi = x >> 32, x_lo = x & 0xFFFFFFFF; - u64 y_hi = y >> 32, y_lo = y & 0xFFFFFFFF; - u64 mulhilo = x_hi * y_lo; - u64 mullohi = x_lo * y_hi; - u64 cross_sum = mulhilo + mullohi; - u64 mullolo = x_lo * y_lo; - u64 shrlolo = mullolo >> 32; - u64 acs = cross_sum + shrlolo; - int carry = acs < mulhilo; - u64 cond = ((u64) carry << 32) + x_hi * y_hi; - return cond + (acs >> 32); -} - -/* Two longhands chained through the low half, with the first high part also - live. After recognition the second chain reads its operand off the first - product as a masked low half, so lowering both leaves a live TImode - multiply the target cannot expand. */ - -u64 chain_low (u64 a, u64 b, u64 c, u64 *hi1) -{ - *hi1 = mulh64 (a, b); - return mulh64 (a * b, c); -} - -/* The same through the high half: after recognition the second chain - multiplies by the first product shifted down, and truncating that shift - would leave the product live instead. */ - -u64 chain_high (u64 a, u64 b, u64 c, u64 *hi1) -{ - u64 h1 = mulh64 (a, b); - *hi1 = h1; - return mulh64 (h1, c); -} - -/* mulh32 collapses to one umull and mulh64 lowers to four; chain_low and - chain_high inline two longhands each, for nine and eight. */ -/* { dg-final { scan-assembler-times "\tumull\t" 22 } } */ -/* One lowering in mulh64 and two in each chain. mulh32 contributes none: - its DImode multiply is converted to a widening multiply instead. */ -/* { dg-final { scan-tree-dump-times "Lowered long-mul high-part chain" 5 "widening_mul" } } */ -/* { dg-final { scan-tree-dump "Narrowed low-half-only long multiply" "widening_mul" } } */ -/* { dg-final { scan-assembler-not "__aeabi_lmul" } } */ -/* { dg-final { scan-assembler-not "__multi3" } } */ diff --git a/gcc/testsuite/gcc.target/i386/long_mul.c b/gcc/testsuite/gcc.target/i386/long_mul.c deleted file mode 100644 index d4b03ed1beda..000000000000 --- a/gcc/testsuite/gcc.target/i386/long_mul.c +++ /dev/null @@ -1,100 +0,0 @@ -/* { dg-do compile { target { ! ia32 } } } */ -/* { dg-options "-O3" } */ - -typedef __UINT32_TYPE__ uint32_t; -typedef __UINT64_TYPE__ uint64_t; - -/* 64-bit ladder pattern for high part. */ -uint64_t mulh_ladder (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_hi = y >> 32; - uint64_t t0 = y_lo * x_lo; - uint64_t t1 = y_lo * x_hi; - uint64_t t2 = y_hi * x_lo; - uint64_t t3 = y_hi * x_hi; - uint64_t t0_hi = t0 >> 32; - uint64_t u0 = t0_hi + t1; - uint64_t u0_lo = u0 & 0xFFFFFFFF; - uint64_t u0_hi = u0 >> 32; - uint64_t u1 = u0_lo + t2; - uint64_t u1_hi = u1 >> 32; - uint64_t u2 = u0_hi + t3; - return u2 + u1_hi; -} - -/* 64-bit carry pattern for high part. */ -uint64_t mulh_carry (uint64_t x, uint64_t y) -{ - uint64_t x_lo = x & 0xFFFFFFFF; - uint64_t x_hi = x >> 32; - uint64_t y_lo = y & 0xFFFFFFFF; - uint64_t y_hi = y >> 32; - uint64_t y_lo_x_hi = y_lo * x_hi; - uint64_t y_hi_x_hi = y_hi * x_hi; - uint64_t y_hi_x_lo = y_hi * x_lo; - uint64_t y_lo_x_lo = y_lo * x_lo; - uint64_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = cross_sum < y_lo_x_hi; - uint64_t carry = (uint64_t) carry_out << 32; - uint64_t y_lo_x_lo_hi = y_lo_x_lo >> 32; - uint64_t cross_sum_lo = cross_sum & 0xFFFFFFFF; - uint64_t cross_sum_hi = cross_sum >> 32; - uint64_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint64_t interm = cross_sum_hi + y_hi_x_hi; - uint64_t low_accum_hi = low_accum >> 32; - uint64_t interm_plus_carry = interm + carry; - return interm_plus_carry + low_accum_hi; -} - -/* 32-bit ladder pattern for high part. */ -uint32_t mulh_ladder_32 (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t y_lo = y & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_hi = y >> 16; - uint32_t t0 = y_lo * x_lo; - uint32_t t1 = y_lo * x_hi; - uint32_t t2 = y_hi * x_lo; - uint32_t t3 = y_hi * x_hi; - uint32_t t0_hi = t0 >> 16; - uint32_t u0 = t0_hi + t1; - uint32_t u0_lo = u0 & 0xFFFF; - uint32_t u0_hi = u0 >> 16; - uint32_t u1 = u0_lo + t2; - uint32_t u1_hi = u1 >> 16; - uint32_t u2 = u0_hi + t3; - return u2 + u1_hi; -} - -/* 32-bit carry pattern for high part. */ -uint32_t mulh_carry_32 (uint32_t x, uint32_t y) -{ - uint32_t x_lo = x & 0xFFFF; - uint32_t x_hi = x >> 16; - uint32_t y_lo = y & 0xFFFF; - uint32_t y_hi = y >> 16; - uint32_t y_lo_x_hi = y_lo * x_hi; - uint32_t y_hi_x_hi = y_hi * x_hi; - uint32_t y_hi_x_lo = y_hi * x_lo; - uint32_t y_lo_x_lo = y_lo * x_lo; - uint32_t cross_sum = y_hi_x_lo + y_lo_x_hi; - int carry_out = (cross_sum < y_lo_x_hi); - uint32_t carry = (uint32_t) carry_out << 16; - uint32_t y_lo_x_lo_hi = y_lo_x_lo >> 16; - uint32_t cross_sum_lo = cross_sum & 0xFFFF; - uint32_t cross_sum_hi = cross_sum >> 16; - uint32_t low_accum = cross_sum_lo + y_lo_x_lo_hi; - uint32_t interm = cross_sum_hi + y_hi_x_hi; - uint32_t low_accum_hi = low_accum >> 16; - uint32_t interm_plus_carry = interm + carry; - return interm_plus_carry + low_accum_hi; -} - -/* 64-bit patterns should emit mulq (unsigned 64x64->128 multiply). */ -/* { dg-final { scan-assembler-times "\tmulq" 2 } } */ -/* 32-bit patterns should emit imulq (64-bit multiply of zero-extended operands). */ -/* { dg-final { scan-assembler-times "\timulq" 2 } } */ diff --git a/gcc/testsuite/gcc.target/i386/widen_mult_high_chain.c b/gcc/testsuite/gcc.target/i386/widen_mult_high_chain.c deleted file mode 100644 index 7cfa42c9b3a5..000000000000 --- a/gcc/testsuite/gcc.target/i386/widen_mult_high_chain.c +++ /dev/null @@ -1,32 +0,0 @@ -/* { dg-do compile { target { lp64 } } } */ -/* { dg-options "-O3" } */ - -/* The high 128 bits of a 128 x 128 -> 256 product has no widening - multiply (no TI x TI -> OI) and no 256-bit expansion path. forwprop - folds the longhand to the canonical (uint256_t) a * (uint256_t) b - >> 128 shape, and widening_mul re-synthesizes it from four - 64 x 64 -> 128 multiplies (mulq). No __mulOI3 libcall. */ - -__uint128_t -mulh_carry_128 (__uint128_t x, __uint128_t y) -{ - __uint128_t x_hi = x >> 64; - __uint128_t x_lo = x & (__uint128_t) 0xFFFFFFFFFFFFFFFF; - __uint128_t y_hi = y >> 64; - __uint128_t y_lo = y & (__uint128_t) 0xFFFFFFFFFFFFFFFF; - __uint128_t mulhilo = x_hi * y_lo; - __uint128_t mullohi = x_lo * y_hi; - __uint128_t cross_sum = mulhilo + mullohi; - __uint128_t mullolo = x_lo * y_lo; - __uint128_t shrlolo = mullolo >> 64; - __uint128_t add_cross_sum = cross_sum + shrlolo; - int carry = add_cross_sum < mulhilo; - __uint128_t cond = ((__uint128_t) carry << 64) + x_hi * y_hi; - __uint128_t add = cond + (add_cross_sum >> 64); - - return add; -} - -/* { dg-final { scan-assembler-not "__multi3" } } */ -/* { dg-final { scan-assembler-not "__mulOI3" } } */ -/* { dg-final { scan-assembler-times "\tmulq" 4 } } */ diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index e6edd6233a23..42cbb5ce3df0 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -4983,26 +4983,6 @@ proc check_effective_target_int128 { } { }] } -# Return 1 if the target's mode table includes OImode (a 256-bit -# scalar_int_mode). Enumerated from `INT_MODE (OI, 32)' declarations -# in gcc/config/*/*-modes.def. - -proc check_effective_target_oi_mode { } { - return [check_cached_effective_target oi_mode { - expr { [istarget aarch64*-*-*] - || [istarget i?86-*-*] - || [istarget x86_64-*-*] - || [istarget riscv*-*-*] - || [istarget sparc*-*-*] - || [istarget s390*-*-*] - || [istarget loongarch*-*-*] - || [istarget arm*-*-*] - || [istarget alpha*-*-*] - || [istarget ia64-*-*] - || [istarget hppa*-*-*] } - }] -} - # Return 1 if the target supports unsigned int->float conversion # diff --git a/gcc/tree-ssa-forwprop.cc b/gcc/tree-ssa-forwprop.cc index 645ccfb301a2..75f06c6ba410 100644 --- a/gcc/tree-ssa-forwprop.cc +++ b/gcc/tree-ssa-forwprop.cc @@ -58,7 +58,6 @@ along with GCC; see the file COPYING3. If not see #include "tree-ssa.h" #include "gimple-range.h" #include "tree-ssa-dce.h" -#include "tree-ssa-math-opts.h" /* This pass propagates the RHS of assignment statements into use sites of the LHS of the assignment. It's basically a specialized @@ -3624,1177 +3623,6 @@ simplify_count_zeroes (gimple_stmt_iterator *gsi) return true; } -/* Long-multiply fold framework. - - Walks the outer addition or bit_ior chain on a candidate statement, - classifies each summand against the atom match patterns from - match.pd, and looks the resulting multiset of (kind, extract) tuples - up in a table. On a hit, three cross-summand consistency checks - decide whether the wide multiply is emitted. */ - -/* Match.pd recognizers for the conditional carry-add pattern. The - two names split the gcond polarity: cond_carry_add matches when - the true edge selects (base + pow2), cond_carry_add_neg when the - true edge selects base. */ - -extern bool gimple_cond_carry_add (tree, tree *, tree (*)(tree)); -extern bool gimple_cond_carry_add_neg (tree, tree *, tree (*)(tree)); - -/* Match.pd functions to match long multiplication. */ - -extern bool gimple_mul_hi (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_lo (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_hilo (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_lolo (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_hihi (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_cross_sum (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_low_sum (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_low_accum (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_carry_cross_sum (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_carry_low_sum (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_carry_low (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_ladder_sum1 (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_ladder_sum2 (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_ladder_sum3 (tree, tree *, tree (*)(tree)); -extern bool gimple_mul_ladder_part_sum (tree, tree *, tree (*)(tree)); - -/* Append to SEQ statements assigning DEST the high-part multiply of - OP1 and OP2, emitted as - (N)(((2N) op1 * (2N) op2) >> N). - pass_optimize_widening_mul's convert_mult_to_widen and - convert_mult_to_highpart later rewrite this to a single - WIDEN_MULT_EXPR or MULT_HIGHPART_EXPR when the target supports it, - otherwise the 2N multiply expands directly. Emitting the canonical - widening shape keeps target-capability decisions in the layer that - already owns them. */ - -static void -build_mul_high_seq (tree op1, tree op2, tree dest, location_t loc, - gimple_seq *seq) -{ - tree op_type = TREE_TYPE (op1); - unsigned int width = TYPE_PRECISION (op_type); - tree wide_type = build_nonstandard_integer_type (width * 2, 1); - - tree wide_a = gimple_convert (seq, loc, wide_type, op1); - tree wide_b = gimple_convert (seq, loc, wide_type, op2); - tree wide_prod = gimple_build (seq, loc, MULT_EXPR, wide_type, - wide_a, wide_b); - tree hi = gimple_build (seq, loc, RSHIFT_EXPR, wide_type, wide_prod, - build_int_cst (integer_type_node, width)); - - gimple *prod = gimple_build_assign (dest, NOP_EXPR, hi); - gimple_set_location (prod, loc); - gimple_seq_add_stmt (seq, prod); -} - -/* Append to SEQ statements combining ACC with each of EXTRAS under - OUTER, the last one assigning to STMT's lhs. EXTRAS are leaves of - STMT's own chain, so any combining order is valid. */ - -static void -long_mul_apply_extras (tree acc, const vec<tree> &extras, tree_code outer, - gassign *stmt, gimple_seq *seq) -{ - location_t loc = gimple_location (stmt); - tree lhs = gimple_assign_lhs (stmt); - for (unsigned i = 0; i + 1 < extras.length (); i++) - acc = gimple_build (seq, loc, outer, TREE_TYPE (lhs), acc, extras[i]); - gimple *last = gimple_build_assign (lhs, outer, acc, extras.last ()); - gimple_set_location (last, loc); - gimple_seq_add_stmt (seq, last); -} - -/* Replace STMT with a high-part multiply of OP1 and OP2, combining any - EXTRAS back on top under OUTER. */ - -static void -create_mul_high_seq (tree op1, tree op2, gassign *stmt, - const vec<tree> &extras, tree_code outer) -{ - gimple_seq seq = NULL; - tree lhs = gimple_assign_lhs (stmt); - tree dest = extras.is_empty () ? lhs : make_ssa_name (TREE_TYPE (lhs)); - build_mul_high_seq (op1, op2, dest, gimple_location (stmt), &seq); - if (!extras.is_empty ()) - long_mul_apply_extras (dest, extras, outer, stmt, &seq); - gimple_stmt_iterator gsi = gsi_for_stmt (stmt); - gsi_replace_with_seq (&gsi, seq, true); -} - -/* Replace STMT with a low-part multiply of OP1 and OP2, combining any - EXTRAS back on top under OUTER. */ - -static void -create_mul_low_seq (tree op1, tree op2, gassign *stmt, - const vec<tree> &extras, tree_code outer) -{ - gimple_seq seq = NULL; - tree lhs = gimple_assign_lhs (stmt); - tree dest = extras.is_empty () ? lhs : make_ssa_name (TREE_TYPE (lhs)); - gimple *prod = gimple_build_assign (dest, MULT_EXPR, op1, op2); - gimple_set_location (prod, gimple_location (stmt)); - gimple_seq_add_stmt (&seq, prod); - if (!extras.is_empty ()) - long_mul_apply_extras (dest, extras, outer, stmt, &seq); - gimple_stmt_iterator gsi = gsi_for_stmt (stmt); - gsi_replace_with_seq (&gsi, seq, true); -} - -/* Widest match.pd atom (mul_carry_low_sum) takes 7 captures; round up - to 8 for the scratch buffers below. */ -static constexpr unsigned LONG_MUL_MAX_CAPTURES = 8; - -/* Longest variant in long_mul_table has 4 summands. */ -static constexpr unsigned LONG_MUL_MAX_SUMMANDS = 4; - -/* Cap on the leaves set aside as not part of the idiom, so an - arbitrarily long unrelated chain still bails early. */ -static constexpr unsigned LONG_MUL_MAX_EXTRAS = 4; - -enum long_mul_kind { - LMK_MUL_HIHI, - LMK_MUL_LOLO, - LMK_MUL_HILO, - LMK_CROSS_SUM, - LMK_LOW_ACCUM, - LMK_LOW_SUM, - LMK_LADDER_SUM1, - LMK_LADDER_SUM2, - LMK_LADDER_SUM3, - LMK_LADDER_PART_SUM, - LMK_CARRY_LOW, - LMK_CARRY_CROSS_SUM, - LMK_CARRY_LOW_SUM, -}; - -/* How the leaf wraps its inner kind. Carry kinds use LMX_NONE: their - match.pd pattern bakes the lshift in, so the leaf is already the - complete carry expression. */ - -enum long_mul_extract { - LMX_NONE, - LMX_HI, - LMX_LO, - LMX_SHL_N, -}; - -struct long_mul_summand { - long_mul_kind kind; - long_mul_extract extract; - tree op0, op1; - tree hilo0, hilo1, hilo2; - tree carry_a, carry_b; - unsigned HOST_WIDE_INT shift; - unsigned HOST_WIDE_INT mask; -}; - -/* Walk the OUTER addition or BIT_IOR chain rooted at STMT and collect - the leaf operands into LEAVES. Descends through single-use - intermediate stmts of the same code. Returns false once the leaf - count exceeds LONG_MUL_MAX_SUMMANDS + LONG_MUL_MAX_EXTRAS, so an - overlong chain bails mid-walk instead of after a full traversal. - - If SHARED_DEF_OUT is non-NULL, record there the first inner stmt that - shares the outer code but has more than one use -- descending into it - would change semantics, so it stays as a leaf. Such a leaf often - classifies as something no row matches, silently disabling the fold; - the caller surfaces this as a dump-file hint. */ - -static bool -long_mul_linearize_chain (gimple *stmt, tree_code outer, vec<tree> &leaves, - gimple **shared_def_out = NULL) -{ - auto_vec<tree, 8> stack; - stack.safe_push (gimple_assign_rhs2 (stmt)); - stack.safe_push (gimple_assign_rhs1 (stmt)); - - while (!stack.is_empty ()) - { - tree t = stack.pop (); - if (TREE_CODE (t) == SSA_NAME) - { - gimple *def = SSA_NAME_DEF_STMT (t); - if (def - && is_gimple_assign (def) - && gimple_assign_rhs_code (def) == outer) - { - if (has_single_use (t)) - { - stack.safe_push (gimple_assign_rhs2 (def)); - stack.safe_push (gimple_assign_rhs1 (def)); - continue; - } - if (shared_def_out && !*shared_def_out) - *shared_def_out = def; - } - } - leaves.safe_push (t); - if (leaves.length () > LONG_MUL_MAX_SUMMANDS + LONG_MUL_MAX_EXTRAS) - return false; - } - return !leaves.is_empty (); -} - -/* If EXPR is defined by LSHIFT_EXPR with a uhwi-valued amount, return - the shifted input via *INNER_OUT and the amount via *SHIFT_OUT. */ - -static bool -long_mul_is_lshift_def (tree expr, tree *inner_out, - unsigned HOST_WIDE_INT *shift_out) -{ - if (TREE_CODE (expr) != SSA_NAME) - return false; - gimple *def = SSA_NAME_DEF_STMT (expr); - if (!def || !is_gimple_assign (def) - || gimple_assign_rhs_code (def) != LSHIFT_EXPR) - return false; - tree amount = gimple_assign_rhs2 (def); - if (!tree_fits_uhwi_p (amount)) - return false; - *inner_out = gimple_assign_rhs1 (def); - *shift_out = tree_to_uhwi (amount); - return true; -} - -/* Fill INFO's kind plus the captures from RES_OPS that the kind requires. - The kind itself determines how many (op0, op1) and hilo captures to - pick up from RES_OPS, and whether a baked-in shift is present. */ - -static void -long_mul_set_summand (long_mul_summand *info, long_mul_kind kind, - const tree *res_ops) -{ - info->kind = kind; - unsigned n_ops = 0; - unsigned n_hilos = 0; - int shift_idx = -1; - switch (kind) - { - case LMK_MUL_HIHI: - case LMK_MUL_LOLO: - case LMK_MUL_HILO: - n_ops = 2; - break; - case LMK_CROSS_SUM: - n_hilos = 2; - break; - case LMK_LOW_ACCUM: - case LMK_LOW_SUM: - case LMK_LADDER_SUM1: - case LMK_LADDER_SUM2: - case LMK_LADDER_SUM3: - n_ops = 2; - n_hilos = 2; - break; - case LMK_LADDER_PART_SUM: - n_ops = 2; - n_hilos = 1; - break; - case LMK_CARRY_CROSS_SUM: - n_hilos = 3; - shift_idx = 3; - break; - case LMK_CARRY_LOW_SUM: - n_ops = 2; - n_hilos = 3; - shift_idx = 5; - break; - case LMK_CARRY_LOW: - info->carry_a = res_ops[0]; - info->carry_b = res_ops[1]; - return; - } - if (n_ops >= 1) - info->op0 = res_ops[0]; - if (n_ops >= 2) - info->op1 = res_ops[1]; - if (n_hilos >= 1) - info->hilo0 = res_ops[n_ops]; - if (n_hilos >= 2) - info->hilo1 = res_ops[n_ops + 1]; - if (n_hilos >= 3) - info->hilo2 = res_ops[n_ops + 2]; - if (shift_idx >= 0) - /* The carry atoms (mul_carry_cross_sum, mul_carry_low_sum) capture the - shift as an INTEGER_CST already checked with tree_fits_uhwi_p, so this - cannot overflow. */ - info->shift = tree_to_uhwi (res_ops[shift_idx]); -} - -/* Classify LEAF as a carry-kind summand. The lshift amount is baked - into mul_carry_cross_sum / mul_carry_low_sum, so they're tried before - any branch that looks for a generic (X >> N) or (X << N) wrapper. */ - -static bool -long_mul_classify_carry (tree leaf, long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - /* mul_carry_low_sum's inner is constrained to mul_low_sum (cross_sum - + mul_hi(mul_lolo)); mul_carry_cross_sum's inner is just - mul_cross_sum (any plus); mul_carry_low matches gt:c (@0, plus(@0, - @1)) without a baked-in shift. Most specific first, so the - less-constrained pattern doesn't shadow the more-constrained one. */ - if (gimple_mul_carry_low_sum (leaf, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_CARRY_LOW_SUM, res_ops); - return true; - } - if (gimple_mul_carry_cross_sum (leaf, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_CARRY_CROSS_SUM, res_ops); - return true; - } - if (gimple_mul_carry_low (leaf, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_CARRY_LOW, res_ops); - return true; - } - return false; -} - -/* Plus-based summand kinds shared by the (X >> SHIFT) and (X << SHIFT) - classifiers. Order is by specificity: mul_low_sum's first arm is any - plus, so mul_ladder_sum1/3 (which constrain that arm to a plus - containing a mul_lo) and mul_low_accum (which constrains both arms) - shadow it and must come first. */ - -static bool -long_mul_classify_plus_kinds (tree inner, long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - if (gimple_mul_low_accum (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_LOW_ACCUM, res_ops); - return true; - } - if (gimple_mul_ladder_sum3 (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_LADDER_SUM3, res_ops); - return true; - } - if (gimple_mul_ladder_sum1 (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_LADDER_SUM1, res_ops); - return true; - } - if (gimple_mul_low_sum (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_LOW_SUM, res_ops); - return true; - } - if (gimple_mul_ladder_sum2 (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_LADDER_SUM2, res_ops); - return true; - } - return false; -} - -/* Classify INNER -- already unwrapped from an outer (X >> SHIFT) -- as - a high-half-extracted summand. mul_hilo (mult-shape) is orthogonal - to the plus-based kinds and is tried first; ladder_part_sum (one arm - unconstrained) and mul_cross_sum (any plus) are the fallbacks after - the shared plus-based ladder. */ - -static bool -long_mul_classify_hi_extract (tree inner, unsigned HOST_WIDE_INT shift, - long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - info->extract = LMX_HI; - info->shift = shift; - if (gimple_mul_hilo (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_MUL_HILO, res_ops); - return true; - } - if (long_mul_classify_plus_kinds (inner, info)) - return true; - if (gimple_mul_ladder_part_sum (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_LADDER_PART_SUM, res_ops); - return true; - } - if (gimple_mul_cross_sum (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_CROSS_SUM, res_ops); - return true; - } - return false; -} - -/* Classify INNER -- already unwrapped from an outer (X & MASK) -- as - a low-half-masked summand. */ - -static bool -long_mul_classify_lo_extract (tree inner, unsigned HOST_WIDE_INT mask, - long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - info->extract = LMX_LO; - info->mask = mask; - if (gimple_mul_lolo (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_MUL_LOLO, res_ops); - return true; - } - return false; -} - -/* Classify INNER -- already unwrapped from an outer (X << SHIFT) -- as - a left-shifted summand. No mul_hilo / ladder_part_sum here -- those - shapes appear only under (X >> SHIFT). */ - -static bool -long_mul_classify_shl_extract (tree inner, unsigned HOST_WIDE_INT shift, - long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - info->extract = LMX_SHL_N; - info->shift = shift; - if (long_mul_classify_plus_kinds (inner, info)) - return true; - if (gimple_mul_cross_sum (inner, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_CROSS_SUM, res_ops); - return true; - } - return false; -} - -/* Classify LEAF as one of the bare-kind summands (no extraction - wrapper): mul_hihi or mul_lolo standing on their own. */ - -static bool -long_mul_classify_bare (tree leaf, long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - if (gimple_mul_hihi (leaf, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_MUL_HIHI, res_ops); - return true; - } - if (gimple_mul_lolo (leaf, res_ops, NULL)) - { - long_mul_set_summand (info, LMK_MUL_LOLO, res_ops); - return true; - } - return false; -} - -/* Classify LEAF as one of the long-multiply summand shapes. On success, - fill *INFO with the kind, extract, captured operands and shift/mask. - Dispatches to per-extract helpers; the order matters because the - carry kinds bake an lshift into the pattern and would otherwise be - misread by the (X << N) branch. */ - -static bool -long_mul_classify_summand (tree leaf, long_mul_summand *info) -{ - tree res_ops[LONG_MUL_MAX_CAPTURES]; - *info = {}; - - if (long_mul_classify_carry (leaf, info)) - return true; - - if (gimple_mul_hi (leaf, res_ops, NULL)) - return long_mul_classify_hi_extract (res_ops[0], - tree_to_uhwi (res_ops[1]), info); - - if (gimple_mul_lo (leaf, res_ops, NULL)) - return long_mul_classify_lo_extract (res_ops[0], - tree_to_uhwi (res_ops[1]), info); - - tree inner; - unsigned HOST_WIDE_INT shift; - if (long_mul_is_lshift_def (leaf, &inner, &shift)) - return long_mul_classify_shl_extract (inner, shift, info); - - return long_mul_classify_bare (leaf, info); -} - -/* qsort comparator: sort summands by (kind, extract) to put a multiset - into canonical order for table lookup. Unstable sort within a tie is - harmless: no row in long_mul_table pairs distinct subterms under the - same (kind, extract), and long_mul_check_consistency cross-validates - that matching summands share one canonical (op0, op1). */ - -static int -long_mul_summand_compare (const void *a, const void *b) -{ - const long_mul_summand *sa = (const long_mul_summand *) a; - const long_mul_summand *sb = (const long_mul_summand *) b; - if (sa->kind != sb->kind) - return (int) sa->kind - (int) sb->kind; - return (int) sa->extract - (int) sb->extract; -} - -/* One row of the long-multiply variant table. COUNT is how many entries - of SIG carry the row's signature (2 to LONG_MUL_MAX_SUMMANDS); a row - with fewer summands leaves the remaining SIG entries zero-initialized. - Those zeros are not a terminator -- {LMK_MUL_HIHI, LMX_NONE} is itself a - valid signature -- so long_mul_signature_matches is bounded by COUNT, - never by a sentinel entry. */ - -struct long_mul_row { - enum long_mul_row_part { HIGH_PART, LOW_PART } part; - tree_code outer; - unsigned char count; - struct { - long_mul_kind kind; - long_mul_extract extract; - } sig[LONG_MUL_MAX_SUMMANDS]; - bool (*extra_check) (const vec<long_mul_summand> &, gimple *); -}; - -/* True if (A, B) is the same pair as (OP0, OP1) in either order. */ - -static inline bool -long_mul_same_ops (tree a, tree b, tree op0, tree op1) -{ - return (a == op0 && b == op1) || (a == op1 && b == op0); -} - -/* True if H is a cross-half product of (OP0, OP1) -- gimple_mul_hilo - recognizes it and its captured operands match the pair. */ - -static bool -long_mul_is_cross_half (tree h, tree op0, tree op1) -{ - tree scratch[LONG_MUL_MAX_CAPTURES]; - return gimple_mul_hilo (h, scratch, NULL) - && long_mul_same_ops (scratch[0], scratch[1], op0, op1); -} - -/* Orientation of the mul_hilo capture H relative to (OP0, OP1): - returns 0 for high(OP0)*low(OP1), 1 for high(OP1)*low(OP0), or -1 - if H does not decompose that way. A cross-sum of two mul_hilos must - see one of each orientation -- otherwise a doubled factor would fold - to the wrong value. (In a self-multiply the two orientations - coincide; see the OP0 == OP1 bypass in long_mul_check_consistency.) */ - -static int -long_mul_hilo_orientation (tree h, tree op0, tree op1) -{ - tree scratch[LONG_MUL_MAX_CAPTURES]; - if (!gimple_mul_hilo (h, scratch, NULL)) - return -1; - if (scratch[0] == op0 && scratch[1] == op1) - return 0; - if (scratch[0] == op1 && scratch[1] == op0) - return 1; - return -1; -} - -/* Find the first summand that carries operand captures, and return its - (op0, op1) pair in *OP0_OUT / *OP1_OUT. Returns false if no summand - provides them. */ - -static bool -long_mul_canonical_ops (const vec<long_mul_summand> &summands, - tree *op0_out, tree *op1_out) -{ - for (const long_mul_summand &s : summands) - if (s.op0) - { - *op0_out = s.op0; - *op1_out = s.op1; - return true; - } - return false; -} - -/* Return the first summand in SUMMANDS whose kind matches KIND, or NULL. */ - -static const long_mul_summand * -long_mul_find_summand (const vec<long_mul_summand> &summands, - long_mul_kind kind) -{ - for (const long_mul_summand &s : summands) - if (s.kind == kind) - return &s; - return NULL; -} - -/* Run the cross-summand validation invariants and return the canonical - (op0, op1). Returns false unless all summands that carry operands use - the same (op0, op1) pair (in either order), every LMX_HI/LMX_SHL_N shift - equals halfwidth, every captured hilo is a true cross-half product of - (op0, op1), and every cross-half pair (both those inside a single - mul_cross_sum-bearing summand and those spread across separate - LMK_MUL_HILO summands) contains one of each orientation. */ - -static bool -long_mul_check_consistency (const vec<long_mul_summand> &summands, - tree *op0_out, tree *op1_out) -{ - tree op0, op1; - if (!long_mul_canonical_ops (summands, &op0, &op1)) - return false; - - tree op_type = TREE_TYPE (op0); - if (!INTEGRAL_TYPE_P (op_type) - || TYPE_PRECISION (op_type) % 2 != 0) - return false; - unsigned int halfwidth = TYPE_PRECISION (op_type) / 2; - - /* Self-multiply (x*x) collapses the two cross-halves onto one value, - so the complementarity constraint is a trivial no-op there. */ - bool need_orient = op0 != op1; - int mul_hilo_orient[2] = { 0, 0 }; - - for (const long_mul_summand &s : summands) - { - if (s.op0 && !long_mul_same_ops (s.op0, s.op1, op0, op1)) - return false; - if ((s.extract == LMX_HI || s.extract == LMX_SHL_N) - && s.shift != halfwidth) - return false; - tree hilos[3] = { s.hilo0, s.hilo1, s.hilo2 }; - for (tree h : hilos) - if (h && !long_mul_is_cross_half (h, op0, op1)) - return false; - - if (!need_orient) - continue; - - /* The two cross-sum operands are the last two non-null hilos: - (hilo1, hilo2) for the CARRY_*_SUM kinds, (hilo0, hilo1) for - the CROSS_SUM / SUM / ACCUM / LADDER_SUM kinds, none for the - rest. */ - tree a = NULL_TREE; - tree b = NULL_TREE; - if (s.hilo2) - { - a = s.hilo1; - b = s.hilo2; - } - else if (s.hilo1) - { - a = s.hilo0; - b = s.hilo1; - } - if (a && b - && (long_mul_hilo_orientation (a, op0, op1) - == long_mul_hilo_orientation (b, op0, op1))) - return false; - - /* Two LMK_MUL_HILO summands (the two-hilos ladder form) stand for - the two cross-halves separately; count orientations and require - the pair to be complementary. s.op0/op1 is already validated to - match (op0, op1) in some order above. */ - if (s.kind == LMK_MUL_HILO && s.op0) - mul_hilo_orient[s.op0 == op1]++; - } - - if (mul_hilo_orient[0] + mul_hilo_orient[1] >= 2 - && (mul_hilo_orient[0] == 0 || mul_hilo_orient[1] == 0)) - return false; - - *op0_out = op0; - *op1_out = op1; - return true; -} - -/* Compare the (already-sorted) SUMMANDS multiset against ROW.sig. */ - -static bool -long_mul_signature_matches (const vec<long_mul_summand> &summands, - const long_mul_row &row) -{ - if (row.count != summands.length ()) - return false; - for (unsigned i = 0; i < row.count; i++) - if (summands[i].kind != row.sig[i].kind - || summands[i].extract != row.sig[i].extract) - return false; - return true; -} - -/* Extra check for the two-carries high-part row: the LMK_CARRY_LOW summand's - two operands (carry_a, carry_b) must be a (cross_shifted, mul_lolo) pair - consistent with the multiset's canonical (op0, op1). */ - -static bool -long_mul_check_two_carries (const vec<long_mul_summand> &summands, - gimple *) -{ - tree op0, op1; - if (!long_mul_canonical_ops (summands, &op0, &op1)) - return false; - unsigned int halfwidth = TYPE_PRECISION (TREE_TYPE (op0)) / 2; - - const long_mul_summand *cl = long_mul_find_summand (summands, LMK_CARRY_LOW); - if (!cl) - return false; - - /* The two carry_low operands must be (cross_shifted, mul_lolo) in either - order. cross_shifted = LSHIFT_EXPR (mul_cross_sum, halfwidth). */ - tree cs = cl->carry_a, lolo = cl->carry_b; - tree inner; - unsigned HOST_WIDE_INT shift; - if (!long_mul_is_lshift_def (cs, &inner, &shift)) - { - std::swap (cs, lolo); - if (!long_mul_is_lshift_def (cs, &inner, &shift)) - return false; - } - if (shift != halfwidth) - return false; - - tree scratch[LONG_MUL_MAX_CAPTURES]; - if (!gimple_mul_cross_sum (inner, scratch, NULL)) - return false; - for (int i = 0; i < 2; i++) - if (!long_mul_is_cross_half (scratch[i], op0, op1)) - return false; - if (!gimple_mul_lolo (lolo, scratch, NULL) - || !long_mul_same_ops (scratch[0], scratch[1], op0, op1)) - return false; - - return true; -} - -/* The lolo + cross_shifted shape is also the low half of a two-carry - long-multiply, where an unsigned overflow compare against one of - the PLUS operands is the low-carry term consumed by the matching - high-part fold. Folding to mul_lo here destroys cross_shifted, - which both the compare and the high-part match still need; defer - so the high-part fold runs first. After it does, the compare is - dead and the surviving lolo + cross_shifted is picked up by this - row in the next forwprop instance. Returns false to defer. */ - -static bool -long_mul_check_low_plus_defer (const vec<long_mul_summand> &, gimple *stmt) -{ - /* The PHI entry passes its gphi as the candidate but commits only to - HIGH_PART rows, so a LOW_PART row never folds from there. Guard the - gimple_assign accessors regardless, so this stays correct if a future - PLUS-shaped row reachable from the PHI path uses it. */ - if (!is_gimple_assign (stmt)) - return false; - - tree lhs = gimple_assign_lhs (stmt); - tree rhs1 = gimple_assign_rhs1 (stmt); - tree rhs2 = gimple_assign_rhs2 (stmt); - - imm_use_iterator iter; - gimple *use_stmt; - FOR_EACH_IMM_USE_STMT (use_stmt, iter, lhs) - { - tree cmp_op1 = NULL_TREE, cmp_op2 = NULL_TREE; - enum tree_code use_code = ERROR_MARK; - if (is_gimple_assign (use_stmt)) - { - use_code = gimple_assign_rhs_code (use_stmt); - cmp_op1 = gimple_assign_rhs1 (use_stmt); - cmp_op2 = gimple_assign_rhs2 (use_stmt); - } - else if (gcond *cond = dyn_cast<gcond *> (use_stmt)) - { - use_code = gimple_cond_code (cond); - cmp_op1 = gimple_cond_lhs (cond); - cmp_op2 = gimple_cond_rhs (cond); - } - if (use_code == GT_EXPR || use_code == LT_EXPR - || use_code == GE_EXPR || use_code == LE_EXPR) - { - tree other = (cmp_op1 == lhs) ? cmp_op2 - : (cmp_op2 == lhs) ? cmp_op1 : NULL_TREE; - if (other && (other == rhs1 || other == rhs2)) - return false; - } - } - return true; -} - -/* Long-multiply variant table. Each row enumerates the multiset of - (kind, extract) summands that compose one long-multiply form. Rows - are sorted by long_mul_summand_compare, matching the input summands' - sort order, so a plain element-wise compare suffices. Rows describe - unsigned schoolbook expansions on an even-width 2N-bit type split at - half-width N; EXTRA_CHECK carries invariants the (kind, extract) - signature cannot express. - - The formula on each row uses xh, xl, yh, yl for the half-width pieces - of x and y, cross_sum for xh*yl + xl*yh, and hilo for either cross-half - product (consumers validate the operand shape). */ - -static const long_mul_row long_mul_table[] = { - /* HIGH-PART folds. */ - /* xh*yh + (low_sum >> N) + ((hilo > low_sum) << N), - low_sum = cross_sum + (xl*yl >> N). */ - { long_mul_row::HIGH_PART, PLUS_EXPR, 3, - { { LMK_MUL_HIHI, LMX_NONE }, - { LMK_LOW_SUM, LMX_HI }, - { LMK_CARRY_LOW_SUM, LMX_NONE } }, - NULL }, - /* xh*yh + (low_accum >> N) + (cross_sum >> N) + ((hilo > cross_sum) << N), - low_accum = (xl*yl >> N) + (cross_sum & mask). */ - { long_mul_row::HIGH_PART, PLUS_EXPR, 4, - { { LMK_MUL_HIHI, LMX_NONE }, - { LMK_CROSS_SUM, LMX_HI }, - { LMK_LOW_ACCUM, LMX_HI }, - { LMK_CARRY_CROSS_SUM, LMX_NONE } }, - NULL }, - /* xh*yh + (cross_sum >> N) + carry_low + ((hilo > cross_sum) << N), - carry_low = (xl*yl + (cross_sum << N)) < (cross_sum << N). */ - { long_mul_row::HIGH_PART, PLUS_EXPR, 4, - { { LMK_MUL_HIHI, LMX_NONE }, - { LMK_CROSS_SUM, LMX_HI }, - { LMK_CARRY_LOW, LMX_NONE }, - { LMK_CARRY_CROSS_SUM, LMX_NONE } }, - long_mul_check_two_carries }, - /* xh*yh + (hilo >> N) + (ladder_sum1 >> N), - ladder_sum1 = (hilo & mask) + hilo' + (xl*yl >> N), - hilo, hilo' the two cross-half products. */ - { long_mul_row::HIGH_PART, PLUS_EXPR, 3, - { { LMK_MUL_HIHI, LMX_NONE }, - { LMK_MUL_HILO, LMX_HI }, - { LMK_LADDER_SUM1, LMX_HI } }, - NULL }, - /* xh*yh + (ladder_sum2 >> N) + (ladder_part_sum >> N), - ladder_part_sum = (xl*yl >> N) + hilo, - ladder_sum2 = (ladder_part_sum & mask) + hilo'. */ - { long_mul_row::HIGH_PART, PLUS_EXPR, 3, - { { LMK_MUL_HIHI, LMX_NONE }, - { LMK_LADDER_SUM2, LMX_HI }, - { LMK_LADDER_PART_SUM, LMX_HI } }, - NULL }, - /* xh*yh + (hilo >> N) + (hilo' >> N) + (ladder_sum3 >> N), - ladder_sum3 = (hilo & mask) + (hilo' & mask) + (xl*yl >> N). */ - { long_mul_row::HIGH_PART, PLUS_EXPR, 4, - { { LMK_MUL_HIHI, LMX_NONE }, - { LMK_MUL_HILO, LMX_HI }, - { LMK_MUL_HILO, LMX_HI }, - { LMK_LADDER_SUM3, LMX_HI } }, - NULL }, - /* LOW-PART folds. Recover the lower 2N bits from xl*yl plus a - shifted cross-half term. */ - /* xl*yl + (cross_sum << N). */ - { long_mul_row::LOW_PART, PLUS_EXPR, 2, - { { LMK_MUL_LOLO, LMX_NONE }, - { LMK_CROSS_SUM, LMX_SHL_N } }, - long_mul_check_low_plus_defer }, - /* (xl*yl & mask) | (low_accum << N), - low_accum = (xl*yl >> N) + (cross_sum & mask). */ - { long_mul_row::LOW_PART, BIT_IOR_EXPR, 2, - { { LMK_MUL_LOLO, LMX_LO }, - { LMK_LOW_ACCUM, LMX_SHL_N } }, - NULL }, - /* (xl*yl & mask) | (low_sum << N), - low_sum = cross_sum + (xl*yl >> N). */ - { long_mul_row::LOW_PART, BIT_IOR_EXPR, 2, - { { LMK_MUL_LOLO, LMX_LO }, - { LMK_LOW_SUM, LMX_SHL_N } }, - NULL }, - /* (xl*yl & mask) | (ladder_sum1 << N), - ladder_sum1 as in the high ladder row above. */ - { long_mul_row::LOW_PART, BIT_IOR_EXPR, 2, - { { LMK_MUL_LOLO, LMX_LO }, - { LMK_LADDER_SUM1, LMX_SHL_N } }, - NULL }, - /* (xl*yl & mask) | (ladder_sum2 << N), - ladder_sum2 as in the high ladder row above. */ - { long_mul_row::LOW_PART, BIT_IOR_EXPR, 2, - { { LMK_MUL_LOLO, LMX_LO }, - { LMK_LADDER_SUM2, LMX_SHL_N } }, - NULL }, - /* (xl*yl & mask) | (ladder_sum3 << N), - ladder_sum3 as in the high ladder-long row above. */ - { long_mul_row::LOW_PART, BIT_IOR_EXPR, 2, - { { LMK_MUL_LOLO, LMX_LO }, - { LMK_LADDER_SUM3, LMX_SHL_N } }, - NULL }, -}; - -/* If a multi-used inner addition (sharing the chain's outer code) blocked - linearization of a long-mul candidate, emit a dump-file hint pointing - at it. */ - -static void -long_mul_hint_shared_intermediate (gimple *shared_def) -{ - if (!shared_def || !dump_file || !(dump_flags & TDF_DETAILS)) - return; - fprintf (dump_file, "long-mul fold rejected: shared intermediate at "); - print_gimple_stmt (dump_file, shared_def, 0, TDF_SLIM); -} - -/* Search long_mul_table for a row whose multiset matches SUMMANDS for - outer kind OUTER on a result of type LHS_TYPE. CANDIDATE_STMT is - passed to per-row extra_check predicates. On a hit, returns the - matching row and writes the half-width operands via OUT_OP0/OUT_OP1. - No IR mutation. */ - -static const long_mul_row * -long_mul_classify_match (const vec<long_mul_summand> &summands, - tree lhs_type, tree_code outer, - gimple *candidate_stmt, - tree *out_op0, tree *out_op1) -{ - /* HIGH_PART rows emit a 2N-bit multiply that pass_optimize - _widening_mul consumes -- either via WIDEN_MULT_EXPR / - MULT_HIGHPART conversion when the target has a native 2N - multiply, or via lower_long_mul_high_chain when it does not. - LOW_PART rows emit a plain MULT_EXPR. Emission needs a 2N - mode to exist in the mode table AND the widening_mul pass to - be active: without the pass, the emit could reach RTL expand - as an unexpandable 2N multiply (e.g. OImode). BITINT_TYPE is - refused -- the long_mul_high_chain atom excludes it. */ - scalar_int_mode mode, wide_mode; - bool can_emit_high - = optimize_widening_mul_active_p () - && TREE_CODE (lhs_type) != BITINT_TYPE - && is_a <scalar_int_mode> (TYPE_MODE (lhs_type), &mode) - && GET_MODE_2XWIDER_MODE (mode).exists (&wide_mode); - - for (const long_mul_row &row : long_mul_table) - { - if (row.outer != outer - || (row.part == long_mul_row::HIGH_PART && !can_emit_high) - || !long_mul_signature_matches (summands, row)) - continue; - - tree op0, op1; - if (!long_mul_check_consistency (summands, &op0, &op1)) - continue; - - /* Do not emit the wide chain when an operand is subject to - abnormal coalescing: the widening_mul-side consumers refuse - such operands (see convert_mult_to_widen), which would leave - the chain without a consumer. */ - if (row.part == long_mul_row::HIGH_PART - && ((TREE_CODE (op0) == SSA_NAME - && SSA_NAME_OCCURS_IN_ABNORMAL_PHI (op0)) - || (TREE_CODE (op1) == SSA_NAME - && SSA_NAME_OCCURS_IN_ABNORMAL_PHI (op1)))) - continue; - - if (row.extra_check && !row.extra_check (summands, candidate_stmt)) - continue; - - *out_op0 = op0; - *out_op1 = op1; - return &row; - } - return NULL; -} - -/* Walk STMT's outer chain (kind OUTER), classify each leaf as a - long-multiply summand, optionally add the already-classified EXTRA, - and look the multiset up in long_mul_table for a result of type - LHS_TYPE. CANDIDATE is passed to per-row extra_check predicates. - - If EXTRAS_OUT is non-NULL, leaves matching no summand are set aside - there instead of failing the match, and the caller must re-apply - them on top of the folded multiply. A leaf that does match is - always consumed: if that makes the signature miss every row the - match fails, rather than retrying with the leaf demoted to an extra - (subset search would be exponential). - - Returns the matched row and the half-width operands via - OUT_OP0/OUT_OP1, or NULL on a miss. No IR mutation. */ - -static const long_mul_row * -long_mul_classify_chain (gimple *stmt, tree_code outer, tree lhs_type, - gimple *candidate, const long_mul_summand *extra, - vec<tree> *extras_out, - tree *out_op0, tree *out_op1) -{ - auto_vec<tree, LONG_MUL_MAX_SUMMANDS + LONG_MUL_MAX_EXTRAS> leaves; - gimple *shared_def = NULL; - if (!long_mul_linearize_chain (stmt, outer, leaves, &shared_def)) - return NULL; - - auto_vec<long_mul_summand, - LONG_MUL_MAX_SUMMANDS + LONG_MUL_MAX_EXTRAS + 1> summands; - for (tree leaf : leaves) - { - long_mul_summand s; - if (long_mul_classify_summand (leaf, &s)) - summands.quick_push (s); - else if (extras_out && extras_out->length () < LONG_MUL_MAX_EXTRAS) - extras_out->safe_push (leaf); - else - { - long_mul_hint_shared_intermediate (shared_def); - return NULL; - } - } - if (extra) - summands.quick_push (*extra); - if (summands.length () < 2 - || summands.length () > LONG_MUL_MAX_SUMMANDS) - return NULL; - summands.qsort (long_mul_summand_compare); - - const long_mul_row *row - = long_mul_classify_match (summands, lhs_type, outer, candidate, - out_op0, out_op1); - if (!row) - long_mul_hint_shared_intermediate (shared_def); - return row; -} - -/* Top-level entry for long-multiply folding. Walks STMT's outer - addition or BIT_IOR chain, classifies the summands, and dispatches - to create_mul_high_seq / create_mul_low_seq if the multiset matches - a known long-multiply form. Returns true on success. */ - -static bool -match_long_mul (gassign *stmt) -{ - tree_code outer = gimple_assign_rhs_code (stmt); - if (outer != PLUS_EXPR && outer != BIT_IOR_EXPR) - return false; - - /* Skip non-candidate adds (signed, pointer, odd-width) before walking the - chain. No legitimate long-mul leaf has a type the atoms would reject. - This just avoids the linearize/classify work on every other PLUS/IOR. */ - tree lhs_type = TREE_TYPE (gimple_assign_lhs (stmt)); - if (!INTEGRAL_TYPE_P (lhs_type) - || !TYPE_UNSIGNED (lhs_type) - || TYPE_PRECISION (lhs_type) % 2 != 0) - return false; - - /* Only start at the end of a chain: a consumer with the same code - linearizes through this statement anyway, so starting here is - redundant. A consumer in another block does not count -- folding - at the later use could sink a loop-invariant multiply into a - loop. */ - use_operand_p use_p; - gimple *use_stmt; - if (single_imm_use (gimple_assign_lhs (stmt), &use_p, &use_stmt) - && is_gimple_assign (use_stmt) - && gimple_assign_rhs_code (use_stmt) == outer - && gimple_bb (use_stmt) == gimple_bb (stmt)) - return false; - - auto_vec<tree, LONG_MUL_MAX_EXTRAS> extras; - tree op0, op1; - const long_mul_row *row - = long_mul_classify_chain (stmt, outer, lhs_type, stmt, NULL, &extras, - &op0, &op1); - if (!row) - return false; - - if (row->part == long_mul_row::HIGH_PART) - { - create_mul_high_seq (op0, op1, stmt, extras, outer); - if (dump_file && (dump_flags & TDF_DETAILS)) - fprintf (dump_file, "Long multiplication high part folded.\n"); - return true; - } - create_mul_low_seq (op0, op1, stmt, extras, outer); - if (dump_file && (dump_flags & TDF_DETAILS)) - fprintf (dump_file, "Long multiplication low part folded.\n"); - return true; -} - -/* PHI-driven entry for long-multiply folding. When PHI's value - flattens to base + (carry << N), probe sum to classify the carry - kind, linearize base for the remaining high-part summands, and run - the long-multiply table. On a hit, emit a 2N-bit multiply at the - top of the join block with PHI_RES as its LHS and remove the PHI. - Otherwise leave the IR untouched. Only HIGH_PART rows are - reachable. LOW_PART rows are BIT_IOR-shaped and never produce a - carry PHI. */ - -static bool -match_long_mul_phi (gphi *phi) -{ - tree phi_res = gimple_phi_result (phi); - tree lhs_type = TREE_TYPE (phi_res); - if (!INTEGRAL_TYPE_P (lhs_type) || !TYPE_UNSIGNED (lhs_type) - || TYPE_PRECISION (lhs_type) % 2 != 0) - return false; - - tree cca_ops[4]; - if (!gimple_cond_carry_add (phi_res, cca_ops, NULL) - && !gimple_cond_carry_add_neg (phi_res, cca_ops, NULL)) - return false; - tree cmp_lhs = cca_ops[0]; - tree sum = cca_ops[1]; - tree base = cca_ops[2]; - - /* Classify sum and populate the carry summand directly. Most - specific first, mirroring long_mul_classify_carry's order. */ - long_mul_summand carry = {}; - tree sum_ops[LONG_MUL_MAX_CAPTURES]; - unsigned HOST_WIDE_INT shift_amt - = wi::exact_log2 (wi::to_wide (cca_ops[3])); - unsigned HOST_WIDE_INT halfwidth = TYPE_PRECISION (lhs_type) / 2; - carry.shift = shift_amt; - - if (gimple_mul_low_sum (sum, sum_ops, NULL) - && shift_amt == halfwidth) - { - /* mul_carry_low_sum's flat form ties the outer lshift amount to - the inner mul_hi's INTEGER_CST@0 via match.pd capture re-use; - the PHI form has no such tie, so gate on shift_amt explicitly. */ - carry.kind = LMK_CARRY_LOW_SUM; - carry.op0 = sum_ops[0]; - carry.op1 = sum_ops[1]; - carry.hilo0 = cmp_lhs; - carry.hilo1 = sum_ops[2]; - carry.hilo2 = sum_ops[3]; - } - else if (gimple_mul_cross_sum (sum, sum_ops, NULL) - && shift_amt == halfwidth) - { - /* mul_cross_sum is just (plus:c @0 @1) with no half-width - constraint. Gate here to mirror mul_carry_cross_sum; - a mismatch falls through to the LMK_CARRY_LOW branch. */ - carry.kind = LMK_CARRY_CROSS_SUM; - carry.hilo0 = cmp_lhs; - carry.hilo1 = sum_ops[0]; - carry.hilo2 = sum_ops[1]; - } - else if (shift_amt == 0 && TREE_CODE (sum) == SSA_NAME) - { - gimple *def = SSA_NAME_DEF_STMT (sum); - if (!is_gimple_assign (def) - || gimple_assign_rhs_code (def) != PLUS_EXPR) - return false; - tree p1 = gimple_assign_rhs1 (def); - tree p2 = gimple_assign_rhs2 (def); - if (p1 != cmp_lhs && p2 != cmp_lhs) - return false; - carry.kind = LMK_CARRY_LOW; - carry.carry_a = cmp_lhs; - carry.carry_b = p1 == cmp_lhs ? p2 : p1; - } - else - return false; - - /* Linearize base, the rest of the high-part chain. */ - if (TREE_CODE (base) != SSA_NAME) - return false; - gimple *base_def = SSA_NAME_DEF_STMT (base); - if (!is_gimple_assign (base_def) - || gimple_assign_rhs_code (base_def) != PLUS_EXPR) - return false; - - tree op0, op1; - const long_mul_row *row - = long_mul_classify_chain (base_def, PLUS_EXPR, lhs_type, phi, &carry, - NULL, &op0, &op1); - if (!row || row->part != long_mul_row::HIGH_PART) - return false; - - gimple_seq seq = NULL; - build_mul_high_seq (op0, op1, phi_res, gimple_location (phi), &seq); - gimple_stmt_iterator gsi = gsi_after_labels (gimple_bb (phi)); - gsi_insert_seq_before (&gsi, seq, GSI_SAME_STMT); - gimple_stmt_iterator psi = gsi_for_stmt (phi); - remove_phi_node (&psi, false); - if (dump_file && (dump_flags & TDF_DETAILS)) - fprintf (dump_file, - "Long multiplication high part folded (carry PHI).\n"); - return true; -} /* Determine whether applying the 2 permutations (mask1 then mask2) gives back one of the input. */ @@ -6581,19 +5409,14 @@ pass_forwprop::execute (function *fun) } } - /* Fold PHI-form long-multiply carries and record degenerate - PHIs in the lattice. Iterator advanced up front so a folded - PHI can be removed in-flight; a long-mul carry PHI is never - degenerate, so the two cases are disjoint. */ - for (gphi_iterator si = gsi_start_phis (bb); !gsi_end_p (si);) + /* Record degenerate PHIs in the lattice. */ + for (gphi_iterator si = gsi_start_phis (bb); !gsi_end_p (si); + gsi_next (&si)) { gphi *phi = si.phi (); - gsi_next (&si); tree res = gimple_phi_result (phi); if (virtual_operand_p (res)) continue; - if (match_long_mul_phi (phi)) - continue; tree first = NULL_TREE; bool all_same = true; @@ -7059,15 +5882,11 @@ pass_forwprop::execute (function *fun) } else if (TREE_CODE_CLASS (code) == tcc_comparison) changed |= forward_propagate_into_comparison (&gsi); - else if ((code == PLUS_EXPR || code == BIT_IOR_EXPR)) - { - bool folded = match_long_mul (as_a <gassign *> (stmt)); - if (!folded) - folded = simplify_rotate (&gsi); - changed |= folded; - } - else if (code == BIT_XOR_EXPR) - changed |= simplify_rotate (&gsi); + else if ((code == PLUS_EXPR + || code == BIT_IOR_EXPR + || code == BIT_XOR_EXPR) + && simplify_rotate (&gsi)) + changed = true; else if (code == VEC_PERM_EXPR) changed |= simplify_permutation (&gsi); else if (code == CONSTRUCTOR diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc index ead37104840a..0df1909ebc43 100644 --- a/gcc/tree-ssa-math-opts.cc +++ b/gcc/tree-ssa-math-opts.cc @@ -6541,484 +6541,6 @@ optimize_spaceship (gcond *stmt) } -/* Long-multiply inverse-lowering helper. - - The forwprop long-multiply recognizer canonicalizes a hand-written - longhand high-part multiply into a cast+mult+shift+cast chain - `(N) ((2N) a * (2N) b) >> N'. When the target lacks an expansion - path for the wide form, `lower_long_mul_high_chain' resynthesizes - the longhand at narrow precision via `build_long_mul_partials'. */ - -/* Test whether the target supports an (HALF)-by-(HALF)->NARROW unsigned - widening multiply. Returns true on success, with the half-width - scalar int mode placed in *HALF_MODE. */ - -static bool -can_widen_to_narrow_p (scalar_int_mode narrow_mode, unsigned int half_width, - scalar_int_mode *half_mode) -{ - if (!int_mode_for_size (half_width, 0).exists (half_mode)) - return false; - return convert_optab_handler (umul_widen_optab, narrow_mode, *half_mode) - != CODE_FOR_nothing; -} - -/* Append to *SEQ the operand split and partial products for an unsigned - long multiply of OP1 by OP2 at the precision of TREE_TYPE (OP1). - HALF_TYPE is the (N/2)-bit unsigned type; HALF_AMT is the integer-typed - shift constant equal to N/2. - - Outputs the four partial products via *LOLO, *HILO, *LOHI, *HIHI. - - USE_WIDEN selects the partial-product form: - true - cast halves to HALF_TYPE and use WIDEN_MULT_EXPR (needs - an (N/2)-by-(N/2)->N widening multiply optab). - false - mask/shift halves within the N-bit accumulator and use - plain MULT_EXPR; the halves fit in N/2 bits so the N-bit - low product is exact. */ - -static void -build_long_mul_partials (gimple_seq *seq, location_t loc, tree op1, tree op2, - tree half_type, tree half_amt, - tree *lolo, tree *hilo, tree *lohi, tree *hihi, - bool use_widen) -{ - tree acc_type = TREE_TYPE (op1); - tree op1_hi = gimple_build (seq, loc, RSHIFT_EXPR, acc_type, op1, half_amt); - tree op2_hi = gimple_build (seq, loc, RSHIFT_EXPR, acc_type, op2, half_amt); - tree op1_lo, op2_lo; - tree_code mul_code; - - if (use_widen) - { - op1_lo = gimple_build (seq, loc, NOP_EXPR, half_type, op1); - op2_lo = gimple_build (seq, loc, NOP_EXPR, half_type, op2); - op1_hi = gimple_build (seq, loc, NOP_EXPR, half_type, op1_hi); - op2_hi = gimple_build (seq, loc, NOP_EXPR, half_type, op2_hi); - mul_code = WIDEN_MULT_EXPR; - } - else - { - tree mask = wide_int_to_tree (acc_type, - wi::mask (TYPE_PRECISION (half_type), false, - TYPE_PRECISION (acc_type))); - op1_lo = gimple_build (seq, loc, BIT_AND_EXPR, acc_type, op1, mask); - op2_lo = gimple_build (seq, loc, BIT_AND_EXPR, acc_type, op2, mask); - mul_code = MULT_EXPR; - } - - *lolo = gimple_build (seq, loc, mul_code, acc_type, op1_lo, op2_lo); - *hilo = gimple_build (seq, loc, mul_code, acc_type, op1_hi, op2_lo); - *lohi = gimple_build (seq, loc, mul_code, acc_type, op1_lo, op2_hi); - *hihi = gimple_build (seq, loc, mul_code, acc_type, op1_hi, op2_hi); -} - -/* Emit into *SEQ the high N bits of the unsigned product A * B, where A and B - are NARROW_TYPE (N-bit) values, as a longhand over (N/2)-bit partials. - Returns the high-part SSA. */ - -static tree -emit_long_mul_highpart (gimple_seq *seq, location_t loc, tree a, tree b, - tree narrow_type) -{ - scalar_int_mode narrow_mode - = as_a <scalar_int_mode> (TYPE_MODE (narrow_type)); - unsigned int half_width = GET_MODE_PRECISION (narrow_mode) / 2; - /* Prefer (N/2)-by-(N/2)->N widening partials; fall back to plain MULT_EXPR - when the target lacks the widen optab. See build_long_mul_partials. */ - scalar_int_mode half_mode; - bool use_widen = can_widen_to_narrow_p (narrow_mode, half_width, &half_mode); - tree half_type = build_nonstandard_integer_type (half_width, 1); - tree half_amt = build_int_cst (integer_type_node, half_width); - tree half_mask = wide_int_to_tree (narrow_type, - wi::mask (half_width, false, - TYPE_PRECISION (narrow_type))); - - tree lolo, hilo, lohi, hihi; - build_long_mul_partials (seq, loc, a, b, half_type, half_amt, - &lolo, &hilo, &lohi, &hihi, use_widen); - tree cross_sum = gimple_build (seq, loc, PLUS_EXPR, narrow_type, hilo, lohi); - tree cross_lt = gimple_build (seq, loc, LT_EXPR, boolean_type_node, - cross_sum, hilo); - tree cross_lt_n = gimple_build (seq, loc, NOP_EXPR, narrow_type, cross_lt); - tree cross_carry = gimple_build (seq, loc, LSHIFT_EXPR, narrow_type, - cross_lt_n, half_amt); - tree lolo_hi = gimple_build (seq, loc, RSHIFT_EXPR, narrow_type, - lolo, half_amt); - tree cross_lo = gimple_build (seq, loc, BIT_AND_EXPR, narrow_type, - cross_sum, half_mask); - tree low_accum = gimple_build (seq, loc, PLUS_EXPR, narrow_type, - lolo_hi, cross_lo); - tree low_accum_hi = gimple_build (seq, loc, RSHIFT_EXPR, narrow_type, - low_accum, half_amt); - tree cross_hi = gimple_build (seq, loc, RSHIFT_EXPR, narrow_type, - cross_sum, half_amt); - tree t1 = gimple_build (seq, loc, PLUS_EXPR, narrow_type, hihi, cross_hi); - tree t2 = gimple_build (seq, loc, PLUS_EXPR, narrow_type, t1, low_accum_hi); - return gimple_build (seq, loc, PLUS_EXPR, narrow_type, t2, cross_carry); -} - -/* Emit into *SEQ the high N bits (NARROW_TYPE) of the unsigned product of two - 2N-bit values given as N-bit halves, x = L1 + H1*2^N and y = L2 + H2*2^N: - the high half of x*y is the high N bits of L1*L2, plus H1*L2 and L1*H2, all - mod 2^N. */ - -static tree -combine_long_mul_halves (gimple_seq *seq, location_t loc, tree l1, tree h1, - tree l2, tree h2, tree narrow_type) -{ - tree hh = emit_long_mul_highpart (seq, loc, l1, l2, narrow_type); - tree c1 = gimple_build (seq, loc, MULT_EXPR, narrow_type, h1, l2); - tree c2 = gimple_build (seq, loc, MULT_EXPR, narrow_type, l1, h2); - tree s = gimple_build (seq, loc, PLUS_EXPR, narrow_type, hh, c1); - return gimple_build (seq, loc, PLUS_EXPR, narrow_type, s, c2); -} - -/* True when OP fits NARROW_PREC bits as an unsigned value. Looks - through widening casts and PHIs, falling back to `tree_nonzero_bits' - otherwise. PHI_SEEN guards against cycles. */ - -static bool -long_mul_op_fits_p (tree op, unsigned narrow_prec, bitmap phi_seen) -{ - if (!TYPE_UNSIGNED (TREE_TYPE (op))) - return false; - if (TYPE_PRECISION (TREE_TYPE (op)) <= narrow_prec) - return true; - if (TREE_CODE (op) == SSA_NAME) - { - gimple *def = SSA_NAME_DEF_STMT (op); - if (is_gimple_assign (def) - && CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (def))) - return long_mul_op_fits_p (gimple_assign_rhs1 (def), narrow_prec, - phi_seen); - if (gphi *phi = dyn_cast <gphi *> (def)) - if (bitmap_set_bit (phi_seen, SSA_NAME_VERSION (op))) - { - for (unsigned i = 0; i < gimple_phi_num_args (phi); ++i) - if (!long_mul_op_fits_p (gimple_phi_arg_def (phi, i), - narrow_prec, phi_seen)) - return false; - return true; - } - } - return wi::min_precision (tree_nonzero_bits (op), UNSIGNED) <= narrow_prec; -} - -/* Split the 2N-bit unsigned value OP into its low and high N bits (*LO and - *HI, both NARROW_TYPE) using only N-bit operations, as the target has no 2N - multiply or shift. A 2N product recurses on its operands, its high half - coming from combine_long_mul_halves. A value shifted down by N recurses on - the shifted value and takes its high half, rather than reading the 2N shift. - A widening cast's low half is the truncated source and its high half is what - the cast extended with, zero or the source's replicated sign bit. A value - that provably fits N bits has a zero high half. Returns false otherwise. */ - -static bool -long_mul_split_operand (gimple_seq *seq, location_t loc, tree op, - tree narrow_type, tree *lo, tree *hi) -{ - unsigned int narrow_prec = TYPE_PRECISION (narrow_type); - if (TREE_CODE (op) == SSA_NAME) - { - gimple *def = SSA_NAME_DEF_STMT (op); - if (is_gimple_assign (def) && gimple_assign_rhs_code (def) == MULT_EXPR) - { - tree a_lo, a_hi, b_lo, b_hi; - if (!long_mul_split_operand (seq, loc, gimple_assign_rhs1 (def), - narrow_type, &a_lo, &a_hi) - || !long_mul_split_operand (seq, loc, gimple_assign_rhs2 (def), - narrow_type, &b_lo, &b_hi)) - return false; - *lo = gimple_build (seq, loc, MULT_EXPR, narrow_type, a_lo, b_lo); - *hi = combine_long_mul_halves (seq, loc, a_lo, a_hi, b_lo, b_hi, - narrow_type); - return true; - } - /* A 2N value shifted down by N is its own high half: split the source - and use that half. Reading the shift instead leaves the 2N source - live, and the target cannot expand it. This has to come before the - widening-cast case below, which would take such a value as it - stands. */ - if (is_gimple_assign (def) - && gimple_assign_rhs_code (def) == RSHIFT_EXPR - && tree_fits_uhwi_p (gimple_assign_rhs2 (def)) - && tree_to_uhwi (gimple_assign_rhs2 (def)) == narrow_prec) - { - tree src_lo, src_hi; - if (!long_mul_split_operand (seq, loc, gimple_assign_rhs1 (def), - narrow_type, &src_lo, &src_hi)) - return false; - *lo = src_hi; - *hi = build_zero_cst (narrow_type); - return true; - } - if (is_gimple_assign (def) - && CONVERT_EXPR_CODE_P (gimple_assign_rhs_code (def))) - { - tree src = gimple_assign_rhs1 (def); - tree src_type = TREE_TYPE (src); - if (INTEGRAL_TYPE_P (src_type) - && TYPE_PRECISION (src_type) <= narrow_prec) - { - *lo = gimple_convert (seq, loc, narrow_type, src); - if (TYPE_UNSIGNED (src_type)) - *hi = build_zero_cst (narrow_type); - else - { - /* Sign extension: the high N bits replicate the sign bit. */ - tree snarrow = signed_type_for (narrow_type); - tree s = gimple_convert (seq, loc, snarrow, *lo); - tree amt = build_int_cst (integer_type_node, narrow_prec - 1); - tree sh = gimple_build (seq, loc, RSHIFT_EXPR, snarrow, s, - amt); - *hi = gimple_convert (seq, loc, narrow_type, sh); - } - return true; - } - } - } - - /* A value provably within N bits: its low half is the truncation to N bits - (a subreg, not a 2N shift), its high half is zero. */ - auto_bitmap phi_seen; - if (long_mul_op_fits_p (op, narrow_prec, phi_seen)) - { - *lo = gimple_convert (seq, loc, narrow_type, op); - *hi = build_zero_cst (narrow_type); - return true; - } - return false; -} - -/* True when every use of PROD reads only its low NARROW_PREC bits -- a - truncation to at most NARROW_PREC bits, or an AND with a low-bit mask. */ - -static bool -long_mul_only_low_half_used_p (tree prod, unsigned int narrow_prec) -{ - imm_use_iterator iui; - gimple *use_stmt; - FOR_EACH_IMM_USE_STMT (use_stmt, iui, prod) - { - if (is_gimple_debug (use_stmt)) - continue; - if (!is_gimple_assign (use_stmt)) - return false; - tree_code code = gimple_assign_rhs_code (use_stmt); - if (CONVERT_EXPR_CODE_P (code)) - { - tree t = TREE_TYPE (gimple_assign_lhs (use_stmt)); - if (!INTEGRAL_TYPE_P (t) || TYPE_PRECISION (t) > narrow_prec) - return false; - } - else if (code == BIT_AND_EXPR - && TREE_CODE (gimple_assign_rhs2 (use_stmt)) == INTEGER_CST) - { - if (wi::min_precision (wi::to_wide (gimple_assign_rhs2 (use_stmt)), - UNSIGNED) > narrow_prec) - return false; - } - else - return false; - } - return true; -} - -static bool narrow_long_mul_low_half (gimple_stmt_iterator *); - -/* OP1 and OP2 are the operands of a 2N multiply just narrowed or lowered; - that rewrite now reads each through an N-bit low-half cast. An operand - defined by another 2N multiply can thereby become low-half-only -- narrow - it too, recursing through chained wide products such as (a*b)*c. */ - -static void -narrow_long_mul_operands (tree op1, tree op2) -{ - for (tree op : { op1, op2 }) - if (TREE_CODE (op) == SSA_NAME) - { - gimple *def = SSA_NAME_DEF_STMT (op); - if (is_gimple_assign (def) && gimple_assign_rhs_code (def) == MULT_EXPR) - { - gimple_stmt_iterator dgsi = gsi_for_stmt (def); - narrow_long_mul_low_half (&dgsi); - } - } -} - -/* If the statement at *GSI is res = a * b with a 2N-bit unsigned result - whose mode the target cannot multiply (no insn and no libcall, so it would - abort expand_mult), and every use reads only the low N bits, narrow it to - res = (2N) ((N) a * (N) b) and return true. The low N bits of a product - depend only on the low N bits of the operands, so this preserves every - use; the unused high half becomes zero. The gate keeps it target-aware: - where a wide or high-part multiply exists the mult is left for - convert_mult_to_widen / convert_mult_to_highpart, so this (which match.pd's - shorten rule omits for MULT_EXPR) does not pessimize it. */ - -static bool -narrow_long_mul_low_half (gimple_stmt_iterator *gsi) -{ - gimple *stmt = gsi_stmt (*gsi); - if (!is_gimple_assign (stmt) || gimple_assign_rhs_code (stmt) != MULT_EXPR) - return false; - - tree lhs = gimple_assign_lhs (stmt); - tree wide_type = TREE_TYPE (lhs); - scalar_int_mode wide_mode; - if (!INTEGRAL_TYPE_P (wide_type) - || !TYPE_UNSIGNED (wide_type) - || !is_a <scalar_int_mode> (TYPE_MODE (wide_type), &wide_mode) - || targetm.scalar_mode_supported_p (wide_mode)) - return false; - - unsigned int narrow_prec = TYPE_PRECISION (wide_type) / 2; - if (!long_mul_only_low_half_used_p (lhs, narrow_prec)) - return false; - - tree op1 = gimple_assign_rhs1 (stmt); - tree op2 = gimple_assign_rhs2 (stmt); - location_t loc = gimple_location (stmt); - tree narrow_type = build_nonstandard_integer_type (narrow_prec, 1); - gimple_seq seq = NULL; - tree a = gimple_convert (&seq, loc, narrow_type, op1); - tree b = gimple_convert (&seq, loc, narrow_type, op2); - tree np = gimple_build (&seq, loc, MULT_EXPR, narrow_type, a, b); - gsi_insert_seq_before (gsi, seq, GSI_SAME_STMT); - gimple *conv = gimple_build_assign (lhs, NOP_EXPR, np); - gimple_set_location (conv, loc); - gsi_replace (gsi, conv, true); - - if (dump_file && (dump_flags & TDF_DETAILS)) - fprintf (dump_file, "Narrowed low-half-only long multiply.\n"); - - narrow_long_mul_operands (op1, op2); - return true; -} - -/* Match.pd recognizer for the long-multiply recognizer's high-part - emit chain. */ - -extern bool gimple_long_mul_high_chain (tree, tree *, tree (*)(tree)); - -/* Rewrite the `long_mul_high_chain' whose tail is the statement at GSI - - wide_a = (T_2N) op1 - wide_b = (T_2N) op2 - wide_prod = wide_a * wide_b - hi = wide_prod >> N - lhs = (convert) hi - - to a longhand high-part synthesis at T_N precision. Never materializes - T_2N in gimple, so it covers cases where the 2N mode has no expansion path - (e.g. the high 128 bits of a 128x128 product where 2N=OImode). An operand - wider than T_N -- a shared wide product or a sign-extended cast -- is split - into T_N halves rather than truncated, so no high input bits are dropped. - Returns true on a rewrite. */ - -static bool -lower_long_mul_high_chain (gimple_stmt_iterator *gsi) -{ - gimple *trunc_stmt = gsi_stmt (*gsi); - if (!is_gimple_assign (trunc_stmt)) - return false; - - tree narrow_lhs = gimple_assign_lhs (trunc_stmt); - tree ops[2]; - if (!gimple_long_mul_high_chain (narrow_lhs, ops, NULL)) - return false; - - /* Walk the matched chain back to the 2N multiply and take narrow_type at - half its precision. */ - gimple *shift_stmt = SSA_NAME_DEF_STMT (gimple_assign_rhs1 (trunc_stmt)); - gimple *mult_stmt = SSA_NAME_DEF_STMT (gimple_assign_rhs1 (shift_stmt)); - unsigned int narrow_prec - = TYPE_PRECISION (TREE_TYPE (gimple_assign_lhs (mult_stmt))) / 2; - tree narrow_type = build_nonstandard_integer_type (narrow_prec, /*uns=*/1); - scalar_int_mode narrow_mode; - if (!is_a <scalar_int_mode> (TYPE_MODE (narrow_type), &narrow_mode)) - return false; - - /* Lower only when the target cannot form the N-bit high part itself. */ - if (can_mult_highpart_p (narrow_mode, true)) - return false; - - location_t loc = gimple_location (trunc_stmt); - gimple_seq seq = NULL; - - /* Split each operand into N-bit halves and combine. An operand that fits - N bits yields h == 0, so its cross term folds away; with both fitting - the combine is just a plain N-bit high part. */ - tree l1, h1, l2, h2; - if (!long_mul_split_operand (&seq, loc, gimple_assign_rhs1 (mult_stmt), - narrow_type, &l1, &h1) - || !long_mul_split_operand (&seq, loc, gimple_assign_rhs2 (mult_stmt), - narrow_type, &l2, &h2)) - return false; - tree hi = combine_long_mul_halves (&seq, loc, l1, h1, l2, h2, narrow_type); - - /* Merging the chain's truncation with a later user cast can retarget the - outer convert to any integral type, so convert the narrow result once - here (the high part is < 2^N, so the conversion preserves it). */ - gimple *result_stmt; - tree lhs_type = TREE_TYPE (narrow_lhs); - if (useless_type_conversion_p (lhs_type, narrow_type)) - result_stmt = gimple_build_assign (narrow_lhs, hi); - else - result_stmt = gimple_build_assign (narrow_lhs, NOP_EXPR, hi); - gimple_set_location (result_stmt, loc); - gimple_seq_add_stmt (&seq, result_stmt); - - gsi_replace_with_seq (gsi, seq, true); - - /* Clean up the shift and the 2N mult now -- LTRANS runs no DCE between - widening_mul and expand, and a dead 2N mult would abort expand_mult. - Dead upstream (T_2N) casts, if any, are harmless NOP_EXPRs and land - with normal DCE. */ - if (has_zero_uses (gimple_assign_lhs (shift_stmt))) - { - gimple_stmt_iterator dgsi = gsi_for_stmt (shift_stmt); - gsi_remove (&dgsi, true); - release_defs (shift_stmt); - } - - /* The mult is either dead (low half recomputed elsewhere) or now read only - for its low half -- narrow_long_mul_low_half rewrites it, recursing into - its operands. Removing a dead mult can leave a chained 2N mult that fed - it low-half-only, so narrow those operands on that path. */ - gimple_stmt_iterator mgsi = gsi_for_stmt (mult_stmt); - if (has_zero_uses (gimple_assign_lhs (mult_stmt))) - { - tree op1 = gimple_assign_rhs1 (mult_stmt); - tree op2 = gimple_assign_rhs2 (mult_stmt); - gsi_remove (&mgsi, true); - release_defs (mult_stmt); - narrow_long_mul_operands (op1, op2); - } - else - narrow_long_mul_low_half (&mgsi); - - if (dump_file && (dump_flags & TDF_DETAILS)) - fprintf (dump_file, "Lowered long-mul high-part chain.\n"); - return true; -} - -/* True when pass_optimize_widening_mul will run. Shared with the - forwprop long-multiply recognizer so its wide-chain emit stays - paired with the lowering that rescues an unsupported 2N shape. - The -Og pipeline (pass_all_optimizations_g) does not contain - pass_optimize_widening_mul at all, so -Og -fexpensive-optimizations - must not enable the emit: the unlowered 2N multiply would reach - expand as an unexpandable mode (e.g. OImode) and ICE. - -fdisable-tree-widening_mul is not observed. */ - -bool -optimize_widening_mul_active_p (void) -{ - return flag_expensive_optimizations && optimize && !optimize_debug; -} - /* Find integer multiplications where the operands are extended from smaller types, and replace the MULT_EXPR with a WIDEN_MULT_EXPR or MULT_HIGHPART_EXPR where appropriate. */ @@ -7048,7 +6570,7 @@ public: /* opt_pass methods: */ bool gate (function *) final override { - return optimize_widening_mul_active_p (); + return flag_expensive_optimizations && optimize; } unsigned int execute (function *) final override; @@ -7116,8 +6638,6 @@ math_opts_dom_walker::after_dom_children (basic_block bb) switch (code) { case MULT_EXPR: - if (narrow_long_mul_low_half (&gsi)) - break; if (!convert_mult_to_widen (stmt, &gsi) && !convert_expand_mult_copysign (stmt, &gsi) && convert_mult_to_fma (stmt, @@ -7184,16 +6704,6 @@ math_opts_dom_walker::after_dom_children (basic_block bb) match_unsigned_saturation_mul (&gsi, as_a<gassign *> (stmt)); match_unsigned_saturation_trunc (&gsi, as_a<gassign *> (stmt)); match_saturation_add_with_assign (&gsi, as_a<gassign *> (stmt)); - /* fall-through */ - case CONVERT_EXPR: - /* The long-multiply recognizer's high-part emit ends in an - outer convert. If the trailing cast+mult+shift+cast - chain has no expansion strategy at the 2N width, lower - the whole chain to a longhand high-part at narrow - precision. */ - if (gsi_stmt (gsi) == stmt - && lower_long_mul_high_chain (&gsi)) - continue; break; default:; diff --git a/gcc/tree-ssa-math-opts.h b/gcc/tree-ssa-math-opts.h index 5de1697ff678..f750b52b5936 100644 --- a/gcc/tree-ssa-math-opts.h +++ b/gcc/tree-ssa-math-opts.h @@ -23,6 +23,4 @@ along with GCC; see the file COPYING3. If not see extern tree powi_as_mults (gimple_stmt_iterator *, location_t, tree, HOST_WIDE_INT); -extern bool optimize_widening_mul_active_p (void); - #endif /* GCC_TREE_SSA_MATH_OPTS_H */