1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00

[X86] AMD Zen 3: same-reg AVX YMM VPANDN is a zero-cycle(!) dep-breaking zero-idiom

As confirmed by exegesis measurements, and ref docs.
This commit is contained in:
Roman Lebedev 2021-05-14 16:20:25 +03:00
parent d334fd8763
commit 522d03976e
2 changed files with 23 additions and 22 deletions

View File

@ -1556,7 +1556,7 @@ def Zn3WriteVZeroIdiomLogicY : SchedWriteVariant<[
SchedVar<MCSchedPredicate<ZeroIdiomPredicate>, [Zn3WriteZeroLatency]>,
SchedVar<NoSchedPred, [WriteVecLogicY]>
]>;
def : InstRW<[Zn3WriteVZeroIdiomLogicY], (instrs VPXORYrr)>;
def : InstRW<[Zn3WriteVZeroIdiomLogicY], (instrs VPXORYrr, VPANDNYrr)>;
def : IsZeroIdiomFunction<[
// GPR Zero-idioms.
@ -1594,7 +1594,8 @@ def : IsZeroIdiomFunction<[
VANDNPSYrr, VANDNPDYrr,
// int variants.
VPXORYrr
VPXORYrr,
VPANDNYrr
], ZeroIdiomPredicate>,
]>;

View File

@ -490,13 +490,13 @@ vpandn %ymm1, %ymm0, %ymm0
# CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003
# CHECK-NEXT: Total Cycles: 3337
# CHECK-NEXT: Total uOps: 20000
# CHECK: Dispatch Width: 6
# CHECK-NEXT: uOps Per Cycle: 1.00
# CHECK-NEXT: IPC: 1.00
# CHECK-NEXT: Block RThroughput: 0.5
# CHECK-NEXT: uOps Per Cycle: 5.99
# CHECK-NEXT: IPC: 5.99
# CHECK-NEXT: Block RThroughput: 0.3
# CHECK: Instruction Info:
# CHECK-NEXT: [1]: #uOps
@ -507,17 +507,17 @@ vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [6]: HasSideEffects (U)
# CHECK: [1] [2] [3] [4] [5] [6] Instructions:
# CHECK-NEXT: 1 1 0.25 vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1 0 0.17 vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpandn %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000
# CHECK-NEXT: Max number of mappings used: 66
# CHECK-NEXT: Total number of mappings created: 10000
# CHECK-NEXT: Max number of mappings used: 9
# CHECK: * Register File #1 -- Zn3FpPRF:
# CHECK-NEXT: Number of physical registers: 160
# CHECK-NEXT: Total number of mappings created: 20000
# CHECK-NEXT: Max number of mappings used: 66
# CHECK-NEXT: Total number of mappings created: 10000
# CHECK-NEXT: Max number of mappings used: 9
# CHECK: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192
@ -551,20 +551,20 @@ vpandn %ymm1, %ymm0, %ymm0
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
# CHECK-NEXT: - - - - - - - - 0.50 0.50 0.50 0.50 - - - - - - - - - - -
# CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12.0] [12.1] [13] [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
# CHECK-NEXT: - - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - - - - - - - - - - - - - - - - vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - 0.25 0.25 0.25 0.25 - - - - - - - - - - - vpandn %ymm1, %ymm0, %ymm0
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK-NEXT: Index 0123
# CHECK: [0,0] DeER .. vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpandn %ymm1, %ymm0, %ymm0
# CHECK: [0,0] DR . vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] DeER vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D--R vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] DeER vpandn %ymm1, %ymm0, %ymm0
# CHECK: Average Wait times (based on the timeline view):
# CHECK-NEXT: [0]: Executions
@ -573,6 +573,6 @@ vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
# CHECK: [0] [1] [2] [3]
# CHECK-NEXT: 0. 2 2.0 0.5 0.0 vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
# CHECK-NEXT: 0. 2 0.0 0.0 1.0 vpandn %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 1.0 1.0 0.0 vpandn %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 0.5 0.5 0.5 <total>