@@ -4620,6 +4620,33 @@ optimize_encoding (void)
i.op[1].regs = i.op[0].regs;
}
}
+ else if (optimize_for_space
+ && i.tm.base_opcode == 0x59
+ && i.tm.opcode_space == SPACE_0F38
+ && i.operands == i.reg_operands
+ && i.tm.opcode_modifier.vex
+ && !(i.op[0].regs->reg_flags & RegRex)
+ && i.op[0].regs->reg_type.bitfield.xmmword
+ && i.vec_encoding != vex_encoding_vex3)
+ {
+ /* Optimize: -Os:
+ vpbroadcastq %xmmN, %xmmM -> vpunpcklqdq %xmmN, %xmmN, %xmmM (N < 8)
+ */
+ i.tm.opcode_space = SPACE_0F;
+ i.tm.base_opcode = 0x6c;
+ i.tm.opcode_modifier.vexvvvv = 1;
+
+ ++i.operands;
+ ++i.reg_operands;
+ ++i.tm.operands;
+
+ i.op[2].regs = i.op[0].regs;
+ i.types[2] = i.types[0];
+ i.flags[2] = i.flags[0];
+ i.tm.operand_types[2] = i.tm.operand_types[0];
+
+ swap_2_operands (1, 2);
+ }
}
/* Return non-zero for load instruction. */
@@ -164,4 +164,5 @@ Disassembly of section .text:
+[a-f0-9]+: 66 .* pcmpeqd %xmm2,%xmm2
+[a-f0-9]+: c5 .* vpcmpeqd %xmm2,%xmm2,%xmm0
+[a-f0-9]+: c5 .* vpcmpeqd %ymm2,%ymm2,%ymm0
+ +[a-f0-9]+: c5 .* vpunpcklqdq %xmm2,%xmm2,%xmm0
#pass
@@ -184,3 +184,5 @@ _start:
pcmpeqq %xmm2, %xmm2
vpcmpeqq %xmm2, %xmm2, %xmm0
vpcmpeqq %ymm2, %ymm2, %ymm0
+
+ vpbroadcastq %xmm2, %xmm0
@@ -165,4 +165,5 @@ Disassembly of section .text:
+[a-f0-9]+: 66 .* pcmpeqq %xmm2,%xmm2
+[a-f0-9]+: c4 .* vpcmpeqq %xmm2,%xmm2,%xmm0
+[a-f0-9]+: c4 .* vpcmpeqq %ymm2,%ymm2,%ymm0
+ +[a-f0-9]+: c4 .* vpbroadcastq %xmm2,%xmm0
#pass
@@ -205,4 +205,6 @@ Disassembly of section .text:
+[a-f0-9]+: 66 .* pcmpeqd %xmm12,%xmm12
+[a-f0-9]+: c4 .* vpcmpeqq %xmm12,%xmm12,%xmm0
+[a-f0-9]+: c4 .* vpcmpeqq %ymm12,%ymm12,%ymm0
+ +[a-f0-9]+: c5 .* vpunpcklqdq %xmm2,%xmm2,%xmm0
+ +[a-f0-9]+: c4 .* vpbroadcastq %xmm12,%xmm0
#pass
@@ -229,3 +229,6 @@ _start:
pcmpeqq %xmm12, %xmm12
vpcmpeqq %xmm12, %xmm12, %xmm0
vpcmpeqq %ymm12, %ymm12, %ymm0
+
+ vpbroadcastq %xmm2, %xmm0
+ vpbroadcastq %xmm12, %xmm0
@@ -206,4 +206,6 @@ Disassembly of section .text:
+[a-f0-9]+: 66 .* pcmpeqq %xmm12,%xmm12
+[a-f0-9]+: c4 .* vpcmpeqq %xmm12,%xmm12,%xmm0
+[a-f0-9]+: c4 .* vpcmpeqq %ymm12,%ymm12,%ymm0
+ +[a-f0-9]+: c4 .* vpbroadcastq %xmm2,%xmm0
+ +[a-f0-9]+: c4 .* vpbroadcastq %xmm12,%xmm0
#pass
@@ -1734,7 +1734,7 @@ vbroadcastsd, 0x6619, AVX2, Modrm|Vex=2|
vbroadcastss, 0x6618, AVX2, Modrm|Vex|Space0F38|VexW=1|NoSuf, { RegXMM, RegXMM|RegYMM }
vpblendd, 0x6602, AVX2, Modrm|Vex|Space0F3A|VexVVVV|VexW0|CheckOperandSize|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegXMM|RegYMM, RegXMM|RegYMM, RegXMM|RegYMM }
vpbroadcast<bw>, 0x6678 | <bw:opc>, AVX2, Modrm|Vex|Space0F38|VexW0|NoSuf, { <bw:elem>|Unspecified|BaseIndex|RegXMM, RegXMM|RegYMM }
-vpbroadcast<dq>, 0x6658 | <dq:opc>, AVX2, Modrm|Vex|Space0F38|VexW0|NoSuf, { <dq:elem>|Unspecified|BaseIndex|RegXMM, RegXMM|RegYMM }
+vpbroadcast<dq>, 0x6658 | <dq:opc>, AVX2, Modrm|Vex|Space0F38|VexW0|NoSuf|Optimize, { <dq:elem>|Unspecified|BaseIndex|RegXMM, RegXMM|RegYMM }
vperm2i128, 0x6646, AVX2, Modrm|Vex=2|Space0F3A|VexVVVV|VexW0|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
vpermd, 0x6636, AVX2, Modrm|Vex256|Space0F38|VexVVVV|VexW0|NoSuf, { Unspecified|BaseIndex|RegYMM, RegYMM, RegYMM }
vpermpd, 0x6601, AVX2, Modrm|Vex=2|Space0F3A|VexW1|NoSuf, { Imm8|Imm8S, Unspecified|BaseIndex|RegYMM, RegYMM }