[gcc(refs/vendors/ibm/heads/dmr-support)] rs6000: Add DMR extract builtins for Dense Math support

https://gcc.gnu.org/g:be3af1c57c71a884f10da4f999ccb204123a5d15

commit be3af1c57c71a884f10da4f999ccb204123a5d15
Author: Surya Kumari Jangala <[email protected]>
Date:   Wed Jul 8 05:20:19 2026 -0500

    rs6000: Add DMR extract builtins for Dense Math support
    
    Add two new builtins for extracting data from 1024-bit Dense Math
    Registers (DMRs):
    
      - __builtin_mma_dmr_extract512 (void *, dm1024 *, const int<2>):
        extracts one 512-bit half of a DMR into four 128-bit vectors.
      - __builtin_mma_disassemble_dmr (void *, dm1024 *):
        extracts both 512-bit halves of a DMR into eight 128-bit vectors.
    
    2026-07-08  Surya Kumari Jangala  <[email protected]>
    
    gcc:
            * config/rs6000/rs6000-builtins.def (__builtin_mma_dmr_extract512): New
            built-in.
            (__builtin_mma_disassemble_dmr): Likewise.
            (__builtin_mma_dmr_extract512_internal): New internal built-in.
            * config/rs6000/mma.md (UNSPEC_DM_EXTRACT1024): New UNSPEC entry.
            * config/rs6000/rs6000-builtin.cc (rs6000_gimple_fold_mma_builtin):
            Exempt RS6000_BIF_DISASSEMBLE_DMR from the early-return guard.
            Handle RS6000_BIF_DM_EXTRACT512 and RS6000_BIF_DISASSEMBLE_DMR.
    
    gcc/testsuite:
            * gcc.target/powerpc/dmf-extract512.c: New test.
            * gcc.target/powerpc/dmf-disassemble-dmr.c: New test.

Diff:
---
 gcc/config/rs6000/mma.md                           |  1 +
 gcc/config/rs6000/rs6000-builtin.cc                | 73 +++++++++++++++++++++-
 gcc/config/rs6000/rs6000-builtins.def              |  9 +++
 .../gcc.target/powerpc/dmf-disassemble-dmr.c       | 24 +++++++
 gcc/testsuite/gcc.target/powerpc/dmf-extract512.c  | 20 ++++++
 5 files changed, 125 insertions(+), 2 deletions(-)

diff --git a/gcc/config/rs6000/mma.md b/gcc/config/rs6000/mma.md
index 07274bc54d05..3328105fcd57 100644
--- a/gcc/config/rs6000/mma.md
+++ b/gcc/config/rs6000/mma.md
@@ -94,6 +94,7 @@
    UNSPEC_DM_INSERT512
    UNSPEC_DMF_EXTRACT512
    UNSPEC_DMF_INSERT1024
+   UNSPEC_DM_EXTRACT1024
    UNSPEC_DMF_DMXOR
    UNSPEC_DMF_DMXVI8GERX4
    UNSPEC_DMF_DMXVI8GERX4PP
diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc
index e16ebb54065b..a9814aa62ffa 100644
--- a/gcc/config/rs6000/rs6000-builtin.cc
+++ b/gcc/config/rs6000/rs6000-builtin.cc
@@ -1127,11 +1127,12 @@ rs6000_gimple_fold_mma_builtin (gimple_stmt_iterator *gsi,
 
   /* Each call that can be gimple-expanded has an associated built-in
      function that it will expand into.  If this one doesn't, we have
-     already expanded it!  Exceptions: lxvp and stxvp.  */
+     already expanded it!  Exceptions: lxvp, stxvp and disassemble_dmr.  */
   if (rs6000_builtin_info[fncode].assoc_bif == RS6000_BIF_NONE
       && fncode != RS6000_BIF_LXVP
       && fncode != RS6000_BIF_STXVP
-      && fncode != RS6000_BIF_DMMR)
+      && fncode != RS6000_BIF_DMMR
+      && fncode != RS6000_BIF_DISASSEMBLE_DMR)
     return false;
 
   bifdata *bd = &rs6000_builtin_info[fncode];
@@ -1139,6 +1140,74 @@ rs6000_gimple_fold_mma_builtin (gimple_stmt_iterator *gsi,
   gimple *new_call;
   tree new_decl;
 
+  if (fncode == RS6000_BIF_DM_EXTRACT512
+      || fncode == RS6000_BIF_DISASSEMBLE_DMR)
+    {
+      unsigned num_extract512;
+      push_gimplify_context (true);
+      tree dst_ptr = gimple_call_arg (stmt, 0);
+      tree src_ptr = gimple_call_arg (stmt, 1);
+      tree src_type = build_pointer_type (dmr1024_type_node);
+
+      if (TREE_TYPE (src_ptr) != src_type)
+	src_ptr = build1 (NOP_EXPR, src_type, src_ptr);
+
+      /* The following code will ensure we are sending *src as parameter.  */
+      tree src = make_ssa_name (TREE_TYPE (src_type));
+      gimplify_assign (src, build_simple_mem_ref (src_ptr), &new_seq);
+
+      /* Now we should call the internal builtin RS6000_BIF_DM_EXTRACT512_INTERNAL.  */
+      if (fncode == RS6000_BIF_DISASSEMBLE_DMR)
+	num_extract512 = 2;
+      else
+	num_extract512 = 1;
+
+      tree extract_decl = rs6000_builtin_decls[RS6000_BIF_DM_EXTRACT512_INTERNAL];
+
+      for (unsigned i = 0; i < num_extract512; i++)
+	{
+	  tree const_arg;
+	  if (fncode == RS6000_BIF_DISASSEMBLE_DMR)
+	    const_arg = build_int_cstu (uint16_type_node, i);
+	  else
+	    const_arg = gimple_call_arg (stmt, 2);
+
+	  /* Create call.  */
+	  new_call = gimple_build_call (extract_decl, 2, src, const_arg);
+	  /* Create a tmp reg to denote lhs of call.  */
+	  tree lhs = make_ssa_name (vector_quad_type_node);
+
+	  /* lhs = new_call  */
+	  gimple_call_set_lhs (new_call, lhs);
+
+	  /* Add gimple stmt to gimple sequence.  */
+	  gimple_seq_add_stmt (&new_seq, new_call);
+
+	  /* Now lhs contains the 512-bit value in vector_quad. We have to now
+	     split up the vector_quad into individual vectors.  */
+
+	  new_decl = rs6000_builtin_decls[RS6000_BIF_DISASSEMBLE_ACC_INTERNAL];
+	  tree dst_type = build_pointer_type_for_mode (unsigned_V16QI_type_node,
+						       ptr_mode, true);
+
+	  tree dst_base = build1 (NOP_EXPR, dst_type, dst_ptr);
+	  for (unsigned j = 0; j < 4; j++)
+	    {
+	      tree dst = build2 (MEM_REF, unsigned_V16QI_type_node, dst_base,
+				 build_int_cst (dst_type, j * 16 + i * 64));
+	      tree dstssa = make_ssa_name (unsigned_V16QI_type_node);
+	      new_call = gimple_build_call (new_decl, 2, lhs,
+					    build_int_cstu (uint16_type_node, j));
+	      gimple_call_set_lhs (new_call, dstssa);
+	      gimple_seq_add_stmt (&new_seq, new_call);
+	      gimplify_assign (dst, dstssa, &new_seq);
+	    }
+	}
+      pop_gimplify_context (NULL);
+      gsi_replace_with_seq (gsi, new_seq, true);
+      return true;
+    }
+
   /* Compatibility built-ins; we used to call these
      __builtin_mma_{dis,}assemble_pair, but now we call them
      __builtin_vsx_{dis,}assemble_pair.  Handle the old versions.  */
diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
index dc39ef2e5262..a6ba2f869cbb 100644
--- a/gcc/config/rs6000/rs6000-builtins.def
+++ b/gcc/config/rs6000/rs6000-builtins.def
@@ -4056,6 +4056,12 @@
   dmr1024 __builtin_dmmr_internal (dmr1024);
     DMMR_INTERNAL movtdo {dm}
 
+  void __builtin_mma_dmr_extract512 (void *, dmr1024 *, const int<2>);
+    DM_EXTRACT512 nothing {dm,dmint}
+
+  v512 __builtin_mma_dmr_extract512_internal (dmr1024, const int<2>);
+    DM_EXTRACT512_INTERNAL dm_extract512 {dm}
+
   void __builtin_dmxor (dmr1024 *, dmr1024 *);
     DMXOR nothing {dm,dmint,dmr}
 
@@ -4068,6 +4074,9 @@
   dmr1024 __builtin_build_dmr_internal (vuc, vuc, vuc, vuc, vuc, vuc, vuc, vuc);
     BUILD_DMR_INTERNAL dmf_build_dmr {dm}
 
+  void __builtin_mma_disassemble_dmr (void *, dmr1024 *);
+    DISASSEMBLE_DMR nothing {dm}
+
   void __builtin_mma_dmxvi8gerx4 (dmr1024 *, v256, vuc);
     DMXVI8GERX4 nothing {dm,dmint}
 
diff --git a/gcc/testsuite/gcc.target/powerpc/dmf-disassemble-dmr.c b/gcc/testsuite/gcc.target/powerpc/dmf-disassemble-dmr.c
new file mode 100644
index 000000000000..3ad2dc43bdef
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/dmf-disassemble-dmr.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_future_compile_ok } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+typedef unsigned char vec_t __attribute__((vector_size(16)));
+
+void
+bar (vec_t *dst, __dmr1024 *src)
+{
+  vec_t res[8];
+  __builtin_mma_disassemble_dmr (res, src);
+  dst[0] = res[0];
+  dst[2] = res[1];
+  dst[4] = res[2];
+  dst[6] = res[3];
+  dst[8] = res[4];
+  dst[10] = res[5];
+  dst[12] = res[6];
+  dst[14] = res[7];
+}
+
+/* { dg-final { scan-assembler-times {\mdmxxextfdmr512\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mstxv\M} 8 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/dmf-extract512.c b/gcc/testsuite/gcc.target/powerpc/dmf-extract512.c
new file mode 100644
index 000000000000..cf4163d9b058
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/dmf-extract512.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_future_compile_ok } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-mdejagnu-cpu=future -O2" } */
+
+typedef unsigned char vec_t __attribute__((vector_size(16)));
+
+void
+bar (vec_t *dst, __dmr1024 *src)
+{
+  vec_t res[4];
+  __builtin_mma_dmr_extract512 (res, src, 0);
+  dst[0] = res[0];
+  dst[2] = res[1];
+  dst[4] = res[2];
+  dst[6] = res[3];
+}
+
+/* { dg-final { scan-assembler-times {\mdmxxextfdmr512\M} 1 } } */
+/* { dg-final { scan-assembler-times {\mstxv\M} 4 } } */