Fix SSE and YMM state support check logic for -march=native

[pf3gnuchains/gcc-fork.git] / gcc / config / i386 / driver-i386.c

diff --git a/gcc/config/i386/driver-i386.c b/gcc/config/i386/driver-i386.c
index b7a1f52..7b5e4d7 100644 (file)
--- a/gcc/config/i386/driver-i386.c
+++ b/gcc/config/i386/driver-i386.c
@@ -396,7 +396,9 @@ const char *host_detect_local_cpu (int argc, const char **argv)
   unsigned int has_popcnt = 0, has_aes = 0, has_avx = 0, has_avx2 = 0;
   unsigned int has_pclmul = 0, has_abm = 0, has_lwp = 0;
   unsigned int has_fma = 0, has_fma4 = 0, has_xop = 0;
-  unsigned int has_bmi = 0, has_tbm = 0, has_lzcnt = 0;
+  unsigned int has_bmi = 0, has_bmi2 = 0, has_tbm = 0, has_lzcnt = 0;
+  unsigned int has_rdrnd = 0, has_f16c = 0, has_fsgsbase = 0;
+  unsigned int has_osxsave = 0;
 
   bool arch;
 
@@ -438,12 +440,15 @@ 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;
   has_aes = ecx & bit_AES;
   has_pclmul = ecx & bit_PCLMUL;
   has_fma = ecx & bit_FMA;
+  has_f16c = ecx & bit_F16C;
+  has_rdrnd = ecx & bit_RDRND;
 
   has_cmpxchg8b = edx & bit_CMPXCHG8B;
   has_cmov = edx & bit_CMOV;
@@ -451,6 +456,37 @@ const char *host_detect_local_cpu (int argc, const char **argv)
   has_sse = edx & bit_SSE;
   has_sse2 = edx & bit_SSE2;
 
+  if (max_level >= 7)
+    {
+      __cpuid_count (7, 0, eax, ebx, ecx, edx);
+
+      has_bmi = ebx & bit_BMI;
+      has_avx2 = ebx & bit_AVX2;
+      has_bmi2 = ebx & bit_BMI2;
+      has_fsgsbase = ebx & bit_FSGSBASE;
+    }
+
+  /* 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 (!has_osxsave
+      || (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);
 
@@ -470,11 +506,6 @@ const char *host_detect_local_cpu (int argc, const char **argv)
       has_longmode = edx & bit_LM;
       has_3dnowp = edx & bit_3DNOWP;
       has_3dnow = edx & bit_3DNOW;
-
-      __cpuid (0x7, eax, ebx, ecx, edx);
-
-      has_bmi = ebx & bit_BMI;
-      has_avx2 = ebx & bit_AVX2;
     }
 
   if (!arch)
@@ -511,7 +542,7 @@ const char *host_detect_local_cpu (int argc, const char **argv)
        processor = PROCESSOR_AMDFAM10;
       else if (has_sse2 || has_longmode)
        processor = PROCESSOR_K8;
-      else if (has_3dnowp)
+      else if (has_3dnowp && family == 6)
        processor = PROCESSOR_ATHLON;
       else if (has_mmx)
        processor = PROCESSOR_K6;
@@ -715,16 +746,21 @@ const char *host_detect_local_cpu (int argc, const char **argv)
       const char *fma4 = has_fma4 ? " -mfma4" : " -mno-fma4";
       const char *xop = has_xop ? " -mxop" : " -mno-xop";
       const char *bmi = has_bmi ? " -mbmi" : " -mno-bmi";
+      const char *bmi2 = has_bmi2 ? " -mbmi2" : " -mno-bmi2";
       const char *tbm = has_tbm ? " -mtbm" : " -mno-tbm";
       const char *avx = has_avx ? " -mavx" : " -mno-avx";
       const char *avx2 = has_avx2 ? " -mavx2" : " -mno-avx2";
       const char *sse4_2 = has_sse4_2 ? " -msse4.2" : " -mno-sse4.2";
       const char *sse4_1 = has_sse4_1 ? " -msse4.1" : " -mno-sse4.1";
       const char *lzcnt = has_lzcnt ? " -mlzcnt" : " -mno-lzcnt";
+      const char *rdrnd = has_rdrnd ? " -mrdrnd" : " -mno-rdrnd";
+      const char *f16c = has_f16c ? " -mf16c" : " -mno-f16c";
+      const char *fsgsbase = has_fsgsbase ? " -mfsgsbase" : " -mno-fsgsbase";
 
       options = concat (options, cx16, sahf, movbe, ase, pclmul,
-                       popcnt, abm, lwp, fma, fma4, xop, bmi, tbm,
-                       avx2, avx, sse4_2, sse4_1, lzcnt, NULL);
+                       popcnt, abm, lwp, fma, fma4, xop, bmi, bmi2,
+                       tbm, avx, avx2, sse4_2, sse4_1, lzcnt, rdrnd,
+                       f16c, fsgsbase, NULL);
     }
 
 done: