x86: Encode AVX256/AVX512 vpsub[bwdq] with VEX128/EVEX128

When 2 source registers are identical, AVX256 and AVX512 vpsub[bwdq]
instructions can be encoded with VEX128 or EVEX128 encodings.

gas/

	* config/tc-i386.c (optimize_encoding): Optimize AVX256 and
	AVX512 vpsub[bwdq] instructions.
	* testsuite/gas/i386/optimize-1.s: Add tests for AVX256 and
	AVX512 vpsub[bwdq] instructions.
	* testsuite/gas/i386/x86-64-optimize-2.s: Likewise.
	* testsuite/gas/i386/optimize-1.d: Updated.
	* testsuite/gas/i386/x86-64-optimize-2.d: Likewise.

opcodes/

	* * i386-opc.tbl: Add "Optimize" to AVX256 and AVX512
	vpsub[bwdq] instructions.
	* i386-tbl.h: Regenerated.

6 files changed, 121 insertions, 2 deletions

diff --git a/gas/ChangeLog b/gas/ChangeLog
index 913d9bc..da34e3b 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,3 +1,13 @@
+2018-03-01  H.J. Lu  <hongjiu.lu@intel.com>
+
+	* config/tc-i386.c (optimize_encoding): Optimize AVX256 and
+	AVX512 vpsub[bwdq] instructions.
+	* testsuite/gas/i386/optimize-1.s: Add tests for AVX256 and
+	AVX512 vpsub[bwdq] instructions.
+	* testsuite/gas/i386/x86-64-optimize-2.s: Likewise.
+	* testsuite/gas/i386/optimize-1.d: Updated.
+	* testsuite/gas/i386/x86-64-optimize-2.d: Likewise.
+
 2018-03-01  Alan Modra  <amodra@gmail.com>
 
 	* configure.ac (ALL_LINGUAS): Add uk.  Sort.
diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c
index f9dccdb..4174d19 100644
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -3856,11 +3856,16 @@ optimize_encoding (void)
 		|| i.tm.base_opcode == 0x66df
 		|| i.tm.base_opcode == 0x57
 		|| i.tm.base_opcode == 0x6657
-		|| i.tm.base_opcode == 0x66ef)
+		|| i.tm.base_opcode == 0x66ef
+		|| i.tm.base_opcode == 0x66f8
+		|| i.tm.base_opcode == 0x66f9
+		|| i.tm.base_opcode == 0x66fa
+		|| i.tm.base_opcode == 0x66fb)
 	       && i.tm.extension_opcode == None))
     {
       /* Optimize: -O2:
-	   VOP, one of vandnps, vandnpd, vxorps and vxorpd:
+	   VOP, one of vandnps, vandnpd, vxorps, vxorpd, vpsubb, vpsubd,
+	   vpsubq and vpsubw:
 	     EVEX VOP %zmmM, %zmmM, %zmmN
 	       -> VEX VOP %xmmM, %xmmM, %xmmN (M and N < 16)
 	       -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16)
diff --git a/gas/testsuite/gas/i386/optimize-1.d b/gas/testsuite/gas/i386/optimize-1.d
index 80b1e83..3ea6e75 100644
--- a/gas/testsuite/gas/i386/optimize-1.d
+++ b/gas/testsuite/gas/i386/optimize-1.d
@@ -42,4 +42,20 @@ Disassembly of section .text:
  +[a-f0-9]+:	62 f1 f5 af ef e9    	vpxorq %ymm1,%ymm1,%ymm5\{%k7\}\{z\}
  +[a-f0-9]+:	c5 f1 ef e9          	vpxor  %xmm1,%xmm1,%xmm5
  +[a-f0-9]+:	c5 f1 ef e9          	vpxor  %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	62 f1 75 4f f8 e9    	vpsubb %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+:	62 f1 75 af f8 e9    	vpsubb %ymm1,%ymm1,%ymm5\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 f1 f8 e9          	vpsubb %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	c5 f1 f8 e9          	vpsubb %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	62 f1 75 4f f9 e9    	vpsubw %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+:	62 f1 75 af f9 e9    	vpsubw %ymm1,%ymm1,%ymm5\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 f1 f9 e9          	vpsubw %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	c5 f1 f9 e9          	vpsubw %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	62 f1 75 4f fa e9    	vpsubd %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+:	62 f1 75 af fa e9    	vpsubd %ymm1,%ymm1,%ymm5\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 f1 fa e9          	vpsubd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	c5 f1 fa e9          	vpsubd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	62 f1 f5 4f fb e9    	vpsubq %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+:	62 f1 f5 af fb e9    	vpsubq %ymm1,%ymm1,%ymm5\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 f1 fb e9          	vpsubq %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+:	c5 f1 fb e9          	vpsubq %xmm1,%xmm1,%xmm5
 #pass
diff --git a/gas/testsuite/gas/i386/optimize-1.s b/gas/testsuite/gas/i386/optimize-1.s
index 042a004..f875f92 100644
--- a/gas/testsuite/gas/i386/optimize-1.s
+++ b/gas/testsuite/gas/i386/optimize-1.s
@@ -46,3 +46,23 @@ _start:
 	vpxorq %ymm1, %ymm1, %ymm5{z}{%k7}
 	vpxorq %zmm1, %zmm1, %zmm5
 	vpxorq %ymm1, %ymm1, %ymm5
+
+	vpsubb %zmm1, %zmm1, %zmm5{%k7}
+	vpsubb %ymm1, %ymm1, %ymm5{z}{%k7}
+	vpsubb %zmm1, %zmm1, %zmm5
+	vpsubb %ymm1, %ymm1, %ymm5
+
+	vpsubw %zmm1, %zmm1, %zmm5{%k7}
+	vpsubw %ymm1, %ymm1, %ymm5{z}{%k7}
+	vpsubw %zmm1, %zmm1, %zmm5
+	vpsubw %ymm1, %ymm1, %ymm5
+
+	vpsubd %zmm1, %zmm1, %zmm5{%k7}
+	vpsubd %ymm1, %ymm1, %ymm5{z}{%k7}
+	vpsubd %zmm1, %zmm1, %zmm5
+	vpsubd %ymm1, %ymm1, %ymm5
+
+	vpsubq %zmm1, %zmm1, %zmm5{%k7}
+	vpsubq %ymm1, %ymm1, %ymm5{z}{%k7}
+	vpsubq %zmm1, %zmm1, %zmm5
+	vpsubq %ymm1, %ymm1, %ymm5
diff --git a/gas/testsuite/gas/i386/x86-64-optimize-2.d b/gas/testsuite/gas/i386/x86-64-optimize-2.d
index f982f52..f59e9b6 100644
--- a/gas/testsuite/gas/i386/x86-64-optimize-2.d
+++ b/gas/testsuite/gas/i386/x86-64-optimize-2.d
@@ -74,4 +74,36 @@ Disassembly of section .text:
  +[a-f0-9]+:	62 e1 f5 08 ef c1    	vpxorq %xmm1,%xmm1,%xmm16
  +[a-f0-9]+:	62 b1 f5 00 ef c9    	vpxorq %xmm17,%xmm17,%xmm1
  +[a-f0-9]+:	62 b1 f5 00 ef c9    	vpxorq %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 71 75 4f f8 f9    	vpsubb %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+:	62 71 75 af f8 f9    	vpsubb %ymm1,%ymm1,%ymm15\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 71 f8 f9          	vpsubb %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	c5 71 f8 f9          	vpsubb %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	62 e1 75 08 f8 c1    	vpsubb %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 e1 75 08 f8 c1    	vpsubb %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 b1 75 00 f8 c9    	vpsubb %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 b1 75 00 f8 c9    	vpsubb %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 71 75 4f f9 f9    	vpsubw %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+:	62 71 75 af f9 f9    	vpsubw %ymm1,%ymm1,%ymm15\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 71 f9 f9          	vpsubw %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	c5 71 f9 f9          	vpsubw %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	62 e1 75 08 f9 c1    	vpsubw %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 e1 75 08 f9 c1    	vpsubw %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 b1 75 00 f9 c9    	vpsubw %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 b1 75 00 f9 c9    	vpsubw %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 71 75 4f fa f9    	vpsubd %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+:	62 71 75 af fa f9    	vpsubd %ymm1,%ymm1,%ymm15\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 71 fa f9          	vpsubd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	c5 71 fa f9          	vpsubd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	62 e1 75 08 fa c1    	vpsubd %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 e1 75 08 fa c1    	vpsubd %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 b1 75 00 fa c9    	vpsubd %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 b1 75 00 fa c9    	vpsubd %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 71 f5 4f fb f9    	vpsubq %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+:	62 71 f5 af fb f9    	vpsubq %ymm1,%ymm1,%ymm15\{%k7\}\{z\}
+ +[a-f0-9]+:	c5 71 fb f9          	vpsubq %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	c5 71 fb f9          	vpsubq %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+:	62 e1 f5 08 fb c1    	vpsubq %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 e1 f5 08 fb c1    	vpsubq %xmm1,%xmm1,%xmm16
+ +[a-f0-9]+:	62 b1 f5 00 fb c9    	vpsubq %xmm17,%xmm17,%xmm1
+ +[a-f0-9]+:	62 b1 f5 00 fb c9    	vpsubq %xmm17,%xmm17,%xmm1
 #pass
diff --git a/gas/testsuite/gas/i386/x86-64-optimize-2.s b/gas/testsuite/gas/i386/x86-64-optimize-2.s
index 6aa968b..4461c09 100644
--- a/gas/testsuite/gas/i386/x86-64-optimize-2.s
+++ b/gas/testsuite/gas/i386/x86-64-optimize-2.s
@@ -78,3 +78,39 @@ _start:
 	vpxorq %ymm1, %ymm1, %ymm16
 	vpxorq %zmm17, %zmm17, %zmm1
 	vpxorq %ymm17, %ymm17, %ymm1
+
+	vpsubb %zmm1, %zmm1, %zmm15{%k7}
+	vpsubb %ymm1, %ymm1, %ymm15{z}{%k7}
+	vpsubb %zmm1, %zmm1, %zmm15
+	vpsubb %ymm1, %ymm1, %ymm15
+	vpsubb %zmm1, %zmm1, %zmm16
+	vpsubb %ymm1, %ymm1, %ymm16
+	vpsubb %zmm17, %zmm17, %zmm1
+	vpsubb %ymm17, %ymm17, %ymm1
+
+	vpsubw %zmm1, %zmm1, %zmm15{%k7}
+	vpsubw %ymm1, %ymm1, %ymm15{z}{%k7}
+	vpsubw %zmm1, %zmm1, %zmm15
+	vpsubw %ymm1, %ymm1, %ymm15
+	vpsubw %zmm1, %zmm1, %zmm16
+	vpsubw %ymm1, %ymm1, %ymm16
+	vpsubw %zmm17, %zmm17, %zmm1
+	vpsubw %ymm17, %ymm17, %ymm1
+
+	vpsubd %zmm1, %zmm1, %zmm15{%k7}
+	vpsubd %ymm1, %ymm1, %ymm15{z}{%k7}
+	vpsubd %zmm1, %zmm1, %zmm15
+	vpsubd %ymm1, %ymm1, %ymm15
+	vpsubd %zmm1, %zmm1, %zmm16
+	vpsubd %ymm1, %ymm1, %ymm16
+	vpsubd %zmm17, %zmm17, %zmm1
+	vpsubd %ymm17, %ymm17, %ymm1
+
+	vpsubq %zmm1, %zmm1, %zmm15{%k7}
+	vpsubq %ymm1, %ymm1, %ymm15{z}{%k7}
+	vpsubq %zmm1, %zmm1, %zmm15
+	vpsubq %ymm1, %ymm1, %ymm15
+	vpsubq %zmm1, %zmm1, %zmm16
+	vpsubq %ymm1, %ymm1, %ymm16
+	vpsubq %zmm17, %zmm17, %zmm1
+	vpsubq %ymm17, %ymm17, %ymm1