x86: optimize {,V}PEXTR{D,Q} with immediate of 0

Such are equivalent to simple moves, which are up to 3 bytes shorter to
encode (and perhaps also cheaper to execute).

9 files changed, 120 insertions, 0 deletions

diff --git a/gas/testsuite/gas/i386/optimize-1.d b/gas/testsuite/gas/i386/optimize-1.d
index 23d715c..f496846 100644
--- a/gas/testsuite/gas/i386/optimize-1.d
+++ b/gas/testsuite/gas/i386/optimize-1.d
@@ -162,6 +162,10 @@ Disassembly of section .text:
  +[a-f0-9]+:	66 .*	pxor   %xmm2,%xmm2
  +[a-f0-9]+:	c5 .*	vpxor  %xmm2,%xmm2,%xmm0
  +[a-f0-9]+:	c5 .*	vpxor  %ymm2,%ymm2,%ymm0
+ +[a-f0-9]+:	66 .*	movd   %xmm1,%edx
+ +[a-f0-9]+:	66 .*	movd   %xmm1,\(%edx\)
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,%edx
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,\(%edx\)
  +[a-f0-9]+:	0f ba e0 0f          	bt     \$0xf,%eax
  +[a-f0-9]+:	66 0f ba e0 10       	bt     \$0x10,%ax
  +[a-f0-9]+:	0f ba f8 0f          	btc    \$0xf,%eax
diff --git a/gas/testsuite/gas/i386/optimize-1.s b/gas/testsuite/gas/i386/optimize-1.s
index f80301d..ce53758 100644
--- a/gas/testsuite/gas/i386/optimize-1.s
+++ b/gas/testsuite/gas/i386/optimize-1.s
@@ -189,6 +189,11 @@ _start:
 	vpcmpgtq	%xmm2, %xmm2, %xmm0
 	vpcmpgtq	%ymm2, %ymm2, %ymm0
 
+	pextrd		$0, %xmm1, %edx
+	pextrd		$0, %xmm1, (%edx)
+	vpextrd		$0, %xmm1, %edx
+	vpextrd		$0, %xmm1, (%edx)
+
 	bt	$15, %ax
 	bt	$16, %ax
 	btc	$15, %ax
diff --git a/gas/testsuite/gas/i386/optimize-1a.d b/gas/testsuite/gas/i386/optimize-1a.d
index 33c647b..b039a0d 100644
--- a/gas/testsuite/gas/i386/optimize-1a.d
+++ b/gas/testsuite/gas/i386/optimize-1a.d
@@ -163,6 +163,10 @@ Disassembly of section .text:
  +[a-f0-9]+:	66 .*	pxor   %xmm2,%xmm2
  +[a-f0-9]+:	c5 .*	vpxor  %xmm2,%xmm2,%xmm0
  +[a-f0-9]+:	c5 .*	vpxor  %ymm2,%ymm2,%ymm0
+ +[a-f0-9]+:	66 .*	movd   %xmm1,%edx
+ +[a-f0-9]+:	66 .*	movd   %xmm1,\(%edx\)
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,%edx
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,\(%edx\)
  +[a-f0-9]+:	0f ba e0 0f          	bt     \$0xf,%eax
  +[a-f0-9]+:	66 0f ba e0 10       	bt     \$0x10,%ax
  +[a-f0-9]+:	0f ba f8 0f          	btc    \$0xf,%eax
diff --git a/gas/testsuite/gas/i386/optimize-4.d b/gas/testsuite/gas/i386/optimize-4.d
index fa9b95f..ea2c761 100644
--- a/gas/testsuite/gas/i386/optimize-4.d
+++ b/gas/testsuite/gas/i386/optimize-4.d
@@ -162,6 +162,10 @@ Disassembly of section .text:
  +[a-f0-9]+:	66 .*	pxor   %xmm2,%xmm2
  +[a-f0-9]+:	c5 .*	vpxor  %xmm2,%xmm2,%xmm0
  +[a-f0-9]+:	c5 .*	vpxor  %ymm2,%ymm2,%ymm0
+ +[a-f0-9]+:	66 .*	movd   %xmm1,%edx
+ +[a-f0-9]+:	66 .*	movd   %xmm1,\(%edx\)
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,%edx
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,\(%edx\)
  +[a-f0-9]+:	0f ba e0 0f          	bt     \$0xf,%eax
  +[a-f0-9]+:	66 0f ba e0 10       	bt     \$0x10,%ax
  +[a-f0-9]+:	0f ba f8 0f          	btc    \$0xf,%eax
diff --git a/gas/testsuite/gas/i386/optimize-5.d b/gas/testsuite/gas/i386/optimize-5.d
index 36d0ba9..d53d2cc 100644
--- a/gas/testsuite/gas/i386/optimize-5.d
+++ b/gas/testsuite/gas/i386/optimize-5.d
@@ -162,6 +162,10 @@ Disassembly of section .text:
  +[a-f0-9]+:	66 .*	pxor   %xmm2,%xmm2
  +[a-f0-9]+:	c5 .*	vpxor  %xmm2,%xmm2,%xmm0
  +[a-f0-9]+:	c5 .*	vpxor  %ymm2,%ymm2,%ymm0
+ +[a-f0-9]+:	66 .*	movd   %xmm1,%edx
+ +[a-f0-9]+:	66 .*	movd   %xmm1,\(%edx\)
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,%edx
+ +[a-f0-9]+:	c5 .*	vmovd  %xmm1,\(%edx\)
  +[a-f0-9]+:	0f ba e0 0f          	bt     \$0xf,%eax
  +[a-f0-9]+:	66 0f ba e0 10       	bt     \$0x10,%ax
  +[a-f0-9]+:	0f ba f8 0f          	btc    \$0xf,%eax
diff --git a/gas/testsuite/gas/i386/x86-64-optimize-pextr.d b/gas/testsuite/gas/i386/x86-64-optimize-pextr.d
new file mode 100644
index 0000000..2b10b8a
--- /dev/null
+++ b/gas/testsuite/gas/i386/x86-64-optimize-pextr.d
@@ -0,0 +1,29 @@
+#as: -O -msse2avx
+#objdump: -drw
+#name: x86-64 PEXTR optimized encoding with -msse2avx
+
+.*: +file format .*
+
+
+Disassembly of section .text:
+
+0+ <pextr>:
+ +[a-f0-9]+:	c5 f9 7e ca          	vmovd  %xmm1,%edx
+ +[a-f0-9]+:	c5 f9 7e 0a          	vmovd  %xmm1,\(%rdx\)
+ +[a-f0-9]+:	62 f9 7d 08 7e ca    	vmovd  %xmm1,%r18d
+ +[a-f0-9]+:	62 f9 7d 08 7e 0a    	vmovd  %xmm1,\(%r18\)
+ +[a-f0-9]+:	c5 f9 7e ca          	vmovd  %xmm1,%edx
+ +[a-f0-9]+:	c5 f9 7e 0a          	vmovd  %xmm1,\(%rdx\)
+ +[a-f0-9]+:	62 e1 7d 08 7e ca    	vmovd  %xmm17,%edx
+ +[a-f0-9]+:	62 f9 7d 08 7e ca    	vmovd  %xmm1,%r18d
+ +[a-f0-9]+:	62 f9 7d 08 7e 0a    	vmovd  %xmm1,\(%r18\)
+ +[a-f0-9]+:	c4 e1 f9 7e ca       	vmovq  %xmm1,%rdx
+ +[a-f0-9]+:	c5 f9 d6 0a          	vmovq  %xmm1,\(%rdx\)
+ +[a-f0-9]+:	62 f9 fd 08 7e ca    	vmovq  %xmm1,%r18
+ +[a-f0-9]+:	62 f9 fd 08 7e 0a    	vmovq  %xmm1,\(%r18\)
+ +[a-f0-9]+:	c4 e1 f9 7e ca       	vmovq  %xmm1,%rdx
+ +[a-f0-9]+:	c5 f9 d6 0a          	vmovq  %xmm1,\(%rdx\)
+ +[a-f0-9]+:	62 e1 fd 08 7e ca    	vmovq  %xmm17,%rdx
+ +[a-f0-9]+:	62 f9 fd 08 7e ca    	vmovq  %xmm1,%r18
+ +[a-f0-9]+:	62 f9 fd 08 7e 0a    	vmovq  %xmm1,\(%r18\)
+#pass
diff --git a/gas/testsuite/gas/i386/x86-64-optimize-pextr.l b/gas/testsuite/gas/i386/x86-64-optimize-pextr.l
new file mode 100644
index 0000000..84e305a
--- /dev/null
+++ b/gas/testsuite/gas/i386/x86-64-optimize-pextr.l
@@ -0,0 +1,41 @@
+.*: Assembler messages:
+.*:6: Error: .*
+.*:7: Error: .*
+.*:19: Error: .*
+.*:20: Error: .*
+[ 	]*[0-9a-f]+[ 	]+\.text
+[ 	]*[0-9a-f]+[ 	]+pextr:
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 660F7ECA[ 	]+pextrd	\$0, %xmm1, %edx
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 660F7E0A[ 	]+pextrd	\$0, %xmm1, \(%rdx\)
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+pextrd	\$0, %xmm1, %r18d
+[ 	]*[0-9a-f]+[ 	]+pextrd	\$0, %xmm1, \(%r18\)
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? C5F97ECA[ 	]+vpextrd	\$0, %xmm1, %edx
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? C5F97E0A[ 	]+vpextrd	\$0, %xmm1, \(%rdx\)
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 62E17D08[ 	]+vpextrd	\$0, %xmm17, %edx
+[ 	]*[0-9a-f]+[ 	]+7ECA
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 62F97D08[ 	]+vpextrd	\$0, %xmm1, %r18d
+[ 	]*[0-9a-f]+[ 	]+7ECA
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 62F97D08[ 	]+vpextrd	\$0, %xmm1, \(%r18\)
+[ 	]*[0-9a-f]+[ 	]+7E0A
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 66480F7E[ 	]+pextrq	\$0, %xmm1, %rdx
+[ 	]*[0-9a-f]+[ 	]+CA
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 660FD60A[ 	]+pextrq	\$0, %xmm1, \(%rdx\)
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+pextrq	\$0, %xmm1, %r18
+[ 	]*[0-9a-f]+[ 	]+pextrq	\$0, %xmm1, \(%r18\)
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? C4E1F97E[ 	]+vpextrq	\$0, %xmm1, %rdx
+[ 	]*[0-9a-f]+[ 	]+CA
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? C5F9D60A[ 	]+vpextrq	\$0, %xmm1, \(%rdx\)
+[ 	]*[0-9a-f]+[ 	]+
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 62E1FD08[ 	]+vpextrq	\$0, %xmm17, %rdx
+[ 	]*[0-9a-f]+[ 	]+7ECA
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 62F9FD08[ 	]+vpextrq	\$0, %xmm1, %r18
+[ 	]*[0-9a-f]+[ 	]+7ECA
+[ 	]*[0-9a-f]+[ 	]+\?\?\?\? 62F9FD08[ 	]+vpextrq	\$0, %xmm1, \(%r18\)
+[ 	]*[0-9a-f]+[ 	]+7E0A
+#pass
diff --git a/gas/testsuite/gas/i386/x86-64-optimize-pextr.s b/gas/testsuite/gas/i386/x86-64-optimize-pextr.s
new file mode 100644
index 0000000..7ec1605
--- /dev/null
+++ b/gas/testsuite/gas/i386/x86-64-optimize-pextr.s
@@ -0,0 +1,27 @@
+	.text
+pextr:
+	pextrd	$0, %xmm1, %edx
+	pextrd	$0, %xmm1, (%rdx)
+
+	pextrd	$0, %xmm1, %r18d
+	pextrd	$0, %xmm1, (%r18)
+
+	vpextrd	$0, %xmm1, %edx
+	vpextrd	$0, %xmm1, (%rdx)
+
+	vpextrd	$0, %xmm17, %edx
+	vpextrd	$0, %xmm1, %r18d
+	vpextrd	$0, %xmm1, (%r18)
+
+	pextrq	$0, %xmm1, %rdx
+	pextrq	$0, %xmm1, (%rdx)
+
+	pextrq	$0, %xmm1, %r18
+	pextrq	$0, %xmm1, (%r18)
+
+	vpextrq	$0, %xmm1, %rdx
+	vpextrq	$0, %xmm1, (%rdx)
+
+	vpextrq	$0, %xmm17, %rdx
+	vpextrq	$0, %xmm1, %r18
+	vpextrq	$0, %xmm1, (%r18)
diff --git a/gas/testsuite/gas/i386/x86-64.exp b/gas/testsuite/gas/i386/x86-64.exp
index a8d49ce..b9eedbe 100644
--- a/gas/testsuite/gas/i386/x86-64.exp
+++ b/gas/testsuite/gas/i386/x86-64.exp
@@ -583,6 +583,8 @@ run_dump_test "x86-64-optimize-6"
 run_list_test "x86-64-optimize-7a" "-I${srcdir}/$subdir -march=+noavx -al"
 run_dump_test "x86-64-optimize-7b"
 run_list_test "x86-64-optimize-8" "-I${srcdir}/$subdir -march=+noavx2 -al"
+run_list_test "x86-64-optimize-pextr" "-O -aln"
+run_dump_test "x86-64-optimize-pextr"
 run_dump_test "x86-64-apx-ndd-optimize"
 run_dump_test "x86-64-align-branch-1a"
 run_dump_test "x86-64-align-branch-1b"