x86-64: Improve branch predication in _dl_runtime_resolve_avx512_opt [BZ #21258]

On Skylake server, _dl_runtime_resolve_avx512_opt is used to preserve
the first 8 vector registers.  The code layout is

  if only %xmm0 - %xmm7 registers are used
     preserve %xmm0 - %xmm7 registers
  if only %ymm0 - %ymm7 registers are used
     preserve %ymm0 - %ymm7 registers
  preserve %zmm0 - %zmm7 registers

Branch predication always executes the fallthrough code path to preserve
%zmm0 - %zmm7 registers speculatively, even though only %xmm0 - %xmm7
registers are used.  This leads to lower CPU frequency on Skylake
server.  This patch changes the fallthrough code path to preserve
%xmm0 - %xmm7 registers instead:

  if whole %zmm0 - %zmm7 registers are used
    preserve %zmm0 - %zmm7 registers
  if only %ymm0 - %ymm7 registers are used
     preserve %ymm0 - %ymm7 registers
  preserve %xmm0 - %xmm7 registers

Tested on Skylake server.

	[BZ #21258]
	* sysdeps/x86_64/dl-trampoline.S (_dl_runtime_resolve_opt):
	Define only if _dl_runtime_resolve is defined to
	_dl_runtime_resolve_sse_vex.
	* sysdeps/x86_64/dl-trampoline.h (_dl_runtime_resolve_opt):
	Fallthrough to _dl_runtime_resolve_sse_vex.

diff --git a/ChangeLog b/ChangeLog
index 3ed2df8719ff7082f4690dc384f1be0d74485ebd..1367e8eaaa788ce6ce26fcab86096b9a9858a176 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,12 @@
+2017-03-21  H.J. Lu  <hongjiu.lu@intel.com>
+
+       [BZ #21258]
+       * sysdeps/x86_64/dl-trampoline.S (_dl_runtime_resolve_opt):
+       Define only if _dl_runtime_resolve is defined to
+       _dl_runtime_resolve_sse_vex.
+       * sysdeps/x86_64/dl-trampoline.h (_dl_runtime_resolve_opt):
+       Fallthrough to _dl_runtime_resolve_sse_vex.
+
 2017-03-21  Joseph Myers  <joseph@codesourcery.com>
 
        * INSTALL: Regenerated.

diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S
index 33d7fcf7d079f717c240baa25da22f89d1d960dd..c14c61aa58bafa865bc1d6de0e314583379fa292 100644 (file)
--- a/sysdeps/x86_64/dl-trampoline.S
+++ b/sysdeps/x86_64/dl-trampoline.S
@@ -87,11 +87,9 @@
 #endif
 #define VEC(i)                 zmm##i
 #define _dl_runtime_resolve    _dl_runtime_resolve_avx512
-#define _dl_runtime_resolve_opt        _dl_runtime_resolve_avx512_opt
 #define _dl_runtime_profile    _dl_runtime_profile_avx512
 #include "dl-trampoline.h"
 #undef _dl_runtime_resolve
-#undef _dl_runtime_resolve_opt
 #undef _dl_runtime_profile
 #undef VEC
 #undef VMOV
@@ -145,4 +143,5 @@
 # define VMOV                  vmovdqu
 #endif
 #define _dl_runtime_resolve    _dl_runtime_resolve_sse_vex
+#define _dl_runtime_resolve_opt        _dl_runtime_resolve_avx512_opt
 #include "dl-trampoline.h"

diff --git a/sysdeps/x86_64/dl-trampoline.h b/sysdeps/x86_64/dl-trampoline.h
index b27fa0697469869a2275e5c3d09e5db64622db90..8db24c16aca2cfc3893ef6f62e1bf39bee205593 100644 (file)
--- a/sysdeps/x86_64/dl-trampoline.h
+++ b/sysdeps/x86_64/dl-trampoline.h
@@ -129,19 +129,20 @@ _dl_runtime_resolve_opt:
        # YMM state isn't in use.
        PRESERVE_BND_REGS_PREFIX
        jz _dl_runtime_resolve_sse_vex
-# elif VEC_SIZE == 64
+# elif VEC_SIZE == 16
        # For ZMM registers, check if YMM state and ZMM state are in
        # use.
        andl $(bit_YMM_state | bit_ZMM0_15_state), %r11d
        cmpl $bit_YMM_state, %r11d
-       # Preserve %xmm0 - %xmm7 registers with the zero upper 384 bits if
-       # neither YMM state nor ZMM state are in use.
+       # Preserve %zmm0 - %zmm7 registers if ZMM state is in use.
        PRESERVE_BND_REGS_PREFIX
-       jl _dl_runtime_resolve_sse_vex
+       jg _dl_runtime_resolve_avx512
        # Preserve %ymm0 - %ymm7 registers with the zero upper 256 bits if
        # ZMM state isn't in use.
        PRESERVE_BND_REGS_PREFIX
        je _dl_runtime_resolve_avx
+       # Preserve %xmm0 - %xmm7 registers with the zero upper 384 bits if
+       # neither YMM state nor ZMM state are in use.
 # else
 #  error Unsupported VEC_SIZE!
 # endif