+2019-03-18 H.J. Lu <hongjiu.lu@intel.com>
+
+ * config/tc-i386.c (optimize_encoding): Encode 256-bit/512-bit
+ VEX/EVEX vector register clearing instructions with 128-bit VEX
+ vector register clearing instructions at -O1.
+ * doc/c-i386.texi: Update -O1 and -O2 documentation.
+ * testsuite/gas/i386/i386.exp: Run optimize-1a and
+ x86-64-optimize-2a.
+ * testsuite/gas/i386/optimize-1a.d: New file.
+ * testsuite/gas/i386/x86-64-optimize-2a.d: Likewise.
+
2019-03-17 H.J. Lu <hongjiu.lu@intel.com>
PR gas/24353
}
}
}
- else if (optimize > 1
- && i.reg_operands == 3
+ else if (i.reg_operands == 3
&& i.op[0].regs == i.op[1].regs
&& !i.types[2].bitfield.xmmword
&& (i.tm.opcode_modifier.vex
|| i.tm.base_opcode == 0x6647)
&& i.tm.extension_opcode == None))
{
- /* Optimize: -O2:
+ /* Optimize: -O1:
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)
+ -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2)
EVEX VOP %ymmM, %ymmM, %ymmN
-> VEX VOP %xmmM, %xmmM, %xmmN (M and N < 16)
- -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16)
+ -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2)
VEX VOP %ymmM, %ymmM, %ymmN
-> VEX VOP %xmmM, %xmmM, %xmmN
VOP, one of vpandn and vpxor:
VOP, one of vpandnd and vpandnq:
EVEX VOP %zmmM, %zmmM, %zmmN
-> VEX vpandn %xmmM, %xmmM, %xmmN (M and N < 16)
- -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16)
+ -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2)
EVEX VOP %ymmM, %ymmM, %ymmN
-> VEX vpandn %xmmM, %xmmM, %xmmN (M and N < 16)
- -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16)
+ -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2)
VOP, one of vpxord and vpxorq:
EVEX VOP %zmmM, %zmmM, %zmmN
-> VEX vpxor %xmmM, %xmmM, %xmmN (M and N < 16)
- -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16)
+ -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2)
EVEX VOP %ymmM, %ymmM, %ymmN
-> VEX vpxor %xmmM, %xmmM, %xmmN (M and N < 16)
- -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16)
+ -> EVEX VOP %xmmM, %xmmM, %xmmN (M || N >= 16) (-O2)
VOP, one of kxord and kxorq:
VEX VOP %kM, %kM, %kN
-> VEX kxorw %kM, %kM, %kN
i.tm.opcode_modifier.vexw = VEXW0;
i.tm.opcode_modifier.evex = 0;
}
- else if (cpu_arch_flags.bitfield.cpuavx512vl
- || cpu_arch_isa_flags.bitfield.cpuavx512vl)
+ else if (optimize > 1
+ && (cpu_arch_flags.bitfield.cpuavx512vl
+ || cpu_arch_isa_flags.bitfield.cpuavx512vl))
i.tm.opcode_modifier.evex = EVEX128;
else
return;
Optimize instruction encoding with smaller instruction size. @samp{-O}
and @samp{-O1} encode 64-bit register load instructions with 64-bit
immediate as 32-bit register load instructions with 31-bit or 32-bits
-immediates and encode 64-bit register clearing instructions with 32-bit
-register clearing instructions. @samp{-O2} includes @samp{-O1}
-optimization plus encodes 256-bit and 512-bit vector register clearing
-instructions with 128-bit vector register clearing instructions.
+immediates, encode 64-bit register clearing instructions with 32-bit
+register clearing instructions and encode 256-bit/512-bit VEX/EVEX
+vector register clearing instructions with 128-bit VEX vector register
+clearing instructions. @samp{-O2} includes @samp{-O1} optimization plus
+encodes 256-bit/512-bit EVEX vector register clearing instructions with
+128-bit EVEX vector register clearing instructions.
@samp{-Os} includes @samp{-O2} optimization plus encodes 16-bit, 32-bit
and 64-bit register tests with immediate as 8-bit register test with
immediate. @samp{-O0} turns off this optimization.
run_dump_test "nop-1"
run_dump_test "nop-2"
run_dump_test "optimize-1"
+ run_dump_test "optimize-1a"
run_dump_test "optimize-2"
run_dump_test "optimize-3"
run_dump_test "optimize-4"
run_dump_test "x86-64-nop-2"
run_dump_test "x86-64-optimize-1"
run_dump_test "x86-64-optimize-2"
+ run_dump_test "x86-64-optimize-2a"
run_dump_test "x86-64-optimize-3"
run_dump_test "x86-64-optimize-4"
run_dump_test "x86-64-optimize-5"
--- /dev/null
+#source: optimize-1.s
+#as: -O
+#objdump: -drw
+#name: optimized encoding 1a with -O
+
+.*: +file format .*
+
+
+Disassembly of section .text:
+
+0+ <_start>:
+ +[a-f0-9]+: 62 f1 f5 4f 55 e9 vandnpd %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 55 e9 vandnpd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 74 4f 55 e9 vandnps %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f0 55 e9 vandnps %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 75 4f df e9 vpandnd %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 f5 4f df e9 vpandnq %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 df e9 vpandn %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 f5 4f 57 e9 vxorpd %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 57 e9 vxorpd %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 74 4f 57 e9 vxorps %zmm1,%zmm1,%zmm5\{%k7\}
+ +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f0 57 e9 vxorps %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 75 4f ef e9 vpxord %zmm1,%zmm1,%zmm5\{%k7\}
+ +[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]+: c5 f1 ef e9 vpxor %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: 62 f1 f5 4f ef e9 vpxorq %zmm1,%zmm1,%zmm5\{%k7\}
+ +[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]+: 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]+: c5 f1 f8 e9 vpsubb %xmm1,%xmm1,%xmm5
+ +[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]+: c5 f1 f9 e9 vpsubw %xmm1,%xmm1,%xmm5
+ +[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]+: c5 f1 fa e9 vpsubd %xmm1,%xmm1,%xmm5
+ +[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]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f1 fb e9 vpsubq %xmm1,%xmm1,%xmm5
+ +[a-f0-9]+: c5 f4 47 e9 kxorw %k1,%k1,%k5
+ +[a-f0-9]+: c5 f4 47 e9 kxorw %k1,%k1,%k5
+ +[a-f0-9]+: c5 f4 42 e9 kandnw %k1,%k1,%k5
+ +[a-f0-9]+: c5 f4 42 e9 kandnw %k1,%k1,%k5
+#pass
--- /dev/null
+#source: x86-64-optimize-2.s
+#as: -O
+#objdump: -drw
+#name: x86-64 optimized encoding 2a with -O
+
+.*: +file format .*
+
+
+Disassembly of section .text:
+
+0+ <_start>:
+ +[a-f0-9]+: 62 71 f5 4f 55 f9 vandnpd %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 55 f9 vandnpd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 f5 48 55 c1 vandnpd %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 f5 28 55 c1 vandnpd %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 f5 40 55 c9 vandnpd %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 f5 20 55 c9 vandnpd %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 74 4f 55 f9 vandnps %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 70 55 f9 vandnps %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 74 48 55 c1 vandnps %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 74 28 55 c1 vandnps %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 74 40 55 c9 vandnps %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 74 20 55 c9 vandnps %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 71 75 4f df f9 vpandnd %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 75 48 df c1 vpandnd %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 75 28 df c1 vpandnd %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 75 40 df c9 vpandnd %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 75 20 df c9 vpandnd %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 f5 4f df f9 vpandnq %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 df f9 vpandn %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 f5 48 df c1 vpandnq %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 f5 28 df c1 vpandnq %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 f5 40 df c9 vpandnq %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 f5 20 df c9 vpandnq %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 f5 4f 57 f9 vxorpd %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 57 f9 vxorpd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 f5 48 57 c1 vxorpd %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 f5 28 57 c1 vxorpd %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 f5 40 57 c9 vxorpd %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 f5 20 57 c9 vxorpd %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 74 4f 57 f9 vxorps %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 70 57 f9 vxorps %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 74 48 57 c1 vxorps %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 74 28 57 c1 vxorps %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 74 40 57 c9 vxorps %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 74 20 57 c9 vxorps %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 71 75 4f ef f9 vpxord %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 75 48 ef c1 vpxord %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 75 28 ef c1 vpxord %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 75 40 ef c9 vpxord %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 75 20 ef c9 vpxord %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 f5 4f ef f9 vpxorq %zmm1,%zmm1,%zmm15\{%k7\}
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: c5 71 ef f9 vpxor %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 f5 48 ef c1 vpxorq %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 f5 28 ef c1 vpxorq %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 f5 40 ef c9 vpxorq %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 f5 20 ef c9 vpxorq %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 75 4f f8 f9 vpsubb %zmm1,%zmm1,%zmm15\{%k7\}
+ +[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]+: c5 71 f8 f9 vpsubb %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 75 48 f8 c1 vpsubb %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 75 28 f8 c1 vpsubb %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 75 40 f8 c9 vpsubb %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 75 20 f8 c9 vpsubb %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 75 4f f9 f9 vpsubw %zmm1,%zmm1,%zmm15\{%k7\}
+ +[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]+: c5 71 f9 f9 vpsubw %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 75 48 f9 c1 vpsubw %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 75 28 f9 c1 vpsubw %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 75 40 f9 c9 vpsubw %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 75 20 f9 c9 vpsubw %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 75 4f fa f9 vpsubd %zmm1,%zmm1,%zmm15\{%k7\}
+ +[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]+: c5 71 fa f9 vpsubd %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 75 48 fa c1 vpsubd %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 75 28 fa c1 vpsubd %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 75 40 fa c9 vpsubd %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 75 20 fa c9 vpsubd %ymm17,%ymm17,%ymm1
+ +[a-f0-9]+: 62 71 f5 4f fb f9 vpsubq %zmm1,%zmm1,%zmm15\{%k7\}
+ +[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]+: c5 71 fb f9 vpsubq %xmm1,%xmm1,%xmm15
+ +[a-f0-9]+: 62 e1 f5 48 fb c1 vpsubq %zmm1,%zmm1,%zmm16
+ +[a-f0-9]+: 62 e1 f5 28 fb c1 vpsubq %ymm1,%ymm1,%ymm16
+ +[a-f0-9]+: 62 b1 f5 40 fb c9 vpsubq %zmm17,%zmm17,%zmm1
+ +[a-f0-9]+: 62 b1 f5 20 fb c9 vpsubq %ymm17,%ymm17,%ymm1
+#pass
projects / deliverable / binutils-gdb.git / commitdiff
