gallium: detect avx512 cpu features

v3: fix check for xmm/ymm test
v2: style code, add avx512 to cpu dump

Reviewed-by: Roland Scheidegger <sroland@vmware.com>

diff --git a/src/gallium/auxiliary/util/u_cpu_detect.c b/src/gallium/auxiliary/util/u_cpu_detect.c
index 3a51ab95cf042a0dfef4cf1230e4fb05638537b4..845fc6b34d5cbe10adbe3dcc72ffd21526168ae5 100644 (file)
--- a/src/gallium/auxiliary/util/u_cpu_detect.c
+++ b/src/gallium/auxiliary/util/u_cpu_detect.c
@@ -388,6 +388,23 @@ util_cpu_detect(void)
          util_cpu_caps.has_avx2 = (regs7[1] >> 5) & 1;
       }
 
+      // check for avx512
+      if (((regs2[2] >> 27) & 1) && // OSXSAVE
+          (xgetbv() & (0x7 << 5)) && // OPMASK: upper-256 enabled by OS
+          ((xgetbv() & 6) == 6)) { // XMM/YMM enabled by OS
+         uint32_t regs3[4];
+         cpuid(0x00000007, regs3);
+         util_cpu_caps.has_avx512f    = (regs3[1] >> 16) & 1;
+         util_cpu_caps.has_avx512dq   = (regs3[1] >> 17) & 1;
+         util_cpu_caps.has_avx512ifma = (regs3[1] >> 21) & 1;
+         util_cpu_caps.has_avx512pf   = (regs3[1] >> 26) & 1;
+         util_cpu_caps.has_avx512er   = (regs3[1] >> 27) & 1;
+         util_cpu_caps.has_avx512cd   = (regs3[1] >> 28) & 1;
+         util_cpu_caps.has_avx512bw   = (regs3[1] >> 30) & 1;
+         util_cpu_caps.has_avx512vl   = (regs3[1] >> 31) & 1;
+         util_cpu_caps.has_avx512vbmi = (regs3[2] >>  1) & 1;
+      }
+
       if (regs[1] == 0x756e6547 && regs[2] == 0x6c65746e && regs[3] == 0x49656e69) {
          /* GenuineIntel */
          util_cpu_caps.has_intel = 1;
@@ -455,6 +472,15 @@ util_cpu_detect(void)
       debug_printf("util_cpu_caps.has_xop = %u\n", util_cpu_caps.has_xop);
       debug_printf("util_cpu_caps.has_altivec = %u\n", util_cpu_caps.has_altivec);
       debug_printf("util_cpu_caps.has_daz = %u\n", util_cpu_caps.has_daz);
+      debug_printf("util_cpu_caps.has_avx512f = %u\n", util_cpu_caps.has_avx512f);
+      debug_printf("util_cpu_caps.has_avx512dq = %u\n", util_cpu_caps.has_avx512dq);
+      debug_printf("util_cpu_caps.has_avx512ifma = %u\n", util_cpu_caps.has_avx512ifma);
+      debug_printf("util_cpu_caps.has_avx512pf = %u\n", util_cpu_caps.has_avx512pf);
+      debug_printf("util_cpu_caps.has_avx512er = %u\n", util_cpu_caps.has_avx512er);
+      debug_printf("util_cpu_caps.has_avx512cd = %u\n", util_cpu_caps.has_avx512cd);
+      debug_printf("util_cpu_caps.has_avx512bw = %u\n", util_cpu_caps.has_avx512bw);
+      debug_printf("util_cpu_caps.has_avx512vl = %u\n", util_cpu_caps.has_avx512vl);
+      debug_printf("util_cpu_caps.has_avx512vbmi = %u\n", util_cpu_caps.has_avx512vbmi);
    }
 #endif
 

diff --git a/src/gallium/auxiliary/util/u_cpu_detect.h b/src/gallium/auxiliary/util/u_cpu_detect.h
index c873232beccb8acf67964d6580d6474ede54b91b..3bd7294f075950e763a1f2bd88c7b74000bb9f53 100644 (file)
--- a/src/gallium/auxiliary/util/u_cpu_detect.h
+++ b/src/gallium/auxiliary/util/u_cpu_detect.h
@@ -72,6 +72,16 @@ struct util_cpu_caps {
    unsigned has_xop:1;
    unsigned has_altivec:1;
    unsigned has_daz:1;
+
+   unsigned has_avx512f:1;
+   unsigned has_avx512dq:1;
+   unsigned has_avx512ifma:1;
+   unsigned has_avx512pf:1;
+   unsigned has_avx512er:1;
+   unsigned has_avx512cd:1;
+   unsigned has_avx512bw:1;
+   unsigned has_avx512vl:1;
+   unsigned has_avx512vbmi:1;
 };
 
 extern struct util_cpu_caps