From: Haochen Jiang <haochen.jiang@intel.com>
Date: Wed, 24 Apr 2024 02:43:18 +0000 (+0800)
Subject: i386: Fix behavior for both using AVX10.1-256 in options and function attribute
X-Git-Tag: basepoints/gcc-15~35
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=d279c9d89b2f6ce89c1eec0ff4b980e9c5f51fd1;p=thirdparty%2Fgcc.git

i386: Fix behavior for both using AVX10.1-256 in options and function attribute

When we are using -mavx10.1-256 in command line and avx10.1-256 in
target attribute together, zmm should never be generated. But current
GCC will generate zmm since it wrongly enables EVEX512 for non-explicitly
set AVX512. This patch will fix that issue.

gcc/ChangeLog:

	* config/i386/i386-options.cc (ix86_valid_target_attribute_tree):
	Check whether AVX512F is explicitly enabled.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/avx10_1-24.c: New test.
---

diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 68a2e1c69109..ac48b5c61c4d 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -1431,6 +1431,7 @@ ix86_valid_target_attribute_tree (tree fndecl, tree args,
      scenario.  */
   if ((def->x_ix86_isa_flags2 & OPTION_MASK_ISA2_AVX10_1_256)
       && (opts->x_ix86_isa_flags & OPTION_MASK_ISA_AVX512F)
+      && (opts->x_ix86_isa_flags_explicit & OPTION_MASK_ISA_AVX512F)
       && !(def->x_ix86_isa_flags2_explicit & OPTION_MASK_ISA2_EVEX512)
       && !(opts->x_ix86_isa_flags2_explicit & OPTION_MASK_ISA2_EVEX512))
     opts->x_ix86_isa_flags2 |= OPTION_MASK_ISA2_EVEX512;
diff --git a/gcc/testsuite/gcc.target/i386/avx10_1-24.c b/gcc/testsuite/gcc.target/i386/avx10_1-24.c
new file mode 100644
index 000000000000..2e93f041760d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx10_1-24.c
@@ -0,0 +1,7 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64 -mavx10.1" } */
+/* { dg-final { scan-assembler-not "%zmm" } } */
+
+typedef float __m512 __attribute__ ((__vector_size__ (64), __may_alias__));
+
+void __attribute__((target("avx10.1-256"))) callee256(__m512 *a, __m512 *b) { *a = *b; }