[PATCH v1 2/3] x86: Remove memcmp-sse4.S

[Noah Goldstein <goldstein.w.n@gmail.com>]

Code didn't actually use any sse4 instructions. The new memcmp-sse2
implementation is also faster.

geometric_mean(N=20) of page cross cases SSE2 / SSE4: 0.905

Note there are two regressions prefering SSE2 for Size = 1 and Size =
65.

Size = 1:
size, align0, align1, ret, New Time/Old Time
   1,      1,      1,   0,               1.2
   1,      1,      1,   1,             1.197
   1,      1,      1,  -1,               1.2

This is intentional. Size == 1 is significantly less hot based on
profiles of GCC11 and Python3 than sizes [4, 8] (which is made
hotter).

Python3 Size = 1        -> 13.64%
Python3 Size = [4, 8]   -> 60.92%

GCC11   Size = 1        ->  1.29%
GCC11   Size = [4, 8]   -> 33.86%

size, align0, align1, ret, New Time/Old Time
   4,      4,      4,   0,             0.622
   4,      4,      4,   1,             0.797
   4,      4,      4,  -1,             0.805
   5,      5,      5,   0,             0.623
   5,      5,      5,   1,             0.777
   5,      5,      5,  -1,             0.802
   6,      6,      6,   0,             0.625
   6,      6,      6,   1,             0.813
   6,      6,      6,  -1,             0.788
   7,      7,      7,   0,             0.625
   7,      7,      7,   1,             0.799
   7,      7,      7,  -1,             0.795
   8,      8,      8,   0,             0.625
   8,      8,      8,   1,             0.848
   8,      8,      8,  -1,             0.914
   9,      9,      9,   0,             0.625

Size = 65:
size, align0, align1, ret, New Time/Old Time
  65,      0,      0,   0,             1.103
  65,      0,      0,   1,             1.216
  65,      0,      0,  -1,             1.227
  65,     65,      0,   0,             1.091
  65,      0,     65,   1,              1.19
  65,     65,     65,  -1,             1.215

This is because A) the checks in range [65, 96] are now unrolled 2x
and B) because smaller values <= 16 are now given a hotter path. By
contrast the SSE4 version has a branch for Size = 80. The unrolled
version has get better performance for returns which need both
comparisons.

size, align0, align1, ret, New Time/Old Time
 128,      4,      8,   0,             0.858
 128,      4,      8,   1,             0.879
 128,      4,      8,  -1,             0.888

As well, out of microbenchmark environments that are not full
predictable the branch will have a real-cost.
---
 sysdeps/x86_64/multiarch/Makefile          | 2 --
 sysdeps/x86_64/multiarch/ifunc-impl-list.c | 4 ----
 sysdeps/x86_64/multiarch/ifunc-memcmp.h    | 4 ----
 3 files changed, 10 deletions(-)

diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index b573966966..0400ea332b 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -11,7 +11,6 @@ sysdep_routines += \
   memcmp-avx2-movbe-rtm \
   memcmp-evex-movbe \
   memcmp-sse2 \
-  memcmp-sse4 \
   memcmpeq-avx2 \
   memcmpeq-avx2-rtm \
   memcmpeq-evex \
@@ -164,7 +163,6 @@ sysdep_routines += \
   wmemcmp-avx2-movbe-rtm \
   wmemcmp-evex-movbe \
   wmemcmp-sse2 \
-  wmemcmp-sse4 \
 # sysdep_routines
 endif
 
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index c6008a73ed..a8afcf81bb 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -96,8 +96,6 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			       && CPU_FEATURE_USABLE (BMI2)
 			       && CPU_FEATURE_USABLE (MOVBE)),
 			      __memcmp_evex_movbe)
-	      IFUNC_IMPL_ADD (array, i, memcmp, CPU_FEATURE_USABLE (SSE4_1),
-			      __memcmp_sse4_1)
 	      IFUNC_IMPL_ADD (array, i, memcmp, 1, __memcmp_sse2))
 
 #ifdef SHARED
@@ -809,8 +807,6 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			       && CPU_FEATURE_USABLE (BMI2)
 			       && CPU_FEATURE_USABLE (MOVBE)),
 			      __wmemcmp_evex_movbe)
-	      IFUNC_IMPL_ADD (array, i, wmemcmp, CPU_FEATURE_USABLE (SSE4_1),
-			      __wmemcmp_sse4_1)
 	      IFUNC_IMPL_ADD (array, i, wmemcmp, 1, __wmemcmp_sse2))
 
   /* Support sysdeps/x86_64/multiarch/wmemset.c.  */
diff --git a/sysdeps/x86_64/multiarch/ifunc-memcmp.h b/sysdeps/x86_64/multiarch/ifunc-memcmp.h
index 44759a3ad5..c743970fe3 100644
--- a/sysdeps/x86_64/multiarch/ifunc-memcmp.h
+++ b/sysdeps/x86_64/multiarch/ifunc-memcmp.h
@@ -20,7 +20,6 @@
 # include <init-arch.h>
 
 extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden;
-extern __typeof (REDIRECT_NAME) OPTIMIZE (sse4_1) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_movbe) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_movbe_rtm) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (evex_movbe) attribute_hidden;
@@ -46,8 +45,5 @@ IFUNC_SELECTOR (void)
 	return OPTIMIZE (avx2_movbe);
     }
 
-  if (CPU_FEATURE_USABLE_P (cpu_features, SSE4_1))
-    return OPTIMIZE (sse4_1);
-
   return OPTIMIZE (sse2);
 }
-- 
2.25.1