[Qemu-devel] [PATCH v2 2/2] avx2 configure: Use primitives in test

["Dr. David Alan Gilbert (git)" <dgilbert@redhat.com>]

From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

Use the avx2 primitives during the test, thus making sure that the
compiler and assembler could actually use avx2.

This also detects the failure case on gcc 4.8.x with -save-temps
and avoids the need for the gcc version check in cutils.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 configure     | 15 +++++++++++----
 util/cutils.c |  8 +-------
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/configure b/configure
index 5693c60..6449e65 100755
--- a/configure
+++ b/configure
@@ -1781,12 +1781,19 @@ fi
 # avx2 optimization requirement check
 
 cat > $TMPC << EOF
-static void bar(void) {}
+#pragma GCC push_options
+#pragma GCC target("avx2")
+#include <cpuid.h>
+#include <immintrin.h>
+
+static int bar(void *a) {
+    return _mm256_movemask_epi8(_mm256_cmpeq_epi8(*(__m256i *)a, (__m256i){0}));
+}
 static void *bar_ifunc(void) {return (void*) bar;}
-void foo(void) __attribute__((ifunc("bar_ifunc")));
-int main(void) { foo(); return 0; }
+int foo(void *a) __attribute__((ifunc("bar_ifunc")));
+int main(int argc, char *argv[]) { return foo(argv[0]);}
 EOF
-if compile_prog "-mavx2" "" ; then
+if compile_prog "" ; then
     if readelf --syms $TMPE |grep "IFUNC.*foo" >/dev/null 2>&1; then
         avx2_opt="yes"
     fi
diff --git a/util/cutils.c b/util/cutils.c
index 43d1afb..5830a68 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -256,13 +256,7 @@ static size_t buffer_find_nonzero_offset_inner(const void *buf, size_t len)
     return i * sizeof(VECTYPE);
 }
 
-/*
- * GCC before version 4.9 has a bug which will cause the target
- * attribute work incorrectly and failed to compile in some case,
- * restrict the gcc version to 4.9+ to prevent the failure.
- */
-
-#if defined CONFIG_AVX2_OPT && QEMU_GNUC_PREREQ(4, 9)
+#if defined CONFIG_AVX2_OPT
 #pragma GCC push_options
 #pragma GCC target("avx2")
 #include <cpuid.h>
-- 
2.7.4