[PATCH] Emulate clock and other stubs on nvptx
"Roger Sayle" <[email protected]>
| Newsgroups | gmane.comp.lib.newlib |
|---|---|
| Message-ID | <[email protected]> |
Please be gentle, this is my first patch to newlib. This patch to the libc/machine/nvptx port of newlib implements an approximation of "clock" and provides some additional stub routines. These changes not only reduce the number of (link) failures in the GCC testsuite when targeting nvptx-none, but also allow the NIST scimark4 benchmark to compile and run without modification. newlib already contains support for backends to provide their own clock implementations via -DCLOCK_PROVIDED. That functionality is used here to return an approximate elapsed time based on the NVidia GPU's clock64 cycle counter. Although not great, this is better than the current behaviour of link error from the unresolved symbol _times_r. The other part of the patch is to add a small number of stub functions to nvptx's misc.c. Adding isatty, for example, resolves linking problems in libc from the dependency in __smakebuf_r, and the sync stub, for example, fixes the failure with GCC's testsuite/gfortran.dg/ISO_Fortran_binding_14.f90 [which simply tests that gfortran can call a/any C function]. Hopefully, these changes are acceptable. If so, if someone could please commit them for me that would be much appreciated (as I don't have repository access). Likewise, these changes should be obvious enough to not require a copyright assignment, but to avoid any objections, I'm happy to put them in the public domain. 2021-08-18 Roger Sayle <[email protected]> newlib/ configure.host: Add -DCLOCK_PROVIDED to newlib_cflags on nvptx*. newlib/libc/machine/nvptx Makefile.am: Add clock.c to lib_a_SOURCES. clock.c: New source file to implement/approximate clock(). misc.c: Add stubs for fstat, isatty, open, sync and unlink. Makefile.in: Regenerate. Many thanks in advance, Roger -- Roger Sayle NextMove Software Limited Cambridge, UK
newlib.patch
(application/octet-stream, 1.6 KB)
diff --git a/newlib/configure.host b/newlib/configure.host
index 4ac5334..ef481ff 100644
--- a/newlib/configure.host
+++ b/newlib/configure.host
@@ -289,7 +289,7 @@ case "${host_cpu}" in
;;
nvptx*)
machine_dir=nvptx
- newlib_cflags="${newlib_cflags} -DMALLOC_PROVIDED"
+ newlib_cflags="${newlib_cflags} -DCLOCK_PROVIDED -DMALLOC_PROVIDED"
;;
or1k*|or1knd*)
machine_dir=or1k
diff --git a/newlib/libc/machine/nvptx/Makefile.am b/newlib/libc/machine/nvptx/Makefile.am
index 66664d3..0cb20cc 100644
--- a/newlib/libc/machine/nvptx/Makefile.am
+++ b/newlib/libc/machine/nvptx/Makefile.am
@@ -10,7 +10,7 @@ noinst_LIBRARIES = lib.a
lib_a_SOURCES = calloc.c callocr.c malloc.c mallocr.c realloc.c reallocr.c \
free.c write.c assert.c puts.c putchar.c printf.c abort.c \
- exit.c misc.c
+ exit.c misc.c clock.c
lib_a_CFLAGS = $(AM_CFLAGS)
ACLOCAL_AMFLAGS = -I ../../.. -I ../../../..
diff --git a/newlib/libc/machine/nvptx/misc.c b/newlib/libc/machine/nvptx/misc.c
index ed1bc34..3609241 100644
--- a/newlib/libc/machine/nvptx/misc.c
+++ b/newlib/libc/machine/nvptx/misc.c
@@ -15,6 +15,7 @@
#include <errno.h>
#include <sys/types.h>
+#include <sys/stat.h>
#undef errno
extern int errno;
@@ -23,12 +24,37 @@ close(int fd) {
return -1;
}
+int
+fstat (int fd, struct stat *buf) {
+ return -1;
+}
+
+int
+isatty (int fd) {
+ return fd == 1;
+}
+
off_t
lseek(int fd, off_t offset, int whence) {
return 0;
}
int
+open (const char *pathname, int flags, ...) {
+ return -1;
+}
+
+int
read(int fd, void *buf, size_t count) {
return 0;
}
+
+void
+sync (void) {
+}
+
+int
+unlink (const char *pathname) {
+ return -1;
+}
+
clock.c
(text/plain, 776 B)
/* clock.c
* Support file for nvptx in newlib.
*/
#include <time.h>
/* PTX's clock64 is a cycle count, whose frequency varies with the GPU's
operating frequency, which may be boosted or thermally throttled at
run-time. The value provided is suitable for relative timings, but
must be corrected [by the host] for accurate elapsed/wall clock times. */
/* NVidia RTX-2080 Super 1650-1815 MHz. */
/* NVidia GTX-1070 1506-1683 MHz. */
/* NVidia RTX-2070 1410 MHz. */
/* NVidia GTX-1050 Ti 1290-1392 MHz. */
/* NVidia Quadro P400 1228-1252 MHz. */
/* NVidia GTX 660 823 MHz. */
#define NVPTX_MHZ 1250
clock_t
clock ()
{
unsigned long long now;
asm volatile("mov.u64 %0, %%clock64;" : "=r"(now));
return now/((NVPTX_MHZ*1000000)/CLOCKS_PER_SEC);
}