Hi,

This patch checks SSE and YMM state support for -march=native.  Tested
on Linux/x86-64.  OK to install?

Thanks.


H.J.
---
2012-10-02  H.J. Lu  <hongjiu...@intel.com>

        PR target/54741
        *  config/i386/driver-i386.c (XCR_XFEATURE_ENABLED_MASK): New.
        (XSTATE_FP): Likewise.
        (XSTATE_SSE): Likewise.
        (XSTATE_YMM): Likewise.
        (host_detect_local_cpu): Disable AVX, AVX2, FMA, FMA4 and XOP if
        SSE and YMM states aren't supported.

diff --git a/gcc/config/i386/driver-i386.c b/gcc/config/i386/driver-i386.c
index bda4e02..4dffc51 100644
--- a/gcc/config/i386/driver-i386.c
+++ b/gcc/config/i386/driver-i386.c
@@ -390,6 +390,7 @@ const char *host_detect_local_cpu (int argc, const char 
**argv)
   unsigned int has_hle = 0, has_rtm = 0;
   unsigned int has_rdrnd = 0, has_f16c = 0, has_fsgsbase = 0;
   unsigned int has_rdseed = 0, has_prfchw = 0, has_adx = 0;
+  unsigned int has_osxsave = 0;
 
   bool arch;
 
@@ -431,6 +432,7 @@ const char *host_detect_local_cpu (int argc, const char 
**argv)
   has_sse4_1 = ecx & bit_SSE4_1;
   has_sse4_2 = ecx & bit_SSE4_2;
   has_avx = ecx & bit_AVX;
+  has_osxsave = ecx & bit_OSXSAVE;
   has_cmpxchg16b = ecx & bit_CMPXCHG16B;
   has_movbe = ecx & bit_MOVBE;
   has_popcnt = ecx & bit_POPCNT;
@@ -460,6 +462,26 @@ const char *host_detect_local_cpu (int argc, const char 
**argv)
       has_adx = ebx & bit_ADX;
     }
 
+  /* Get XCR_XFEATURE_ENABLED_MASK register with xgetbv.  */
+#define XCR_XFEATURE_ENABLED_MASK      0x0
+#define XSTATE_FP                      0x1
+#define XSTATE_SSE                     0x2
+#define XSTATE_YMM                     0x4
+  if (has_osxsave)
+    asm (".byte 0x0f; .byte 0x01; .byte 0xd0"
+        : "=a" (eax), "=d" (edx)
+        : "c" (XCR_XFEATURE_ENABLED_MASK));
+
+  /* Check if SSE and YMM states are supported.  */
+  if ((eax & (XSTATE_SSE | XSTATE_YMM)) == (XSTATE_SSE | XSTATE_YMM))
+    {
+      has_avx = 0;
+      has_avx2 = 0;
+      has_fma = 0;
+      has_fma4 = 0;
+      has_xop = 0;
+    }
+
   /* Check cpuid level of extended features.  */
   __cpuid (0x80000000, ext_level, ebx, ecx, edx);
 

Reply via email to