maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

The patch updates sched numbers for YMM AVX instrs such as VMOVx, VORx, VXOR, VPERMILx, VBROADCASTx, etc. 

PR32857 should be closed.
Differential Revision: https://reviews.llvm.org/D39227

llvm-svn: 317196
This commit is contained in:
Andrew V. Tischenko 2017-11-02 10:33:41 +00:00
parent 8b4a9fa0b6
commit 3c8bf5ec37
4 changed files with 129 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

93
llvm/lib/Target/X86/X86ScheduleBtVer2.td
View File

@ -573,6 +573,99 @@ def WriteVCVTPDYLd: SchedWriteRes<[JLAGU, JSTC, JFPU01]> {
def : InstRW<[WriteVCVTPDYLd, ReadAfterLd], (instregex "VCVTPD2(DQ|PS)Yrm")>;
def : InstRW<[WriteVCVTPDYLd, ReadAfterLd], (instregex "VCVTTPD2DQYrm")>;
def WriteVBlendVPY: SchedWriteRes<[JFPU01]> {
let Latency = 3;
let ResourceCycles = [6];
}
def : InstRW<[WriteVBlendVPY], (instregex "VBLENDVP(S|D)Yrr", "VPERMILP(D|S)Yrr")>;
def WriteVBlendVPYLd: SchedWriteRes<[JLAGU, JFPU01]> {
let Latency = 8;
let ResourceCycles = [1, 6];
}
def : InstRW<[WriteVBlendVPYLd, ReadAfterLd], (instregex "VBLENDVP(S|D)Yrm")>;
def WriteVBROADCASTYLd: SchedWriteRes<[JLAGU, JFPU01]> {
let Latency = 6;
let ResourceCycles = [1, 4];
}
def : InstRW<[WriteVBROADCASTYLd, ReadAfterLd], (instregex "VBROADCASTS(S|D)Yrm")>;
def WriteFPAY22: SchedWriteRes<[JFPU0]> {
let Latency = 2;
let ResourceCycles = [2];
}
def : InstRW<[WriteFPAY22], (instregex "VCMPP(S|D)Yrri", "VM(AX|IN)P(D|S)Yrr")>;
def WriteFPAY22Ld: SchedWriteRes<[JLAGU, JFPU0]> {
let Latency = 7;
let ResourceCycles = [1, 2];
}
def : InstRW<[WriteFPAY22Ld, ReadAfterLd], (instregex "VCMPP(S|D)Yrmi", "VM(AX|IN)P(D|S)Yrm")>;
def WriteVHAddSubY: SchedWriteRes<[JFPU0]> {
let Latency = 3;
let ResourceCycles = [2];
}
def : InstRW<[WriteVHAddSubY], (instregex "VH(ADD|SUB)P(D|S)Yrr")>;
def WriteVHAddSubYLd: SchedWriteRes<[JLAGU, JFPU0]> {
let Latency = 8;
let ResourceCycles = [1, 2];
}
def : InstRW<[WriteVHAddSubYLd], (instregex "VH(ADD|SUB)P(D|S)Yrm")>;
def WriteVMaskMovLd: SchedWriteRes<[JLAGU,JFPU01]> {
let Latency = 6;
let ResourceCycles = [1, 2];
}
def : InstRW<[WriteVMaskMovLd], (instregex "VMASKMOVP(D|S)rm")>;
def WriteVMaskMovYLd: SchedWriteRes<[JLAGU,JFPU01]> {
let Latency = 6;
let ResourceCycles = [1, 4];
}
def : InstRW<[WriteVMaskMovYLd], (instregex "VMASKMOVP(D|S)Yrm")>;
def WriteVMaskMovSt: SchedWriteRes<[JFPU01,JSAGU]> {
let Latency = 6;
let ResourceCycles = [4, 1];
}
def : InstRW<[WriteVMaskMovSt], (instregex "VMASKMOVP(D|S)mr")>;
def WriteVMaskMovYSt: SchedWriteRes<[JFPU01,JSAGU]> {
let Latency = 6;
let ResourceCycles = [4, 1];
}
def : InstRW<[WriteVMaskMovYSt], (instregex "VMASKMOVP(D|S)Ymr")>;
// TODO: In fact we have latency '2+i'. The +i represents an additional 1 cycle transfer
// operation which moves the floating point result to the integer unit. During this
// additional cycle the floating point unit execution resources are not occupied
// and ALU0 in the integer unit is occupied instead.
def WriteVMOVMSK: SchedWriteRes<[JFPU0]> {
let Latency = 3;
}
def : InstRW<[WriteVMOVMSK], (instregex "VMOVMSKP(D|S)(Y)?rr")>;
// TODO: In fact we have latency '3+i'. The +i represents an additional 1 cycle transfer
// operation which moves the floating point result to the integer unit. During this
// additional cycle the floating point unit execution resources are not occupied
// and ALU0 in the integer unit is occupied instead.
def WriteVTESTY: SchedWriteRes<[JFPU01, JFPU0]> {
let Latency = 4;
let ResourceCycles = [4, 2];
}
def : InstRW<[WriteVTESTY], (instregex "VTESTP(S|D)Yrr")>;
def : InstRW<[WriteVTESTY], (instregex "VPTESTYrr")>;
def WriteVTESTYLd: SchedWriteRes<[JLAGU, JFPU01, JFPU0]> {
let Latency = 9;
let ResourceCycles = [1, 4, 2];
}
def : InstRW<[WriteVTESTYLd], (instregex "VTESTP(S|D)Yrm")>;
def : InstRW<[WriteVTESTYLd], (instregex "VPTESTYrm")>;
def WriteVSQRTYPD: SchedWriteRes<[JFPU1]> {
let Latency = 54;
let ResourceCycles = [54];

68
llvm/test/CodeGen/X86/avx-schedule.ll
View File

@ -655,8 +655,8 @@ define <4 x double> @test_blendvpd(<4 x double> %a0, <4 x double> %a1, <4 x doub
;
; BTVER2-LABEL: test_blendvpd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vblendvpd %ymm2, %ymm1, %ymm0, %ymm0 # sched: [2:1.00]
; BTVER2-NEXT: vblendvpd %ymm2, (%rdi), %ymm0, %ymm0 # sched: [7:1.00]
; BTVER2-NEXT: vblendvpd %ymm2, %ymm1, %ymm0, %ymm0 # sched: [3:3.00]
; BTVER2-NEXT: vblendvpd %ymm2, (%rdi), %ymm0, %ymm0 # sched: [8:3.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_blendvpd:
@ -710,8 +710,8 @@ define <8 x float> @test_blendvps(<8 x float> %a0, <8 x float> %a1, <8 x float>
;
; BTVER2-LABEL: test_blendvps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vblendvps %ymm2, %ymm1, %ymm0, %ymm0 # sched: [2:1.00]
; BTVER2-NEXT: vblendvps %ymm2, (%rdi), %ymm0, %ymm0 # sched: [7:1.00]
; BTVER2-NEXT: vblendvps %ymm2, %ymm1, %ymm0, %ymm0 # sched: [3:3.00]
; BTVER2-NEXT: vblendvps %ymm2, (%rdi), %ymm0, %ymm0 # sched: [8:3.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_blendvps:
@ -804,7 +804,7 @@ define <4 x double> @test_broadcastsd_ymm(double *%a0) {
;
; BTVER2-LABEL: test_broadcastsd_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: vbroadcastsd (%rdi), %ymm0 # sched: [6:1.00]
; BTVER2-NEXT: vbroadcastsd (%rdi), %ymm0 # sched: [6:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_broadcastsd_ymm:
@ -896,7 +896,7 @@ define <8 x float> @test_broadcastss_ymm(float *%a0) {
;
; BTVER2-LABEL: test_broadcastss_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: vbroadcastss (%rdi), %ymm0 # sched: [6:1.00]
; BTVER2-NEXT: vbroadcastss (%rdi), %ymm0 # sched: [6:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_broadcastss_ymm:
@ -956,8 +956,8 @@ define <4 x double> @test_cmppd(<4 x double> %a0, <4 x double> %a1, <4 x double>
;
; BTVER2-LABEL: test_cmppd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vcmpeqpd %ymm1, %ymm0, %ymm1 # sched: [3:1.00]
; BTVER2-NEXT: vcmpeqpd (%rdi), %ymm0, %ymm0 # sched: [8:1.00]
; BTVER2-NEXT: vcmpeqpd %ymm1, %ymm0, %ymm1 # sched: [2:2.00]
; BTVER2-NEXT: vcmpeqpd (%rdi), %ymm0, %ymm0 # sched: [7:2.00]
; BTVER2-NEXT: vorpd %ymm0, %ymm1, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -1024,8 +1024,8 @@ define <8 x float> @test_cmpps(<8 x float> %a0, <8 x float> %a1, <8 x float> *%a
;
; BTVER2-LABEL: test_cmpps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vcmpeqps %ymm1, %ymm0, %ymm1 # sched: [3:1.00]
; BTVER2-NEXT: vcmpeqps (%rdi), %ymm0, %ymm0 # sched: [8:1.00]
; BTVER2-NEXT: vcmpeqps %ymm1, %ymm0, %ymm1 # sched: [2:2.00]
; BTVER2-NEXT: vcmpeqps (%rdi), %ymm0, %ymm0 # sched: [7:2.00]
; BTVER2-NEXT: vorps %ymm0, %ymm1, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -2089,8 +2089,8 @@ define <2 x double> @test_maskmovpd(i8* %a0, <2 x i64> %a1, <2 x double> %a2) {
;
; BTVER2-LABEL: test_maskmovpd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmaskmovpd (%rdi), %xmm0, %xmm2
; BTVER2-NEXT: vmaskmovpd %xmm1, %xmm0, (%rdi)
; BTVER2-NEXT: vmaskmovpd (%rdi), %xmm0, %xmm2 # sched: [6:1.00]
; BTVER2-NEXT: vmaskmovpd %xmm1, %xmm0, (%rdi) # sched: [6:2.00]
; BTVER2-NEXT: vmovapd %xmm2, %xmm0 # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -2152,8 +2152,8 @@ define <4 x double> @test_maskmovpd_ymm(i8* %a0, <4 x i64> %a1, <4 x double> %a2
;
; BTVER2-LABEL: test_maskmovpd_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmaskmovpd (%rdi), %ymm0, %ymm2
; BTVER2-NEXT: vmaskmovpd %ymm1, %ymm0, (%rdi)
; BTVER2-NEXT: vmaskmovpd (%rdi), %ymm0, %ymm2 # sched: [6:2.00]
; BTVER2-NEXT: vmaskmovpd %ymm1, %ymm0, (%rdi) # sched: [6:2.00]
; BTVER2-NEXT: vmovapd %ymm2, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -2215,8 +2215,8 @@ define <4 x float> @test_maskmovps(i8* %a0, <4 x i32> %a1, <4 x float> %a2) {
;
; BTVER2-LABEL: test_maskmovps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmaskmovps (%rdi), %xmm0, %xmm2
; BTVER2-NEXT: vmaskmovps %xmm1, %xmm0, (%rdi)
; BTVER2-NEXT: vmaskmovps (%rdi), %xmm0, %xmm2 # sched: [6:1.00]
; BTVER2-NEXT: vmaskmovps %xmm1, %xmm0, (%rdi) # sched: [6:2.00]
; BTVER2-NEXT: vmovaps %xmm2, %xmm0 # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -2278,8 +2278,8 @@ define <8 x float> @test_maskmovps_ymm(i8* %a0, <8 x i32> %a1, <8 x float> %a2)
;
; BTVER2-LABEL: test_maskmovps_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmaskmovps (%rdi), %ymm0, %ymm2
; BTVER2-NEXT: vmaskmovps %ymm1, %ymm0, (%rdi)
; BTVER2-NEXT: vmaskmovps (%rdi), %ymm0, %ymm2 # sched: [6:2.00]
; BTVER2-NEXT: vmaskmovps %ymm1, %ymm0, (%rdi) # sched: [6:2.00]
; BTVER2-NEXT: vmovaps %ymm2, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -2335,8 +2335,8 @@ define <4 x double> @test_maxpd(<4 x double> %a0, <4 x double> %a1, <4 x double>
;
; BTVER2-LABEL: test_maxpd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmaxpd %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; BTVER2-NEXT: vmaxpd (%rdi), %ymm0, %ymm0 # sched: [8:1.00]
; BTVER2-NEXT: vmaxpd %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vmaxpd (%rdi), %ymm0, %ymm0 # sched: [7:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_maxpd:
@ -2390,8 +2390,8 @@ define <8 x float> @test_maxps(<8 x float> %a0, <8 x float> %a1, <8 x float> *%a
;
; BTVER2-LABEL: test_maxps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmaxps %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; BTVER2-NEXT: vmaxps (%rdi), %ymm0, %ymm0 # sched: [8:1.00]
; BTVER2-NEXT: vmaxps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vmaxps (%rdi), %ymm0, %ymm0 # sched: [7:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_maxps:
@ -2445,8 +2445,8 @@ define <4 x double> @test_minpd(<4 x double> %a0, <4 x double> %a1, <4 x double>
;
; BTVER2-LABEL: test_minpd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vminpd %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; BTVER2-NEXT: vminpd (%rdi), %ymm0, %ymm0 # sched: [8:1.00]
; BTVER2-NEXT: vminpd %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vminpd (%rdi), %ymm0, %ymm0 # sched: [7:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_minpd:
@ -2500,8 +2500,8 @@ define <8 x float> @test_minps(<8 x float> %a0, <8 x float> %a1, <8 x float> *%a
;
; BTVER2-LABEL: test_minps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vminps %ymm1, %ymm0, %ymm0 # sched: [3:1.00]
; BTVER2-NEXT: vminps (%rdi), %ymm0, %ymm0 # sched: [8:1.00]
; BTVER2-NEXT: vminps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vminps (%rdi), %ymm0, %ymm0 # sched: [7:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_minps:
@ -2742,7 +2742,7 @@ define i32 @test_movmskpd(<4 x double> %a0) {
;
; BTVER2-LABEL: test_movmskpd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovmskpd %ymm0, %eax # sched: [1:0.50]
; BTVER2-NEXT: vmovmskpd %ymm0, %eax # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_movmskpd:
@ -2794,7 +2794,7 @@ define i32 @test_movmskps(<8 x float> %a0) {
;
; BTVER2-LABEL: test_movmskps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovmskps %ymm0, %eax # sched: [1:0.50]
; BTVER2-NEXT: vmovmskps %ymm0, %eax # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_movmskps:
@ -3818,7 +3818,7 @@ define <4 x double> @test_permilvarpd_ymm(<4 x double> %a0, <4 x i64> %a1, <4 x
;
; BTVER2-LABEL: test_permilvarpd_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpermilpd %ymm1, %ymm0, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: vpermilpd %ymm1, %ymm0, %ymm0 # sched: [3:3.00]
; BTVER2-NEXT: vpermilpd (%rdi), %ymm0, %ymm0 # sched: [6:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -3928,7 +3928,7 @@ define <8 x float> @test_permilvarps_ymm(<8 x float> %a0, <8 x i32> %a1, <8 x i3
;
; BTVER2-LABEL: test_permilvarps_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: vpermilps %ymm1, %ymm0, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: vpermilps %ymm1, %ymm0, %ymm0 # sched: [3:3.00]
; BTVER2-NEXT: vpermilps (%rdi), %ymm0, %ymm0 # sched: [6:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -4697,9 +4697,9 @@ define i32 @test_testpd_ymm(<4 x double> %a0, <4 x double> %a1, <4 x double> *%a
; BTVER2-LABEL: test_testpd_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: xorl %eax, %eax # sched: [1:0.50]
; BTVER2-NEXT: vtestpd %ymm1, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: vtestpd %ymm1, %ymm0 # sched: [4:3.00]
; BTVER2-NEXT: setb %al # sched: [1:0.50]
; BTVER2-NEXT: vtestpd (%rdi), %ymm0 # sched: [6:1.00]
; BTVER2-NEXT: vtestpd (%rdi), %ymm0 # sched: [9:3.00]
; BTVER2-NEXT: adcl $0, %eax # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
@ -4864,9 +4864,9 @@ define i32 @test_testps_ymm(<8 x float> %a0, <8 x float> %a1, <8 x float> *%a2)
; BTVER2-LABEL: test_testps_ymm:
; BTVER2: # BB#0:
; BTVER2-NEXT: xorl %eax, %eax # sched: [1:0.50]
; BTVER2-NEXT: vtestps %ymm1, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: vtestps %ymm1, %ymm0 # sched: [4:3.00]
; BTVER2-NEXT: setb %al # sched: [1:0.50]
; BTVER2-NEXT: vtestps (%rdi), %ymm0 # sched: [6:1.00]
; BTVER2-NEXT: vtestps (%rdi), %ymm0 # sched: [9:3.00]
; BTVER2-NEXT: adcl $0, %eax # sched: [1:0.50]
; BTVER2-NEXT: retq # sched: [4:1.00]
;

2
llvm/test/CodeGen/X86/sse-schedule.ll
View File

@ -1942,7 +1942,7 @@ define i32 @test_movmskps(<4 x float> %a0) {
;
; BTVER2-LABEL: test_movmskps:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovmskps %xmm0, %eax # sched: [1:0.50]
; BTVER2-NEXT: vmovmskps %xmm0, %eax # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_movmskps:

2
llvm/test/CodeGen/X86/sse2-schedule.ll
View File

@ -3179,7 +3179,7 @@ define i32 @test_movmskpd(<2 x double> %a0) {
;
; BTVER2-LABEL: test_movmskpd:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovmskpd %xmm0, %eax # sched: [1:0.50]
; BTVER2-NEXT: vmovmskpd %xmm0, %eax # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; ZNVER1-LABEL: test_movmskpd: