This is an archive of the discontinued LLVM Phabricator instance.

Differential D52347

[X86][BtVer2] Fix latency and resource cycles of AVX 256-bit zero-idioms.
ClosedPublic

Authored by andreadb on Sep 21 2018, 2:55 AM.

Details

Reviewers
RKSimon
spatel
craig.topper
mattd
courbet
Commits
rG4cd5cf9fc8ef: [X86][BtVer2] Fix latency and resource cycles of AVX 256-bit zero-idioms.
rL342728: [X86][BtVer2] Fix latency and resource cycles of AVX 256-bit zero-idioms.
Summary

This patch introduces a SchedWriteVariant to describe zero-idiom VXORP(S|D)Yrr and VANDNP(S|D)Yrr.

This is a follow-up of r342555.

On Jaguar, a VXORPSYrr is 2 macro opcodes. Only one opcode is eliminated at register-renaming stage. The other opcode has to be executed to set the upper half of the destination YMM.
Same for VANDNP(S|D)Yrr.

Diff Detail

Repository
rL LLVM

Event Timeline

andreadb created this revision.Sep 21 2018, 2:55 AM
Herald added a subscriber: gbedwell. · View Herald TranscriptSep 21 2018, 2:55 AM
lebedev.ri added a subscriber: lebedev.ri.Sep 21 2018, 3:01 AM
lebedev.ri added inline comments.
test/CodeGen/X86/avx-schedule.ll
5508 ↗(On Diff #166424)

There is no way to achieve this without inline asm?
When committing, please commit the baseline first.

RKSimon accepted this revision.Sep 21 2018, 3:13 AM

LGTM - as @lebedev.ri suggested please pre-commit the avx-schedule.ll baseline

This revision is now accepted and ready to land.Sep 21 2018, 3:13 AM
andreadb added inline comments.Sep 21 2018, 4:34 AM
test/CodeGen/X86/avx-schedule.ll
5508 ↗(On Diff #166424)

Not that I know of. In this case, I am pretty sure that there is no other way.

I will add the test in a separate commit.

Thanks for the review!

Closed by commit rL342728: [X86][BtVer2] Fix latency and resource cycles of AVX 256-bit zero-idioms. (authored by adibiagio). · Explain WhySep 21 2018, 5:44 AM
This revision was automatically updated to reflect the committed changes.

Revision Contents

PathSize
llvm/
trunk/
lib/
Target/
X86/
11 lines
test/
CodeGen/
X86/
8 lines
tools/
llvm-mca/
X86/
BtVer2/
84 lines

Diff 166463

llvm/trunk/lib/Target/X86/X86ScheduleBtVer2.td

Show First 20 Lines • Show All 589 Lines • ▼ Show 20 Lines
/////////////////////////////////////////////////////////////////////////////// ///////////////////////////////////////////////////////////////////////////////
// SchedWriteVariant definitions. // SchedWriteVariant definitions.
/////////////////////////////////////////////////////////////////////////////// ///////////////////////////////////////////////////////////////////////////////
def JWriteZeroLatency : SchedWriteRes<[]> { def JWriteZeroLatency : SchedWriteRes<[]> {
let Latency = 0; let Latency = 0;
} }
def JWriteZeroIdiomYmm : SchedWriteRes<[JFPU01, JFPX]> {
let NumMicroOps = 2;
}
// Certain instructions that use the same register for both source // Certain instructions that use the same register for both source
// operands do not have a real dependency on the previous contents of the // operands do not have a real dependency on the previous contents of the
// register, and thus, do not have to wait before completing. They can be // register, and thus, do not have to wait before completing. They can be
// optimized out at register renaming stage. // optimized out at register renaming stage.
// Reference: Section 10.8 of the "Software Optimization Guide for AMD Family // Reference: Section 10.8 of the "Software Optimization Guide for AMD Family
// 15h Processors". // 15h Processors".
// Reference: Agner's Fog "The microarchitecture of Intel, AMD and VIA CPUs", // Reference: Agner's Fog "The microarchitecture of Intel, AMD and VIA CPUs",
// Section 21.8 [Dependency-breaking instructions]. // Section 21.8 [Dependency-breaking instructions].
def JWriteZeroIdiom : SchedWriteVariant<[ def JWriteZeroIdiom : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>, SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteALU]> SchedVar<NoSchedPred, [WriteALU]>
]>; ]>;
def : InstRW<[JWriteZeroIdiom], (instrs SUB32rr, SUB64rr, def : InstRW<[JWriteZeroIdiom], (instrs SUB32rr, SUB64rr,
XOR32rr, XOR64rr)>; XOR32rr, XOR64rr)>;
def JWriteFZeroIdiom : SchedWriteVariant<[ def JWriteFZeroIdiom : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>, SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteFLogic]> SchedVar<NoSchedPred, [WriteFLogic]>
]>; ]>;
def : InstRW<[JWriteFZeroIdiom], (instrs XORPSrr, VXORPSrr, XORPDrr, VXORPDrr, def : InstRW<[JWriteFZeroIdiom], (instrs XORPSrr, VXORPSrr, XORPDrr, VXORPDrr,
ANDNPSrr, VANDNPSrr, ANDNPSrr, VANDNPSrr,
ANDNPDrr, VANDNPDrr)>; ANDNPDrr, VANDNPDrr)>;
def JWriteFZeroIdiomY : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroIdiomYmm]>,
SchedVar<NoSchedPred, [WriteFLogicY]>
]>;
def : InstRW<[JWriteFZeroIdiomY], (instrs VXORPSYrr, VXORPDYrr,
VANDNPSYrr, VANDNPDYrr)>;
def JWriteVZeroIdiomLogic : SchedWriteVariant<[ def JWriteVZeroIdiomLogic : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>, SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteVecLogic]> SchedVar<NoSchedPred, [WriteVecLogic]>
]>; ]>;
def : InstRW<[JWriteVZeroIdiomLogic], (instrs MMX_PXORirr, MMX_PANDNirr)>; def : InstRW<[JWriteVZeroIdiomLogic], (instrs MMX_PXORirr, MMX_PANDNirr)>;
def JWriteVZeroIdiomLogicX : SchedWriteVariant<[ def JWriteVZeroIdiomLogicX : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>, SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [JWriteZeroLatency]>,
▲ Show 20 Lines • Show All 123 Lines • Show Last 20 Lines

llvm/trunk/test/CodeGen/X86/avx-schedule.ll

Show First 20 Lines • Show All 5,483 Lines • ▼ Show 20 Lines
; SKX-NEXT: vandnps %ymm2, %ymm2, %ymm2 # sched: [1:0.33] ; SKX-NEXT: vandnps %ymm2, %ymm2, %ymm2 # sched: [1:0.33]
; SKX-NEXT: vandnpd %ymm3, %ymm3, %ymm3 # sched: [1:0.33] ; SKX-NEXT: vandnpd %ymm3, %ymm3, %ymm3 # sched: [1:0.33]
; SKX-NEXT: #NO_APP ; SKX-NEXT: #NO_APP
; SKX-NEXT: retq # sched: [7:1.00] ; SKX-NEXT: retq # sched: [7:1.00]
; ;
; BTVER2-LABEL: test_avx256_zero_idioms: ; BTVER2-LABEL: test_avx256_zero_idioms:
; BTVER2: # %bb.0: ; BTVER2: # %bb.0:
; BTVER2-NEXT: #APP ; BTVER2-NEXT: #APP
; BTVER2-NEXT: vxorps %ymm0, %ymm0, %ymm0 # sched: [1:1.00] ; BTVER2-NEXT: vxorps %ymm0, %ymm0, %ymm0 # sched: [1:0.50]
; BTVER2-NEXT: vxorpd %ymm1, %ymm1, %ymm1 # sched: [1:1.00] ; BTVER2-NEXT: vxorpd %ymm1, %ymm1, %ymm1 # sched: [1:0.50]
; BTVER2-NEXT: vandnps %ymm2, %ymm2, %ymm2 # sched: [1:1.00] ; BTVER2-NEXT: vandnps %ymm2, %ymm2, %ymm2 # sched: [1:0.50]
; BTVER2-NEXT: vandnpd %ymm3, %ymm3, %ymm3 # sched: [1:1.00] ; BTVER2-NEXT: vandnpd %ymm3, %ymm3, %ymm3 # sched: [1:0.50]
; BTVER2-NEXT: #NO_APP ; BTVER2-NEXT: #NO_APP
; BTVER2-NEXT: retq # sched: [4:1.00] ; BTVER2-NEXT: retq # sched: [4:1.00]
; ;
; ZNVER1-LABEL: test_avx256_zero_idioms: ; ZNVER1-LABEL: test_avx256_zero_idioms:
; ZNVER1: # %bb.0: ; ZNVER1: # %bb.0:
; ZNVER1-NEXT: #APP ; ZNVER1-NEXT: #APP
; ZNVER1-NEXT: vxorps %ymm0, %ymm0, %ymm0 # sched: [1:0.25] ; ZNVER1-NEXT: vxorps %ymm0, %ymm0, %ymm0 # sched: [1:0.25]
; ZNVER1-NEXT: vxorpd %ymm1, %ymm1, %ymm1 # sched: [1:0.25] ; ZNVER1-NEXT: vxorpd %ymm1, %ymm1, %ymm1 # sched: [1:0.25]
Show All 10 Lines

llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s

Show All 29 Lines
vaddps %ymm0, %ymm1, %ymm2 vaddps %ymm0, %ymm1, %ymm2
vandnps %ymm2, %ymm2, %ymm3 vandnps %ymm2, %ymm2, %ymm3
# LLVM-MCA-END # LLVM-MCA-END
# CHECK: [0] Code Region - ZERO-IDIOM-1 # CHECK: [0] Code Region - ZERO-IDIOM-1
# CHECK: Iterations: 100 # CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 300 # CHECK-NEXT: Instructions: 300
# CHECK-NEXT: Total Cycles: 306 # CHECK-NEXT: Total Cycles: 304
# CHECK-NEXT: Total uOps: 600 # CHECK-NEXT: Total uOps: 600
# CHECK: Dispatch Width: 2 # CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96 # CHECK-NEXT: uOps Per Cycle: 1.97
# CHECK-NEXT: IPC: 0.98 # CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 3.0 # CHECK-NEXT: Block RThroughput: 3.0
# CHECK: Instruction Info: # CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps # CHECK-NEXT: [1]: #uOps
# CHECK-NEXT: [2]: Latency # CHECK-NEXT: [2]: Latency
# CHECK-NEXT: [3]: RThroughput # CHECK-NEXT: [3]: RThroughput
# CHECK-NEXT: [4]: MayLoad # CHECK-NEXT: [4]: MayLoad
# CHECK-NEXT: [5]: MayStore # CHECK-NEXT: [5]: MayStore
# CHECK-NEXT: [6]: HasSideEffects (U) # CHECK-NEXT: [6]: HasSideEffects (U)
# CHECK: [1] [2] [3] [4] [5] [6] Instructions: # CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm0, %ymm1 # CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm0, %ymm1
# CHECK-NEXT: 2 1 1.00 vxorps %ymm1, %ymm1, %ymm1 # CHECK-NEXT: 2 1 0.50 vxorps %ymm1, %ymm1, %ymm1
# CHECK-NEXT: 2 1 1.00 vblendps $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: 2 1 1.00 vblendps $2, %ymm1, %ymm2, %ymm3
# CHECK: Resources: # CHECK: Resources:
# CHECK-NEXT: [0] - JALU0 # CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1 # CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv # CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA # CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM # CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0 # CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1 # CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU # CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul # CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU # CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC # CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0 # CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1 # CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL # CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration: # CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - 3.00 3.00 3.00 3.00 - - - - - - - # CHECK-NEXT: - - - 3.00 2.00 3.00 2.00 - - - - - - -
# CHECK: Resource pressure by instruction: # CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm0, %ymm1 # CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm0, %ymm1
# CHECK-NEXT: - - - - 2.00 - 2.00 - - - - - - - vxorps %ymm1, %ymm1, %ymm1 # CHECK-NEXT: - - - - 1.00 - 1.00 - - - - - - - vxorps %ymm1, %ymm1, %ymm1
# CHECK-NEXT: - - - 1.00 1.00 1.00 1.00 - - - - - - - vblendps $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: - - - 1.00 1.00 1.00 1.00 - - - - - - - vblendps $2, %ymm1, %ymm2, %ymm3
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: 012 # CHECK-NEXT: 0123
# CHECK-NEXT: Index 0123456789 # CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeER . . vaddps %ymm0, %ymm0, %ymm1 # CHECK: [0,0] DeeeER . . vaddps %ymm0, %ymm0, %ymm1
# CHECK-NEXT: [0,1] .DeE-R . . vxorps %ymm1, %ymm1, %ymm1 # CHECK-NEXT: [0,1] .DeE-R . . vxorps %ymm1, %ymm1, %ymm1
# CHECK-NEXT: [0,2] . DeE-R . . vblendps $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: [0,2] . DeE-R . . vblendps $2, %ymm1, %ymm2, %ymm3
# CHECK-NEXT: [1,0] . D=eeeER. . vaddps %ymm0, %ymm0, %ymm1 # CHECK-NEXT: [1,0] . DeeeER . . vaddps %ymm0, %ymm0, %ymm1
# CHECK-NEXT: [1,1] . DeE--R. . vxorps %ymm1, %ymm1, %ymm1 # CHECK-NEXT: [1,1] . DeE-R . . vxorps %ymm1, %ymm1, %ymm1
# CHECK-NEXT: [1,2] . D=eE-R . vblendps $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: [1,2] . DeE-R. . vblendps $2, %ymm1, %ymm2, %ymm3
# CHECK-NEXT: [2,0] . .DeeeER. vaddps %ymm0, %ymm0, %ymm1 # CHECK-NEXT: [2,0] . .D=eeeER. vaddps %ymm0, %ymm0, %ymm1
# CHECK-NEXT: [2,1] . . D=eER. vxorps %ymm1, %ymm1, %ymm1 # CHECK-NEXT: [2,1] . . DeE--R. vxorps %ymm1, %ymm1, %ymm1
# CHECK-NEXT: [2,2] . . D=eER vblendps $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: [2,2] . . DeE--R vblendps $2, %ymm1, %ymm2, %ymm3
# CHECK: Average Wait times (based on the timeline view): # CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions # CHECK-NEXT: [0]: Executions
# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue # 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: [2]: Average time spent waiting in a scheduler's queue while ready
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
# CHECK: [0] [1] [2] [3] # CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 3 1.3 1.3 0.0 vaddps %ymm0, %ymm0, %ymm1 # CHECK-NEXT: 0. 3 1.3 1.3 0.0 vaddps %ymm0, %ymm0, %ymm1
# CHECK-NEXT: 1. 3 1.3 1.3 1.0 vxorps %ymm1, %ymm1, %ymm1 # CHECK-NEXT: 1. 3 1.0 1.0 1.3 vxorps %ymm1, %ymm1, %ymm1
# CHECK-NEXT: 2. 3 1.7 0.3 0.7 vblendps $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: 2. 3 1.0 0.0 1.3 vblendps $2, %ymm1, %ymm2, %ymm3
# CHECK: [1] Code Region - ZERO-IDIOM-2 # CHECK: [1] Code Region - ZERO-IDIOM-2
# CHECK: Iterations: 100 # CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 300 # CHECK-NEXT: Instructions: 300
# CHECK-NEXT: Total Cycles: 306 # CHECK-NEXT: Total Cycles: 304
# CHECK-NEXT: Total uOps: 600 # CHECK-NEXT: Total uOps: 600
# CHECK: Dispatch Width: 2 # CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96 # CHECK-NEXT: uOps Per Cycle: 1.97
# CHECK-NEXT: IPC: 0.98 # CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 3.0 # CHECK-NEXT: Block RThroughput: 3.0
# CHECK: Instruction Info: # CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps # CHECK-NEXT: [1]: #uOps
# CHECK-NEXT: [2]: Latency # CHECK-NEXT: [2]: Latency
# CHECK-NEXT: [3]: RThroughput # CHECK-NEXT: [3]: RThroughput
# CHECK-NEXT: [4]: MayLoad # CHECK-NEXT: [4]: MayLoad
# CHECK-NEXT: [5]: MayStore # CHECK-NEXT: [5]: MayStore
# CHECK-NEXT: [6]: HasSideEffects (U) # CHECK-NEXT: [6]: HasSideEffects (U)
# CHECK: [1] [2] [3] [4] [5] [6] Instructions: # CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 2 3 2.00 vaddpd %ymm0, %ymm0, %ymm1 # CHECK-NEXT: 2 3 2.00 vaddpd %ymm0, %ymm0, %ymm1
# CHECK-NEXT: 2 1 1.00 vxorpd %ymm1, %ymm1, %ymm1 # CHECK-NEXT: 2 1 0.50 vxorpd %ymm1, %ymm1, %ymm1
# CHECK-NEXT: 2 1 1.00 vblendpd $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: 2 1 1.00 vblendpd $2, %ymm1, %ymm2, %ymm3
# CHECK: Resources: # CHECK: Resources:
# CHECK-NEXT: [0] - JALU0 # CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1 # CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv # CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA # CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM # CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0 # CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1 # CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU # CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul # CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU # CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC # CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0 # CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1 # CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL # CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration: # CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - 3.00 3.00 3.00 3.00 - - - - - - - # CHECK-NEXT: - - - 3.00 2.00 3.00 2.00 - - - - - - -
# CHECK: Resource pressure by instruction: # CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddpd %ymm0, %ymm0, %ymm1 # CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddpd %ymm0, %ymm0, %ymm1
# CHECK-NEXT: - - - - 2.00 - 2.00 - - - - - - - vxorpd %ymm1, %ymm1, %ymm1 # CHECK-NEXT: - - - - 1.00 - 1.00 - - - - - - - vxorpd %ymm1, %ymm1, %ymm1
# CHECK-NEXT: - - - 1.00 1.00 1.00 1.00 - - - - - - - vblendpd $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: - - - 1.00 1.00 1.00 1.00 - - - - - - - vblendpd $2, %ymm1, %ymm2, %ymm3
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: 012 # CHECK-NEXT: 0123
# CHECK-NEXT: Index 0123456789 # CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeER . . vaddpd %ymm0, %ymm0, %ymm1 # CHECK: [0,0] DeeeER . . vaddpd %ymm0, %ymm0, %ymm1
# CHECK-NEXT: [0,1] .DeE-R . . vxorpd %ymm1, %ymm1, %ymm1 # CHECK-NEXT: [0,1] .DeE-R . . vxorpd %ymm1, %ymm1, %ymm1
# CHECK-NEXT: [0,2] . DeE-R . . vblendpd $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: [0,2] . DeE-R . . vblendpd $2, %ymm1, %ymm2, %ymm3
# CHECK-NEXT: [1,0] . D=eeeER. . vaddpd %ymm0, %ymm0, %ymm1 # CHECK-NEXT: [1,0] . DeeeER . . vaddpd %ymm0, %ymm0, %ymm1
# CHECK-NEXT: [1,1] . DeE--R. . vxorpd %ymm1, %ymm1, %ymm1 # CHECK-NEXT: [1,1] . DeE-R . . vxorpd %ymm1, %ymm1, %ymm1
# CHECK-NEXT: [1,2] . D=eE-R . vblendpd $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: [1,2] . DeE-R. . vblendpd $2, %ymm1, %ymm2, %ymm3
# CHECK-NEXT: [2,0] . .DeeeER. vaddpd %ymm0, %ymm0, %ymm1 # CHECK-NEXT: [2,0] . .D=eeeER. vaddpd %ymm0, %ymm0, %ymm1
# CHECK-NEXT: [2,1] . . D=eER. vxorpd %ymm1, %ymm1, %ymm1 # CHECK-NEXT: [2,1] . . DeE--R. vxorpd %ymm1, %ymm1, %ymm1
# CHECK-NEXT: [2,2] . . D=eER vblendpd $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: [2,2] . . DeE--R vblendpd $2, %ymm1, %ymm2, %ymm3
# CHECK: Average Wait times (based on the timeline view): # CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions # CHECK-NEXT: [0]: Executions
# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue # 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: [2]: Average time spent waiting in a scheduler's queue while ready
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage # CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
# CHECK: [0] [1] [2] [3] # CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 3 1.3 1.3 0.0 vaddpd %ymm0, %ymm0, %ymm1 # CHECK-NEXT: 0. 3 1.3 1.3 0.0 vaddpd %ymm0, %ymm0, %ymm1
# CHECK-NEXT: 1. 3 1.3 1.3 1.0 vxorpd %ymm1, %ymm1, %ymm1 # CHECK-NEXT: 1. 3 1.0 1.0 1.3 vxorpd %ymm1, %ymm1, %ymm1
# CHECK-NEXT: 2. 3 1.7 0.3 0.7 vblendpd $2, %ymm1, %ymm2, %ymm3 # CHECK-NEXT: 2. 3 1.0 0.0 1.3 vblendpd $2, %ymm1, %ymm2, %ymm3
# CHECK: [2] Code Region - ZERO-IDIOM-3 # CHECK: [2] Code Region - ZERO-IDIOM-3
# CHECK: Iterations: 100 # CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 200 # CHECK-NEXT: Instructions: 200
# CHECK-NEXT: Total Cycles: 204 # CHECK-NEXT: Total Cycles: 204
# CHECK-NEXT: Total uOps: 400 # CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 2 # CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96 # CHECK-NEXT: uOps Per Cycle: 1.96
# CHECK-NEXT: IPC: 0.98 # CHECK-NEXT: IPC: 0.98
# CHECK-NEXT: Block RThroughput: 2.0 # CHECK-NEXT: Block RThroughput: 2.0
# CHECK: Instruction Info: # CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps # CHECK-NEXT: [1]: #uOps
# CHECK-NEXT: [2]: Latency # CHECK-NEXT: [2]: Latency
# CHECK-NEXT: [3]: RThroughput # CHECK-NEXT: [3]: RThroughput
# CHECK-NEXT: [4]: MayLoad # CHECK-NEXT: [4]: MayLoad
# CHECK-NEXT: [5]: MayStore # CHECK-NEXT: [5]: MayStore
# CHECK-NEXT: [6]: HasSideEffects (U) # CHECK-NEXT: [6]: HasSideEffects (U)
# CHECK: [1] [2] [3] [4] [5] [6] Instructions: # CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: 2 1 1.00 vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: 2 1 0.50 vandnps %ymm2, %ymm2, %ymm3
# CHECK: Resources: # CHECK: Resources:
# CHECK-NEXT: [0] - JALU0 # CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1 # CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv # CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA # CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM # CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0 # CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1 # CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU # CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul # CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU # CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC # CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0 # CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1 # CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL # CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration: # CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - 2.00 2.00 2.00 2.00 - - - - - - - # CHECK-NEXT: - - - 2.00 1.00 2.00 1.00 - - - - - - -
# CHECK: Resource pressure by instruction: # CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: - - - - 2.00 - 2.00 - - - - - - - vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: - - - - 1.00 - 1.00 - - - - - - - vandnps %ymm2, %ymm2, %ymm3
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789 # CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeER . vaddps %ymm0, %ymm1, %ymm2 # CHECK: [0,0] DeeeER . vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: [0,1] .DeE-R . vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: [0,1] .DeE-R . vandnps %ymm2, %ymm2, %ymm3
# CHECK-NEXT: [1,0] . DeeeER . vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: [1,0] . DeeeER . vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: [1,1] . DeE-R . vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: [1,1] . DeE-R . vandnps %ymm2, %ymm2, %ymm3
Show All 27 Lines
# CHECK-NEXT: [2]: Latency # CHECK-NEXT: [2]: Latency
# CHECK-NEXT: [3]: RThroughput # CHECK-NEXT: [3]: RThroughput
# CHECK-NEXT: [4]: MayLoad # CHECK-NEXT: [4]: MayLoad
# CHECK-NEXT: [5]: MayStore # CHECK-NEXT: [5]: MayStore
# CHECK-NEXT: [6]: HasSideEffects (U) # CHECK-NEXT: [6]: HasSideEffects (U)
# CHECK: [1] [2] [3] [4] [5] [6] Instructions: # CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: 2 3 2.00 vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: 2 1 1.00 vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: 2 1 0.50 vandnps %ymm2, %ymm2, %ymm3
# CHECK: Resources: # CHECK: Resources:
# CHECK-NEXT: [0] - JALU0 # CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1 # CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv # CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA # CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM # CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0 # CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1 # CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU # CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul # CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU # CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC # CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0 # CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1 # CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL # CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration: # CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - 2.00 2.00 2.00 2.00 - - - - - - - # CHECK-NEXT: - - - 2.00 1.00 2.00 1.00 - - - - - - -
# CHECK: Resource pressure by instruction: # CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: # CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: - - - 2.00 - 2.00 - - - - - - - - vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: - - - - 2.00 - 2.00 - - - - - - - vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: - - - - 1.00 - 1.00 - - - - - - - vandnps %ymm2, %ymm2, %ymm3
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789 # CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeER . vaddps %ymm0, %ymm1, %ymm2 # CHECK: [0,0] DeeeER . vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: [0,1] .DeE-R . vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: [0,1] .DeE-R . vandnps %ymm2, %ymm2, %ymm3
# CHECK-NEXT: [1,0] . DeeeER . vaddps %ymm0, %ymm1, %ymm2 # CHECK-NEXT: [1,0] . DeeeER . vaddps %ymm0, %ymm1, %ymm2
# CHECK-NEXT: [1,1] . DeE-R . vandnps %ymm2, %ymm2, %ymm3 # CHECK-NEXT: [1,1] . DeE-R . vandnps %ymm2, %ymm2, %ymm3
Show All 12 Lines