diff options
| author | H.J. Lu <hjl.tools@gmail.com> | 2017-03-21 10:59:31 -0700 |
|---|---|---|
| committer | H.J. Lu <hjl.tools@gmail.com> | 2017-04-20 07:55:44 -0700 |
| commit | 883cadc5543ffd3a4537498b44c782ded8a4a4e8 (patch) | |
| tree | 7f8420bd13c9e7660a4e097c9f62b01a2695a2d2 | |
| parent | 83037ea1d9e84b1b44ed307f01cbb5eeac24e22d (diff) | |
| download | glibc-hjl/pr21258/2.23.tar.gz | |
x86-64: Improve branch predication in _dl_runtime_resolve_avx512_opt [BZ #21258]hjl/pr21258/2.23
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.
(cherry picked from commit c15f8eb50cea7ad1a4ccece6e0982bf426d52c00)
| -rw-r--r-- | sysdeps/x86_64/dl-trampoline.S | 5 | ||||
| -rw-r--r-- | sysdeps/x86_64/dl-trampoline.h | 9 |
2 files changed, 6 insertions, 8 deletions
diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S index 3f812b89c0..177f666164 100644 --- a/sysdeps/x86_64/dl-trampoline.S +++ b/sysdeps/x86_64/dl-trampoline.S @@ -88,11 +88,9 @@ # 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 @@ -101,8 +99,6 @@ #else strong_alias (_dl_runtime_resolve_avx, _dl_runtime_resolve_avx512) .hidden _dl_runtime_resolve_avx512 -strong_alias (_dl_runtime_resolve_avx_opt, _dl_runtime_resolve_avx512_opt) - .hidden _dl_runtime_resolve_avx512_opt strong_alias (_dl_runtime_profile_avx, _dl_runtime_profile_avx512) .hidden _dl_runtime_profile_avx512 #endif @@ -154,4 +150,5 @@ strong_alias (_dl_runtime_profile_avx, _dl_runtime_profile_avx512) # 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 abe4471c1d..32ad3af202 100644 --- 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 |