From: Debian Science Team <debian-science-maintainers@lists.alioth.debian.org>
Date: Sun, 25 Jun 2023 19:56:08 +0000 (+0100)
Subject: Fix incorrect results of AVX512 DGEMM kernel when built on pre-AVX2 machine
X-Git-Tag: archive/raspbian/0.3.13+ds-3+rpi1+deb11u1^2~1
X-Git-Url: https://dgit.raspbian.org/?a=commitdiff_plain;h=0dee94d5bf64eb881d61b639d78415652ea864ad;p=openblas.git

Fix incorrect results of AVX512 DGEMM kernel when built on pre-AVX2 machine

Origin: upstream, https://github.com/xianyi/OpenBLAS/pull/3579
Bug: https://github.com/xianyi/OpenBLAS/issues/2986
     https://github.com/xianyi/OpenBLAS/issues/3454
     https://github.com/xianyi/OpenBLAS/issues/3557
Bug-Debian: https://bugs.debian.org/1025480
Applied-Upstream: 0.3.21
Reviewed-by: Sébastien Villemot <sebastien@debian.org>
Last-Update: 2023-06-26

When building OpenBLAS with dynamic arch selection on x86-64 hardware
that does not support AVX2 (e.g. Intel Ivybridge or earlier), then
the AVX512 (SkylakeX) kernel for DGEMM would produce incorrect
results (of course when run on AVX512-capable hardware).

The problem was that the check for determining whether the compiler
is able to understand AVX512 assembly/intrinsics was doubly
incorrect: it would test the build machine capabilities (instead of
the compiler capabilities); and it would check for AVX2 instead of
AVX512. As a consequence, on pre-AVX2 hardware, the build system
would conclude that the compiler is not able to understand AVX512
primitives, and would create a broken AVX512 (SkylakeX) DGEMM kernel
(essentially a Haswell kernel, but with some wrong assumptions, hence
leading to incorrect numerical results).
Last-Update: 2023-06-26
Gbp-Pq: Name avx512-dgemm.patch
---

diff --git a/Makefile.prebuild b/Makefile.prebuild
index d6395da..05f102d 100644
--- a/Makefile.prebuild
+++ b/Makefile.prebuild
@@ -67,7 +67,8 @@ endif
 
 
 getarch : getarch.c cpuid.S dummy $(CPUIDEMU)
-	$(HOSTCC) $(HOST_CFLAGS) $(EXFLAGS) -o $(@F) getarch.c cpuid.S $(CPUIDEMU)
+	avx512=$$(perl c_check - - gcc | grep NO_AVX512); \
+	$(HOSTCC) $(HOST_CFLAGS) $(EXFLAGS) $${avx512:+-D$${avx512}} -o $(@F) getarch.c cpuid.S $(CPUIDEMU)
 
 getarch_2nd : getarch_2nd.c config.h dummy
 ifndef TARGET_CORE
diff --git a/c_check b/c_check
index 970d475..1d2464d 100644
--- a/c_check
+++ b/c_check
@@ -240,7 +240,7 @@ if (($architecture eq "x86") || ($architecture eq "x86_64")) {
 #	$tmpf = new File::Temp( UNLINK => 1 );
 	($fh,$tmpf) = tempfile( SUFFIX => '.c' , UNLINK => 1 );
 	$code = '"vbroadcastss -4 * 4(%rsi), %zmm2"';
-	print $tmpf "#include <immintrin.h>\n\nint main(void){ __asm__ volatile($code); }\n";
+	print $fh "#include <immintrin.h>\n\nint main(void){ __asm__ volatile($code); }\n";
 	$args = " -march=skylake-avx512 -c -o $tmpf.o $tmpf";
 	if ($compiler eq "PGI") {
 	    $args = " -tp skylake -c -o $tmpf.o $tmpf";
@@ -264,7 +264,7 @@ if ($data =~ /HAVE_C11/) {
        $c11_atomics = 0;
     } else {
        ($fh,$tmpf) = tempfile( SUFFIX => '.c' , UNLINK => 1 );
-       print $tmpf "#include <stdatomic.h>\nint main(void){}\n";
+       print $fh "#include <stdatomic.h>\nint main(void){}\n";
        $args = " -c -o $tmpf.o $tmpf";
        my @cmd = ("$compiler_name $flags $args >/dev/null 2>/dev/null");
        system(@cmd) == 0;
diff --git a/getarch.c b/getarch.c
index f48944f..7d59d0e 100644
--- a/getarch.c
+++ b/getarch.c
@@ -94,14 +94,6 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <sys/sysinfo.h>
 #endif
 
-#if defined(__x86_64__) || defined(_M_X64)
-#if (( defined(__GNUC__)  && __GNUC__   > 6 && defined(__AVX2__)) || (defined(__clang__) && __clang_major__ >= 6))
-#else
-#ifndef NO_AVX512
-#define NO_AVX512
-#endif
-#endif
-#endif
 /* #define FORCE_P2		*/
 /* #define FORCE_KATMAI		*/
 /* #define FORCE_COPPERMINE	*/