[PATCH 3/8] perf bench: add memset_movnti()

[Ankur Arora]

Clone memset_movnti() from arch/x86/lib/memset_64.S.

perf bench mem memset on -f x86-64-movnt on Intel Broadwellx, Skylakex
and AMD Rome:

Intel Broadwellx:
$ for i in 2 8 32 128 512; do
	perf bench mem memset -f x86-64-movnt -s ${i}MB
  done

  # Output pruned.
  # Running 'mem/memset' benchmark:
  # function 'x86-64-movnt' (movnt-based memset() in arch/x86/lib/memset_64.S)
  # Copying 2MB bytes ...
        11.837121 GB/sec
  # Copying 8MB bytes ...
        11.783560 GB/sec
  # Copying 32MB bytes ...
        11.868591 GB/sec
  # Copying 128MB bytes ...
        11.865211 GB/sec
  # Copying 512MB bytes ...
        11.864085 GB/sec

Intel Skylakex:
$ for i in 2 8 32 128 512; do
	perf bench mem memset -f x86-64-movnt -s ${i}MB
  done
  # Running 'mem/memset' benchmark:
  # function 'x86-64-movnt' (movnt-based memset() in arch/x86/lib/memset_64.S)
  # Copying 2MB bytes ...
         6.361971 GB/sec
  # Copying 8MB bytes ...
         6.300403 GB/sec
  # Copying 32MB bytes ...
         6.288992 GB/sec
  # Copying 128MB bytes ...
         6.328793 GB/sec
  # Copying 512MB bytes ...
         6.324471 GB/sec

AMD Rome:
$ for i in 2 8 32 128 512; do
	perf bench mem memset -f x86-64-movnt -s ${i}MB
  done
  # Running 'mem/memset' benchmark:
  # function 'x86-64-movnt' (movnt-based memset() in arch/x86/lib/memset_64.S)
  # Copying 2MB bytes ...
        10.993199 GB/sec
  # Copying 8MB bytes ...
        14.221784 GB/sec
  # Copying 32MB bytes ...
        14.293337 GB/sec
  # Copying 128MB bytes ...
        15.238947 GB/sec
  # Copying 512MB bytes ...
        16.476093 GB/sec

Signed-off-by: Ankur Arora <ankur.a.arora@xxxxxxxxxx>
---
 tools/arch/x86/lib/memset_64.S               | 68 ++++++++++++++++------------
 tools/perf/bench/mem-memset-x86-64-asm-def.h |  6 ++-
 2 files changed, 43 insertions(+), 31 deletions(-)

diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index fd5d25a474b7..bfbf6d06f81e 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -26,7 +26,7 @@ SYM_FUNC_START(__memset)
 	 *
 	 * Otherwise, use original memset function.
 	 */
-	ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
+	ALTERNATIVE_2 "jmp memset_movq", "", X86_FEATURE_REP_GOOD, \
 		      "jmp memset_erms", X86_FEATURE_ERMS
 
 	movq %rdi,%r9
@@ -65,7 +65,8 @@ SYM_FUNC_START(memset_erms)
 	ret
 SYM_FUNC_END(memset_erms)
 
-SYM_FUNC_START(memset_orig)
+.macro MEMSET_MOV OP fence
+SYM_FUNC_START(memset_\OP)
 	movq %rdi,%r10
 
 	/* expand byte value  */
@@ -76,64 +77,71 @@ SYM_FUNC_START(memset_orig)
 	/* align dst */
 	movl  %edi,%r9d
 	andl  $7,%r9d
-	jnz  .Lbad_alignment
-.Lafter_bad_alignment:
+	jnz  .Lbad_alignment_\@
+.Lafter_bad_alignment_\@:
 
 	movq  %rdx,%rcx
 	shrq  $6,%rcx
-	jz	 .Lhandle_tail
+	jz	 .Lhandle_tail_\@
 
 	.p2align 4
-.Lloop_64:
+.Lloop_64_\@:
 	decq  %rcx
-	movq  %rax,(%rdi)
-	movq  %rax,8(%rdi)
-	movq  %rax,16(%rdi)
-	movq  %rax,24(%rdi)
-	movq  %rax,32(%rdi)
-	movq  %rax,40(%rdi)
-	movq  %rax,48(%rdi)
-	movq  %rax,56(%rdi)
+	\OP  %rax,(%rdi)
+	\OP  %rax,8(%rdi)
+	\OP  %rax,16(%rdi)
+	\OP  %rax,24(%rdi)
+	\OP  %rax,32(%rdi)
+	\OP  %rax,40(%rdi)
+	\OP  %rax,48(%rdi)
+	\OP  %rax,56(%rdi)
 	leaq  64(%rdi),%rdi
-	jnz    .Lloop_64
+	jnz    .Lloop_64_\@
 
 	/* Handle tail in loops. The loops should be faster than hard
 	   to predict jump tables. */
 	.p2align 4
-.Lhandle_tail:
+.Lhandle_tail_\@:
 	movl	%edx,%ecx
 	andl    $63&(~7),%ecx
-	jz 		.Lhandle_7
+	jz 		.Lhandle_7_\@
 	shrl	$3,%ecx
 	.p2align 4
-.Lloop_8:
+.Lloop_8_\@:
 	decl   %ecx
-	movq  %rax,(%rdi)
+	\OP  %rax,(%rdi)
 	leaq  8(%rdi),%rdi
-	jnz    .Lloop_8
+	jnz    .Lloop_8_\@
 
-.Lhandle_7:
+.Lhandle_7_\@:
 	andl	$7,%edx
-	jz      .Lende
+	jz      .Lende_\@
 	.p2align 4
-.Lloop_1:
+.Lloop_1_\@:
 	decl    %edx
 	movb 	%al,(%rdi)
 	leaq	1(%rdi),%rdi
-	jnz     .Lloop_1
+	jnz     .Lloop_1_\@
 
-.Lende:
+.Lende_\@:
+	.if \fence
+	sfence
+	.endif
 	movq	%r10,%rax
 	ret
 
-.Lbad_alignment:
+.Lbad_alignment_\@:
 	cmpq $7,%rdx
-	jbe	.Lhandle_7
+	jbe	.Lhandle_7_\@
 	movq %rax,(%rdi)	/* unaligned store */
 	movq $8,%r8
 	subq %r9,%r8
 	addq %r8,%rdi
 	subq %r8,%rdx
-	jmp .Lafter_bad_alignment
-.Lfinal:
-SYM_FUNC_END(memset_orig)
+	jmp .Lafter_bad_alignment_\@
+.Lfinal_\@:
+SYM_FUNC_END(memset_\OP)
+.endm
+
+MEMSET_MOV OP=movq fence=0
+MEMSET_MOV OP=movnti fence=1
diff --git a/tools/perf/bench/mem-memset-x86-64-asm-def.h b/tools/perf/bench/mem-memset-x86-64-asm-def.h
index dac6d2b7c39b..53ead7f91313 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm-def.h
+++ b/tools/perf/bench/mem-memset-x86-64-asm-def.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
-MEMSET_FN(memset_orig,
+MEMSET_FN(memset_movq,
 	"x86-64-unrolled",
 	"unrolled memset() in arch/x86/lib/memset_64.S")
 
@@ -11,3 +11,7 @@ MEMSET_FN(__memset,
 MEMSET_FN(memset_erms,
 	"x86-64-stosb",
 	"movsb-based memset() in arch/x86/lib/memset_64.S")
+
+MEMSET_FN(memset_movnti,
+	"x86-64-movnt",
+	"movnt-based memset() in arch/x86/lib/memset_64.S")
-- 
2.9.3