[llvm] r342736 - [X86][Sched] Add zero idiom sched data to the SNB model.
Clement Courbet via llvm-commits
llvm-commits at lists.llvm.org
Fri Sep 21 07:07:20 PDT 2018
Author: courbet
Date: Fri Sep 21 07:07:20 2018
New Revision: 342736
URL: http://llvm.org/viewvc/llvm-project?rev=342736&view=rev
Log:
[X86][Sched] Add zero idiom sched data to the SNB model.
Summary:
On SNB, renamer-based zeroing does not work for:
- 16 and 8-bit GPRs[1].
- MMX [2].
- ANDN variants [3]
[1] echo 'sub %ax, %ax' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
[2] echo 'pxor %mm0, %mm0' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
[3] echo 'andnps %xmm0, %xmm0' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
Reviewers: RKSimon, andreadb
Subscribers: gbedwell, craig.topper, llvm-commits
Differential Revision: https://reviews.llvm.org/D52358
Added:
llvm/trunk/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s
Modified:
llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td
llvm/trunk/test/CodeGen/X86/avx-schedule.ll
llvm/trunk/test/CodeGen/X86/avx512-schedule.ll
llvm/trunk/test/CodeGen/X86/sse-schedule.ll
Modified: llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td?rev=342736&r1=342735&r2=342736&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td (original)
+++ llvm/trunk/lib/Target/X86/X86SchedSandyBridge.td Fri Sep 21 07:07:20 2018
@@ -718,7 +718,6 @@ def SBWriteResGroup30 : SchedWriteRes<[S
let NumMicroOps = 1;
let ResourceCycles = [1];
}
-def: InstRW<[SBWriteResGroup30], (instregex "(V?)PCMPGTQrr")>;
def SBWriteResGroup31 : SchedWriteRes<[SBPort23]> {
let Latency = 5;
@@ -1138,4 +1137,55 @@ def: InstRW<[SBWriteResGroup131], (instr
def: InstRW<[WriteZero], (instrs CLC)>;
+// Intruction variants handled by the renamer. These might not need execution
+// ports in certain conditions.
+// See Agner's Fog "The microarchitecture of Intel, AMD and VIA CPUs",
+// section "Sandy Bridge and Ivy Bridge Pipeline" > "Register allocation and
+// renaming".
+// These can be investigated with llvm-exegesis, e.g.
+// echo 'pxor %mm0, %mm0' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
+// echo 'vxorpd %xmm0, %xmm0, %xmm1' | /tmp/llvm-exegesis -mode=uops -snippets-file=-
+
+def SBWriteZeroLatency : SchedWriteRes<[]> {
+ let Latency = 0;
+}
+
+def SBWriteZeroIdiom : SchedWriteVariant<[
+ SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [SBWriteZeroLatency]>,
+ SchedVar<NoSchedPred, [WriteALU]>
+]>;
+def : InstRW<[SBWriteZeroIdiom], (instrs SUB32rr, SUB64rr,
+ XOR32rr, XOR64rr)>;
+
+def SBWriteFZeroIdiom : SchedWriteVariant<[
+ SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [SBWriteZeroLatency]>,
+ SchedVar<NoSchedPred, [WriteFLogic]>
+]>;
+def : InstRW<[SBWriteFZeroIdiom], (instrs XORPSrr, VXORPSrr, XORPDrr,
+ VXORPDrr)>;
+
+def SBWriteVZeroIdiomLogicX : SchedWriteVariant<[
+ SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [SBWriteZeroLatency]>,
+ SchedVar<NoSchedPred, [WriteVecLogicX]>
+]>;
+def : InstRW<[SBWriteVZeroIdiomLogicX], (instrs PXORrr, VPXORrr)>;
+
+def SBWriteVZeroIdiomALUX : SchedWriteVariant<[
+ SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [SBWriteZeroLatency]>,
+ SchedVar<NoSchedPred, [WriteVecALUX]>
+]>;
+def : InstRW<[SBWriteVZeroIdiomALUX], (instrs PSUBBrr, VPSUBBrr,
+ PSUBDrr, VPSUBDrr,
+ PSUBQrr, VPSUBQrr,
+ PSUBWrr, VPSUBWrr,
+ PCMPGTBrr, VPCMPGTBrr,
+ PCMPGTDrr, VPCMPGTDrr,
+ PCMPGTWrr, VPCMPGTWrr)>;
+
+def SBWriteVZeroIdiomPCMPGTQ : SchedWriteVariant<[
+ SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [SBWriteZeroLatency]>,
+ SchedVar<NoSchedPred, [SBWriteResGroup30]>
+]>;
+def : InstRW<[SBWriteVZeroIdiomPCMPGTQ], (instrs PCMPGTQrr, VPCMPGTQrr)>;
+
} // SchedModel
Modified: llvm/trunk/test/CodeGen/X86/avx-schedule.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx-schedule.ll?rev=342736&r1=342735&r2=342736&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx-schedule.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx-schedule.ll Fri Sep 21 07:07:20 2018
@@ -4637,7 +4637,7 @@ define <8 x float> @test_subps(<8 x floa
define i32 @test_testpd(<2 x double> %a0, <2 x double> %a1, <2 x double> *%a2) {
; GENERIC-LABEL: test_testpd:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; GENERIC-NEXT: xorl %eax, %eax # sched: [0:0.25]
; GENERIC-NEXT: vtestpd %xmm1, %xmm0 # sched: [1:1.00]
; GENERIC-NEXT: setb %al # sched: [1:0.50]
; GENERIC-NEXT: vtestpd (%rdi), %xmm0 # sched: [7:1.00]
@@ -4646,7 +4646,7 @@ define i32 @test_testpd(<2 x double> %a0
;
; SANDY-LABEL: test_testpd:
; SANDY: # %bb.0:
-; SANDY-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; SANDY-NEXT: xorl %eax, %eax # sched: [0:0.25]
; SANDY-NEXT: vtestpd %xmm1, %xmm0 # sched: [1:1.00]
; SANDY-NEXT: setb %al # sched: [1:0.50]
; SANDY-NEXT: vtestpd (%rdi), %xmm0 # sched: [7:1.00]
@@ -4717,7 +4717,7 @@ declare i32 @llvm.x86.avx.vtestc.pd(<2 x
define i32 @test_testpd_ymm(<4 x double> %a0, <4 x double> %a1, <4 x double> *%a2) {
; GENERIC-LABEL: test_testpd_ymm:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; GENERIC-NEXT: xorl %eax, %eax # sched: [0:0.25]
; GENERIC-NEXT: vtestpd %ymm1, %ymm0 # sched: [1:1.00]
; GENERIC-NEXT: setb %al # sched: [1:0.50]
; GENERIC-NEXT: vtestpd (%rdi), %ymm0 # sched: [8:1.00]
@@ -4727,7 +4727,7 @@ define i32 @test_testpd_ymm(<4 x double>
;
; SANDY-LABEL: test_testpd_ymm:
; SANDY: # %bb.0:
-; SANDY-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; SANDY-NEXT: xorl %eax, %eax # sched: [0:0.25]
; SANDY-NEXT: vtestpd %ymm1, %ymm0 # sched: [1:1.00]
; SANDY-NEXT: setb %al # sched: [1:0.50]
; SANDY-NEXT: vtestpd (%rdi), %ymm0 # sched: [8:1.00]
@@ -4804,7 +4804,7 @@ declare i32 @llvm.x86.avx.vtestc.pd.256(
define i32 @test_testps(<4 x float> %a0, <4 x float> %a1, <4 x float> *%a2) {
; GENERIC-LABEL: test_testps:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; GENERIC-NEXT: xorl %eax, %eax # sched: [0:0.25]
; GENERIC-NEXT: vtestps %xmm1, %xmm0 # sched: [1:1.00]
; GENERIC-NEXT: setb %al # sched: [1:0.50]
; GENERIC-NEXT: vtestps (%rdi), %xmm0 # sched: [7:1.00]
@@ -4813,7 +4813,7 @@ define i32 @test_testps(<4 x float> %a0,
;
; SANDY-LABEL: test_testps:
; SANDY: # %bb.0:
-; SANDY-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; SANDY-NEXT: xorl %eax, %eax # sched: [0:0.25]
; SANDY-NEXT: vtestps %xmm1, %xmm0 # sched: [1:1.00]
; SANDY-NEXT: setb %al # sched: [1:0.50]
; SANDY-NEXT: vtestps (%rdi), %xmm0 # sched: [7:1.00]
@@ -4884,7 +4884,7 @@ declare i32 @llvm.x86.avx.vtestc.ps(<4 x
define i32 @test_testps_ymm(<8 x float> %a0, <8 x float> %a1, <8 x float> *%a2) {
; GENERIC-LABEL: test_testps_ymm:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; GENERIC-NEXT: xorl %eax, %eax # sched: [0:0.25]
; GENERIC-NEXT: vtestps %ymm1, %ymm0 # sched: [1:1.00]
; GENERIC-NEXT: setb %al # sched: [1:0.50]
; GENERIC-NEXT: vtestps (%rdi), %ymm0 # sched: [8:1.00]
@@ -4894,7 +4894,7 @@ define i32 @test_testps_ymm(<8 x float>
;
; SANDY-LABEL: test_testps_ymm:
; SANDY: # %bb.0:
-; SANDY-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; SANDY-NEXT: xorl %eax, %eax # sched: [0:0.25]
; SANDY-NEXT: vtestps %ymm1, %ymm0 # sched: [1:1.00]
; SANDY-NEXT: setb %al # sched: [1:0.50]
; SANDY-NEXT: vtestps (%rdi), %ymm0 # sched: [8:1.00]
Modified: llvm/trunk/test/CodeGen/X86/avx512-schedule.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-schedule.ll?rev=342736&r1=342735&r2=342736&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-schedule.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-schedule.ll Fri Sep 21 07:07:20 2018
@@ -1141,7 +1141,7 @@ define i32 @test3(float %a, float %b) {
define float @test5(float %p) #0 {
; GENERIC-LABEL: test5:
; GENERIC: # %bb.0: # %entry
-; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vucomiss %xmm1, %xmm0 # sched: [2:1.00]
; GENERIC-NEXT: jne .LBB67_1 # sched: [1:1.00]
; GENERIC-NEXT: jp .LBB67_1 # sched: [1:1.00]
@@ -1183,7 +1183,7 @@ return:
define i32 @test6(i32 %a, i32 %b) {
; GENERIC-LABEL: test6:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; GENERIC-NEXT: xorl %eax, %eax # sched: [0:0.25]
; GENERIC-NEXT: cmpl %esi, %edi # sched: [1:0.33]
; GENERIC-NEXT: sete %al # sched: [1:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -1202,7 +1202,7 @@ define i32 @test6(i32 %a, i32 %b) {
define i32 @test7(double %x, double %y) #2 {
; GENERIC-LABEL: test7:
; GENERIC: # %bb.0: # %entry
-; GENERIC-NEXT: xorl %eax, %eax # sched: [1:0.33]
+; GENERIC-NEXT: xorl %eax, %eax # sched: [0:0.25]
; GENERIC-NEXT: vucomisd %xmm1, %xmm0 # sched: [2:1.00]
; GENERIC-NEXT: setne %al # sched: [1:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -2424,7 +2424,7 @@ define <16 x double> @scto16f64(<16 x i8
define <16 x double> @sbto16f64(<16 x double> %a) {
; GENERIC-LABEL: sbto16f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm2, %xmm2, %xmm2 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm2, %xmm2, %xmm2 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltpd %zmm0, %zmm2, %k0 # sched: [3:1.00]
; GENERIC-NEXT: vcmpltpd %zmm1, %zmm2, %k1 # sched: [3:1.00]
; GENERIC-NEXT: kunpckbw %k0, %k1, %k0 # sched: [1:1.00]
@@ -2453,7 +2453,7 @@ define <16 x double> @sbto16f64(<16 x do
define <8 x double> @sbto8f64(<8 x double> %a) {
; GENERIC-LABEL: sbto8f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltpd %zmm0, %zmm1, %k0 # sched: [3:1.00]
; GENERIC-NEXT: vpmovm2d %k0, %ymm0 # sched: [1:0.33]
; GENERIC-NEXT: vcvtdq2pd %ymm0, %zmm0 # sched: [4:1.00]
@@ -2474,7 +2474,7 @@ define <8 x double> @sbto8f64(<8 x doubl
define <8 x float> @sbto8f32(<8 x float> %a) {
; GENERIC-LABEL: sbto8f32:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: vcvtdq2ps %ymm0, %ymm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -2493,7 +2493,7 @@ define <8 x float> @sbto8f32(<8 x float>
define <4 x float> @sbto4f32(<4 x float> %a) {
; GENERIC-LABEL: sbto4f32:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; GENERIC-NEXT: vcvtdq2ps %xmm0, %xmm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -2512,7 +2512,7 @@ define <4 x float> @sbto4f32(<4 x float>
define <4 x double> @sbto4f64(<4 x double> %a) {
; GENERIC-LABEL: sbto4f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltpd %ymm0, %ymm1, %k0 # sched: [3:1.00]
; GENERIC-NEXT: vpmovm2d %k0, %xmm0 # sched: [1:0.33]
; GENERIC-NEXT: vcvtdq2pd %xmm0, %ymm0 # sched: [4:1.00]
@@ -2533,7 +2533,7 @@ define <4 x double> @sbto4f64(<4 x doubl
define <2 x float> @sbto2f32(<2 x float> %a) {
; GENERIC-LABEL: sbto2f32:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; GENERIC-NEXT: vcvtdq2ps %xmm0, %xmm0 # sched: [3:1.00]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -2552,7 +2552,7 @@ define <2 x float> @sbto2f32(<2 x float>
define <2 x double> @sbto2f64(<2 x double> %a) {
; GENERIC-LABEL: sbto2f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpltpd %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; GENERIC-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,2,3] sched: [1:1.00]
; GENERIC-NEXT: vcvtdq2pd %xmm0, %xmm0 # sched: [4:1.00]
@@ -2827,7 +2827,7 @@ define <16 x double> @ubto16f64(<16 x i3
define <8 x float> @ubto8f32(<8 x i32> %a) {
; GENERIC-LABEL: ubto8f32:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpcmpgtd %ymm0, %ymm1, %ymm0 # sched: [1:0.50]
; GENERIC-NEXT: vpandd {{.*}}(%rip){1to8}, %ymm0, %ymm0 # sched: [8:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -2846,7 +2846,7 @@ define <8 x float> @ubto8f32(<8 x i32> %
define <8 x double> @ubto8f64(<8 x i32> %a) {
; GENERIC-LABEL: ubto8f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpcmpgtd %ymm0, %ymm1, %ymm0 # sched: [1:0.50]
; GENERIC-NEXT: vpsrld $31, %ymm0, %ymm0 # sched: [1:1.00]
; GENERIC-NEXT: vcvtdq2pd %ymm0, %zmm0 # sched: [4:1.00]
@@ -2867,7 +2867,7 @@ define <8 x double> @ubto8f64(<8 x i32>
define <4 x float> @ubto4f32(<4 x i32> %a) {
; GENERIC-LABEL: ubto4f32:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpcmpgtd %xmm0, %xmm1, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: vpandd {{.*}}(%rip){1to4}, %xmm0, %xmm0 # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -2886,7 +2886,7 @@ define <4 x float> @ubto4f32(<4 x i32> %
define <4 x double> @ubto4f64(<4 x i32> %a) {
; GENERIC-LABEL: ubto4f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpcmpgtd %xmm0, %xmm1, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: vpsrld $31, %xmm0, %xmm0 # sched: [1:1.00]
; GENERIC-NEXT: vcvtdq2pd %xmm0, %ymm0 # sched: [4:1.00]
@@ -2907,7 +2907,7 @@ define <4 x double> @ubto4f64(<4 x i32>
define <2 x float> @ubto2f32(<2 x i32> %a) {
; GENERIC-LABEL: ubto2f32:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3] sched: [1:0.50]
; GENERIC-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: vpandn {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:0.50]
@@ -2930,7 +2930,7 @@ define <2 x float> @ubto2f32(<2 x i32> %
define <2 x double> @ubto2f64(<2 x i32> %a) {
; GENERIC-LABEL: ubto2f64:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3] sched: [1:0.50]
; GENERIC-NEXT: vpcmpeqq %xmm1, %xmm0, %xmm0 # sched: [1:0.50]
; GENERIC-NEXT: vpandn {{.*}}(%rip), %xmm0, %xmm0 # sched: [7:0.50]
@@ -6501,7 +6501,7 @@ define <8 x i64> @mov_test39(i8 * %addr,
define <16 x float> @mov_test40(i8 * %addr, <16 x float> %old, <16 x float> %mask1) {
; GENERIC-LABEL: mov_test40:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm2, %xmm2, %xmm2 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm2, %xmm2, %xmm2 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqps %zmm2, %zmm1, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovaps (%rdi), %zmm0 {%k1} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6522,7 +6522,7 @@ define <16 x float> @mov_test40(i8 * %ad
define <16 x float> @mov_test41(i8 * %addr, <16 x float> %old, <16 x float> %mask1) {
; GENERIC-LABEL: mov_test41:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm2, %xmm2, %xmm2 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm2, %xmm2, %xmm2 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqps %zmm2, %zmm1, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovups (%rdi), %zmm0 {%k1} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6543,7 +6543,7 @@ define <16 x float> @mov_test41(i8 * %ad
define <16 x float> @mov_test42(i8 * %addr, <16 x float> %mask1) {
; GENERIC-LABEL: mov_test42:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqps %zmm1, %zmm0, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovaps (%rdi), %zmm0 {%k1} {z} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6564,7 +6564,7 @@ define <16 x float> @mov_test42(i8 * %ad
define <16 x float> @mov_test43(i8 * %addr, <16 x float> %mask1) {
; GENERIC-LABEL: mov_test43:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqps %zmm1, %zmm0, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovups (%rdi), %zmm0 {%k1} {z} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6585,7 +6585,7 @@ define <16 x float> @mov_test43(i8 * %ad
define <8 x double> @mov_test44(i8 * %addr, <8 x double> %old, <8 x double> %mask1) {
; GENERIC-LABEL: mov_test44:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm2, %xmm2, %xmm2 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm2, %xmm2, %xmm2 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqpd %zmm2, %zmm1, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovapd (%rdi), %zmm0 {%k1} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6606,7 +6606,7 @@ define <8 x double> @mov_test44(i8 * %ad
define <8 x double> @mov_test45(i8 * %addr, <8 x double> %old, <8 x double> %mask1) {
; GENERIC-LABEL: mov_test45:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm2, %xmm2, %xmm2 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm2, %xmm2, %xmm2 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqpd %zmm2, %zmm1, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovupd (%rdi), %zmm0 {%k1} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6627,7 +6627,7 @@ define <8 x double> @mov_test45(i8 * %ad
define <8 x double> @mov_test46(i8 * %addr, <8 x double> %mask1) {
; GENERIC-LABEL: mov_test46:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqpd %zmm1, %zmm0, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovapd (%rdi), %zmm0 {%k1} {z} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -6648,7 +6648,7 @@ define <8 x double> @mov_test46(i8 * %ad
define <8 x double> @mov_test47(i8 * %addr, <8 x double> %mask1) {
; GENERIC-LABEL: mov_test47:
; GENERIC: # %bb.0:
-; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [1:1.00]
+; GENERIC-NEXT: vxorpd %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vcmpneq_oqpd %zmm1, %zmm0, %k1 # sched: [3:1.00]
; GENERIC-NEXT: vmovupd (%rdi), %zmm0 {%k1} {z} # sched: [7:0.50]
; GENERIC-NEXT: retq # sched: [1:1.00]
@@ -7064,7 +7064,7 @@ define <16 x i8> @vcmp_test8(<16 x i32>%
; GENERIC-NEXT: vzeroupper # sched: [100:0.33]
; GENERIC-NEXT: retq # sched: [1:1.00]
; GENERIC-NEXT: .LBB386_1:
-; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [1:0.33]
+; GENERIC-NEXT: vpxor %xmm1, %xmm1, %xmm1 # sched: [0:0.25]
; GENERIC-NEXT: vpcmpgtd %zmm1, %zmm0, %k0 # sched: [1:0.50]
; GENERIC-NEXT: vpmovm2b %k0, %xmm0 # sched: [1:0.33]
; GENERIC-NEXT: vzeroupper # sched: [100:0.33]
@@ -8459,7 +8459,7 @@ define <16 x float> @_xmm16xfloat(<16
define <16 x i32> @test_vbroadcast() {
; GENERIC-LABEL: test_vbroadcast:
; GENERIC: # %bb.0: # %entry
-; GENERIC-NEXT: vxorps %xmm0, %xmm0, %xmm0 # sched: [1:1.00]
+; GENERIC-NEXT: vxorps %xmm0, %xmm0, %xmm0 # sched: [0:0.25]
; GENERIC-NEXT: vcmpunordps %zmm0, %zmm0, %k0 # sched: [3:1.00]
; GENERIC-NEXT: vpmovm2d %k0, %zmm0 # sched: [1:0.33]
; GENERIC-NEXT: knotw %k0, %k1 # sched: [1:0.33]
Modified: llvm/trunk/test/CodeGen/X86/sse-schedule.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/sse-schedule.ll?rev=342736&r1=342735&r2=342736&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/sse-schedule.ll (original)
+++ llvm/trunk/test/CodeGen/X86/sse-schedule.ll Fri Sep 21 07:07:20 2018
@@ -6120,7 +6120,7 @@ define <4 x float> @test_fnop() nounwind
; GENERIC-NEXT: #APP
; GENERIC-NEXT: nop # sched: [1:0.25]
; GENERIC-NEXT: #NO_APP
-; GENERIC-NEXT: xorps %xmm0, %xmm0 # sched: [1:1.00]
+; GENERIC-NEXT: xorps %xmm0, %xmm0 # sched: [0:0.25]
; GENERIC-NEXT: retq # sched: [1:1.00]
;
; ATOM-LABEL: test_fnop:
@@ -6148,7 +6148,7 @@ define <4 x float> @test_fnop() nounwind
; SANDY-SSE-NEXT: #APP
; SANDY-SSE-NEXT: nop # sched: [1:0.25]
; SANDY-SSE-NEXT: #NO_APP
-; SANDY-SSE-NEXT: xorps %xmm0, %xmm0 # sched: [1:1.00]
+; SANDY-SSE-NEXT: xorps %xmm0, %xmm0 # sched: [0:0.25]
; SANDY-SSE-NEXT: retq # sched: [1:1.00]
;
; SANDY-LABEL: test_fnop:
@@ -6156,7 +6156,7 @@ define <4 x float> @test_fnop() nounwind
; SANDY-NEXT: #APP
; SANDY-NEXT: nop # sched: [1:0.25]
; SANDY-NEXT: #NO_APP
-; SANDY-NEXT: vxorps %xmm0, %xmm0, %xmm0 # sched: [1:1.00]
+; SANDY-NEXT: vxorps %xmm0, %xmm0, %xmm0 # sched: [0:0.25]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-SSE-LABEL: test_fnop:
Added: llvm/trunk/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s?rev=342736&view=auto
==============================================================================
--- llvm/trunk/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s (added)
+++ llvm/trunk/test/tools/llvm-mca/X86/SandyBridge/zero-idioms.s Fri Sep 21 07:07:20 2018
@@ -0,0 +1,348 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=sandybridge -timeline -register-file-stats -iterations=1 < %s | FileCheck %s
+
+# On SNB, renamer-based zeroing does not work for:
+# - 16 and 8-bit GPRs
+# - MMX
+# - ANDN variants
+
+subl %eax, %eax
+subq %rax, %rax
+xorl %eax, %eax
+xorq %rax, %rax
+
+pcmpgtb %mm2, %mm2
+pcmpgtd %mm2, %mm2
+# pcmpgtq %mm2, %mm2 # invalid operand for instruction
+pcmpgtw %mm2, %mm2
+
+pcmpgtb %xmm2, %xmm2
+pcmpgtd %xmm2, %xmm2
+pcmpgtq %xmm2, %xmm2
+pcmpgtw %xmm2, %xmm2
+
+vpcmpgtb %xmm3, %xmm3, %xmm3
+vpcmpgtd %xmm3, %xmm3, %xmm3
+vpcmpgtq %xmm3, %xmm3, %xmm3
+vpcmpgtw %xmm3, %xmm3, %xmm3
+
+vpcmpgtb %xmm3, %xmm3, %xmm5
+vpcmpgtd %xmm3, %xmm3, %xmm5
+vpcmpgtq %xmm3, %xmm3, %xmm5
+vpcmpgtw %xmm3, %xmm3, %xmm5
+
+psubb %mm2, %mm2
+psubd %mm2, %mm2
+psubq %mm2, %mm2
+psubw %mm2, %mm2
+psubb %xmm2, %xmm2
+psubd %xmm2, %xmm2
+psubq %xmm2, %xmm2
+psubw %xmm2, %xmm2
+vpsubb %xmm3, %xmm3, %xmm3
+vpsubd %xmm3, %xmm3, %xmm3
+vpsubq %xmm3, %xmm3, %xmm3
+vpsubw %xmm3, %xmm3, %xmm3
+
+vpsubb %xmm3, %xmm3, %xmm5
+vpsubd %xmm3, %xmm3, %xmm5
+vpsubq %xmm3, %xmm3, %xmm5
+vpsubw %xmm3, %xmm3, %xmm5
+
+andnps %xmm0, %xmm0
+andnpd %xmm1, %xmm1
+vandnps %xmm2, %xmm2, %xmm2
+vandnpd %xmm1, %xmm1, %xmm1
+pandn %mm2, %mm2
+pandn %xmm2, %xmm2
+vpandn %xmm3, %xmm3, %xmm3
+
+vandnps %xmm2, %xmm2, %xmm5
+vandnpd %xmm1, %xmm1, %xmm5
+vpandn %xmm3, %xmm3, %xmm5
+
+xorps %xmm0, %xmm0
+xorpd %xmm1, %xmm1
+vxorps %xmm2, %xmm2, %xmm2
+vxorpd %xmm1, %xmm1, %xmm1
+pxor %mm2, %mm2
+pxor %xmm2, %xmm2
+vpxor %xmm3, %xmm3, %xmm3
+
+vxorps %xmm4, %xmm4, %xmm5
+vxorpd %xmm1, %xmm1, %xmm3
+vpxor %xmm3, %xmm3, %xmm5
+
+# CHECK: Iterations: 1
+# CHECK-NEXT: Instructions: 55
+# CHECK-NEXT: Total Cycles: 27
+# CHECK-NEXT: Total uOps: 55
+
+# CHECK: Dispatch Width: 4
+# CHECK-NEXT: uOps Per Cycle: 2.04
+# CHECK-NEXT: IPC: 2.04
+# CHECK-NEXT: Block RThroughput: 13.8
+
+# CHECK: Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects (U)
+
+# CHECK: [1] [2] [3] [4] [5] [6] Instructions:
+# CHECK-NEXT: 1 0 0.25 subl %eax, %eax
+# CHECK-NEXT: 1 0 0.25 subq %rax, %rax
+# CHECK-NEXT: 1 0 0.25 xorl %eax, %eax
+# CHECK-NEXT: 1 0 0.25 xorq %rax, %rax
+# CHECK-NEXT: 1 3 1.00 pcmpgtb %mm2, %mm2
+# CHECK-NEXT: 1 3 1.00 pcmpgtd %mm2, %mm2
+# CHECK-NEXT: 1 3 1.00 pcmpgtw %mm2, %mm2
+# CHECK-NEXT: 1 0 0.25 pcmpgtb %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 pcmpgtd %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 pcmpgtq %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 pcmpgtw %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 vpcmpgtb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpcmpgtd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpcmpgtq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpcmpgtw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpcmpgtb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 vpcmpgtd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 vpcmpgtq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 vpcmpgtw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 3 1.00 psubb %mm2, %mm2
+# CHECK-NEXT: 1 3 1.00 psubd %mm2, %mm2
+# CHECK-NEXT: 1 3 1.00 psubq %mm2, %mm2
+# CHECK-NEXT: 1 3 1.00 psubw %mm2, %mm2
+# CHECK-NEXT: 1 0 0.25 psubb %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 psubd %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 psubq %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 psubw %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 vpsubb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpsubd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpsubq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpsubw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpsubb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 vpsubd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 vpsubq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 vpsubw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 1 1.00 andnps %xmm0, %xmm0
+# CHECK-NEXT: 1 1 1.00 andnpd %xmm1, %xmm1
+# CHECK-NEXT: 1 1 1.00 vandnps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: 1 1 1.00 vandnpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: 1 1 0.33 pandn %mm2, %mm2
+# CHECK-NEXT: 1 1 0.33 pandn %xmm2, %xmm2
+# CHECK-NEXT: 1 1 0.33 vpandn %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 1 1.00 vandnps %xmm2, %xmm2, %xmm5
+# CHECK-NEXT: 1 1 1.00 vandnpd %xmm1, %xmm1, %xmm5
+# CHECK-NEXT: 1 1 0.33 vpandn %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 1 0 0.25 xorps %xmm0, %xmm0
+# CHECK-NEXT: 1 0 0.25 xorpd %xmm1, %xmm1
+# CHECK-NEXT: 1 0 0.25 vxorps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 vxorpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: 1 1 0.33 pxor %mm2, %mm2
+# CHECK-NEXT: 1 0 0.25 pxor %xmm2, %xmm2
+# CHECK-NEXT: 1 0 0.25 vpxor %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 1 0 0.25 vxorps %xmm4, %xmm4, %xmm5
+# CHECK-NEXT: 1 0 0.25 vxorpd %xmm1, %xmm1, %xmm3
+# CHECK-NEXT: 1 0 0.25 vpxor %xmm3, %xmm3, %xmm5
+
+# CHECK: Register File statistics:
+# CHECK-NEXT: Total number of mappings created: 59
+# CHECK-NEXT: Max number of mappings used: 42
+
+# CHECK: Resources:
+# CHECK-NEXT: [0] - SBDivider
+# CHECK-NEXT: [1] - SBFPDivider
+# CHECK-NEXT: [2] - SBPort0
+# CHECK-NEXT: [3] - SBPort1
+# CHECK-NEXT: [4] - SBPort4
+# CHECK-NEXT: [5] - SBPort5
+# CHECK-NEXT: [6.0] - SBPort23
+# CHECK-NEXT: [6.1] - SBPort23
+
+# CHECK: Resource pressure per iteration:
+# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
+# CHECK-NEXT: - - 4.00 8.00 - 6.00 - -
+
+# CHECK: Resource pressure by instruction:
+# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
+# CHECK-NEXT: - - - - - - - - subl %eax, %eax
+# CHECK-NEXT: - - - - - - - - subq %rax, %rax
+# CHECK-NEXT: - - - - - - - - xorl %eax, %eax
+# CHECK-NEXT: - - - - - - - - xorq %rax, %rax
+# CHECK-NEXT: - - - 1.00 - - - - pcmpgtb %mm2, %mm2
+# CHECK-NEXT: - - - 1.00 - - - - pcmpgtd %mm2, %mm2
+# CHECK-NEXT: - - - 1.00 - - - - pcmpgtw %mm2, %mm2
+# CHECK-NEXT: - - - - - - - - pcmpgtb %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - pcmpgtd %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - pcmpgtq %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - pcmpgtw %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - vpcmpgtb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpcmpgtd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpcmpgtq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpcmpgtw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpcmpgtb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - vpcmpgtd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - vpcmpgtq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - vpcmpgtw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - 1.00 - - - - psubb %mm2, %mm2
+# CHECK-NEXT: - - - 1.00 - - - - psubd %mm2, %mm2
+# CHECK-NEXT: - - - 1.00 - - - - psubq %mm2, %mm2
+# CHECK-NEXT: - - - 1.00 - - - - psubw %mm2, %mm2
+# CHECK-NEXT: - - - - - - - - psubb %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - psubd %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - psubq %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - psubw %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - vpsubb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpsubd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpsubq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpsubw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vpsubb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - vpsubd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - vpsubq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - vpsubw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - 1.00 - - andnps %xmm0, %xmm0
+# CHECK-NEXT: - - - - - 1.00 - - andnpd %xmm1, %xmm1
+# CHECK-NEXT: - - - - - 1.00 - - vandnps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: - - - - - 1.00 - - vandnpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: - - 1.00 - - - - - pandn %mm2, %mm2
+# CHECK-NEXT: - - 1.00 - - - - - pandn %xmm2, %xmm2
+# CHECK-NEXT: - - 1.00 - - - - - vpandn %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - 1.00 - - vandnps %xmm2, %xmm2, %xmm5
+# CHECK-NEXT: - - - - - 1.00 - - vandnpd %xmm1, %xmm1, %xmm5
+# CHECK-NEXT: - - - 1.00 - - - - vpandn %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: - - - - - - - - xorps %xmm0, %xmm0
+# CHECK-NEXT: - - - - - - - - xorpd %xmm1, %xmm1
+# CHECK-NEXT: - - - - - - - - vxorps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - vxorpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: - - 1.00 - - - - - pxor %mm2, %mm2
+# CHECK-NEXT: - - - - - - - - pxor %xmm2, %xmm2
+# CHECK-NEXT: - - - - - - - - vpxor %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: - - - - - - - - vxorps %xmm4, %xmm4, %xmm5
+# CHECK-NEXT: - - - - - - - - vxorpd %xmm1, %xmm1, %xmm3
+# CHECK-NEXT: - - - - - - - - vpxor %xmm3, %xmm3, %xmm5
+
+# CHECK: Timeline view:
+# CHECK-NEXT: 0123456789
+# CHECK-NEXT: Index 0123456789 0123456
+
+# CHECK: [0,0] DR . . . . .. subl %eax, %eax
+# CHECK-NEXT: [0,1] DR . . . . .. subq %rax, %rax
+# CHECK-NEXT: [0,2] DR . . . . .. xorl %eax, %eax
+# CHECK-NEXT: [0,3] DR . . . . .. xorq %rax, %rax
+# CHECK-NEXT: [0,4] .DeeeER . . . .. pcmpgtb %mm2, %mm2
+# CHECK-NEXT: [0,5] .D===eeeER. . . .. pcmpgtd %mm2, %mm2
+# CHECK-NEXT: [0,6] .D======eeeER . . .. pcmpgtw %mm2, %mm2
+# CHECK-NEXT: [0,7] .D----------R . . .. pcmpgtb %xmm2, %xmm2
+# CHECK-NEXT: [0,8] . D---------R . . .. pcmpgtd %xmm2, %xmm2
+# CHECK-NEXT: [0,9] . D---------R . . .. pcmpgtq %xmm2, %xmm2
+# CHECK-NEXT: [0,10] . D---------R . . .. pcmpgtw %xmm2, %xmm2
+# CHECK-NEXT: [0,11] . D---------R . . .. vpcmpgtb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,12] . D--------R . . .. vpcmpgtd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,13] . D--------R . . .. vpcmpgtq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,14] . D--------R . . .. vpcmpgtw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,15] . D--------R . . .. vpcmpgtb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,16] . D-------R . . .. vpcmpgtd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,17] . D-------R . . .. vpcmpgtq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,18] . D-------R . . .. vpcmpgtw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,19] . D======eeeER . .. psubb %mm2, %mm2
+# CHECK-NEXT: [0,20] . D========eeeER . .. psubd %mm2, %mm2
+# CHECK-NEXT: [0,21] . D===========eeeER .. psubq %mm2, %mm2
+# CHECK-NEXT: [0,22] . D==============eeeER.. psubw %mm2, %mm2
+# CHECK-NEXT: [0,23] . D------------------R.. psubb %xmm2, %xmm2
+# CHECK-NEXT: [0,24] . .D-----------------R.. psubd %xmm2, %xmm2
+# CHECK-NEXT: [0,25] . .D-----------------R.. psubq %xmm2, %xmm2
+# CHECK-NEXT: [0,26] . .D-----------------R.. psubw %xmm2, %xmm2
+# CHECK-NEXT: [0,27] . .D-----------------R.. vpsubb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,28] . . D----------------R.. vpsubd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,29] . . D----------------R.. vpsubq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,30] . . D----------------R.. vpsubw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,31] . . D----------------R.. vpsubb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,32] . . D---------------R.. vpsubd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,33] . . D---------------R.. vpsubq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,34] . . D---------------R.. vpsubw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,35] . . DeE-------------R.. andnps %xmm0, %xmm0
+# CHECK-NEXT: [0,36] . . DeE------------R.. andnpd %xmm1, %xmm1
+# CHECK-NEXT: [0,37] . . D=eE-----------R.. vandnps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: [0,38] . . D==eE----------R.. vandnpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,39] . . D=============eER. pandn %mm2, %mm2
+# CHECK-NEXT: [0,40] . . D=eE-----------R. pandn %xmm2, %xmm2
+# CHECK-NEXT: [0,41] . . DeE------------R. vpandn %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,42] . . D==eE----------R. vandnps %xmm2, %xmm2, %xmm5
+# CHECK-NEXT: [0,43] . . D===eE---------R. vandnpd %xmm1, %xmm1, %xmm5
+# CHECK-NEXT: [0,44] . . .DeE-----------R. vpandn %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: [0,45] . . .D-------------R. xorps %xmm0, %xmm0
+# CHECK-NEXT: [0,46] . . .D=E-----------R. xorpd %xmm1, %xmm1
+# CHECK-NEXT: [0,47] . . .D=E-----------R. vxorps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: [0,48] . . . DE-----------R. vxorpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: [0,49] . . . D===========eER pxor %mm2, %mm2
+# CHECK-NEXT: [0,50] . . . DE------------R pxor %xmm2, %xmm2
+# CHECK-NEXT: [0,51] . . . D-------------R vpxor %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: [0,52] . . . D------------R vxorps %xmm4, %xmm4, %xmm5
+# CHECK-NEXT: [0,53] . . . D------------R vxorpd %xmm1, %xmm1, %xmm3
+# CHECK-NEXT: [0,54] . . . D------------R vpxor %xmm3, %xmm3, %xmm5
+
+# CHECK: Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK: [0] [1] [2] [3]
+# CHECK-NEXT: 0. 1 0.0 0.0 0.0 subl %eax, %eax
+# CHECK-NEXT: 1. 1 0.0 0.0 0.0 subq %rax, %rax
+# CHECK-NEXT: 2. 1 0.0 0.0 0.0 xorl %eax, %eax
+# CHECK-NEXT: 3. 1 0.0 0.0 0.0 xorq %rax, %rax
+# CHECK-NEXT: 4. 1 1.0 1.0 0.0 pcmpgtb %mm2, %mm2
+# CHECK-NEXT: 5. 1 4.0 0.0 0.0 pcmpgtd %mm2, %mm2
+# CHECK-NEXT: 6. 1 7.0 0.0 0.0 pcmpgtw %mm2, %mm2
+# CHECK-NEXT: 7. 1 0.0 0.0 10.0 pcmpgtb %xmm2, %xmm2
+# CHECK-NEXT: 8. 1 0.0 0.0 9.0 pcmpgtd %xmm2, %xmm2
+# CHECK-NEXT: 9. 1 0.0 0.0 9.0 pcmpgtq %xmm2, %xmm2
+# CHECK-NEXT: 10. 1 0.0 0.0 9.0 pcmpgtw %xmm2, %xmm2
+# CHECK-NEXT: 11. 1 0.0 0.0 9.0 vpcmpgtb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 12. 1 0.0 0.0 8.0 vpcmpgtd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 13. 1 0.0 0.0 8.0 vpcmpgtq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 14. 1 0.0 0.0 8.0 vpcmpgtw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 15. 1 0.0 0.0 8.0 vpcmpgtb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 16. 1 0.0 0.0 7.0 vpcmpgtd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 17. 1 0.0 0.0 7.0 vpcmpgtq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 18. 1 0.0 0.0 7.0 vpcmpgtw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 19. 1 7.0 0.0 0.0 psubb %mm2, %mm2
+# CHECK-NEXT: 20. 1 9.0 0.0 0.0 psubd %mm2, %mm2
+# CHECK-NEXT: 21. 1 12.0 0.0 0.0 psubq %mm2, %mm2
+# CHECK-NEXT: 22. 1 15.0 0.0 0.0 psubw %mm2, %mm2
+# CHECK-NEXT: 23. 1 0.0 0.0 18.0 psubb %xmm2, %xmm2
+# CHECK-NEXT: 24. 1 0.0 0.0 17.0 psubd %xmm2, %xmm2
+# CHECK-NEXT: 25. 1 0.0 0.0 17.0 psubq %xmm2, %xmm2
+# CHECK-NEXT: 26. 1 0.0 0.0 17.0 psubw %xmm2, %xmm2
+# CHECK-NEXT: 27. 1 0.0 0.0 17.0 vpsubb %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 28. 1 0.0 0.0 16.0 vpsubd %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 29. 1 0.0 0.0 16.0 vpsubq %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 30. 1 0.0 0.0 16.0 vpsubw %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 31. 1 0.0 0.0 16.0 vpsubb %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 32. 1 0.0 0.0 15.0 vpsubd %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 33. 1 0.0 0.0 15.0 vpsubq %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 34. 1 0.0 0.0 15.0 vpsubw %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 35. 1 1.0 1.0 13.0 andnps %xmm0, %xmm0
+# CHECK-NEXT: 36. 1 1.0 1.0 12.0 andnpd %xmm1, %xmm1
+# CHECK-NEXT: 37. 1 2.0 2.0 11.0 vandnps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: 38. 1 3.0 1.0 10.0 vandnpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: 39. 1 14.0 0.0 0.0 pandn %mm2, %mm2
+# CHECK-NEXT: 40. 1 2.0 0.0 11.0 pandn %xmm2, %xmm2
+# CHECK-NEXT: 41. 1 1.0 1.0 12.0 vpandn %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 42. 1 3.0 0.0 10.0 vandnps %xmm2, %xmm2, %xmm5
+# CHECK-NEXT: 43. 1 4.0 1.0 9.0 vandnpd %xmm1, %xmm1, %xmm5
+# CHECK-NEXT: 44. 1 1.0 0.0 11.0 vpandn %xmm3, %xmm3, %xmm5
+# CHECK-NEXT: 45. 1 0.0 0.0 13.0 xorps %xmm0, %xmm0
+# CHECK-NEXT: 46. 1 2.0 0.0 11.0 xorpd %xmm1, %xmm1
+# CHECK-NEXT: 47. 1 2.0 0.0 11.0 vxorps %xmm2, %xmm2, %xmm2
+# CHECK-NEXT: 48. 1 1.0 0.0 11.0 vxorpd %xmm1, %xmm1, %xmm1
+# CHECK-NEXT: 49. 1 12.0 0.0 0.0 pxor %mm2, %mm2
+# CHECK-NEXT: 50. 1 1.0 0.0 12.0 pxor %xmm2, %xmm2
+# CHECK-NEXT: 51. 1 0.0 0.0 13.0 vpxor %xmm3, %xmm3, %xmm3
+# CHECK-NEXT: 52. 1 0.0 0.0 12.0 vxorps %xmm4, %xmm4, %xmm5
+# CHECK-NEXT: 53. 1 0.0 0.0 12.0 vxorpd %xmm1, %xmm1, %xmm3
+# CHECK-NEXT: 54. 1 0.0 0.0 12.0 vpxor %xmm3, %xmm3, %xmm5
More information about the llvm-commits
mailing list