RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
Code Issues Projects Releases Wiki Activity

[X86] AMD Zen 3: same-reg AVX YMM VPSUBS{B,W} is a 1-cycle(!) dep-breaking zero-idiom

Browse Source 
Not really mentioned in ref docs, but measures as such.
Yes, this one is also not zero-cycle.
This commit is contained in:
Roman Lebedev 2021-05-14 18:17:33 +03:00
parent 139c28fa45
commit 19263a16d8
2 changed files with 32 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lib/Target/X86/X86ScheduleZnver3.td
View File

@ -1615,7 +1615,8 @@ def : IsZeroIdiomFunction<[
// int variants. // int variants.
VPXORYrr, VPXORYrr,
VPANDNYrr, VPANDNYrr,
VPSUBBYrr, VPSUBWYrr, VPSUBDYrr, VPSUBQYrr VPSUBBYrr, VPSUBWYrr, VPSUBDYrr, VPSUBQYrr,
VPSUBSBYrr, VPSUBSWYrr
], ZeroIdiomPredicate>, ], ZeroIdiomPredicate>,
]>; ]>;

60
test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s
View File

@ -975,12 +975,12 @@ vpxor %ymm1, %ymm0, %ymm0
# CHECK: Iterations: 10000 # CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000 # CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003 # CHECK-NEXT: Total Cycles: 5004
# CHECK-NEXT: Total uOps: 20000 # CHECK-NEXT: Total uOps: 20000
# CHECK: Dispatch Width: 6 # CHECK: Dispatch Width: 6
# CHECK-NEXT: uOps Per Cycle: 1.00 # CHECK-NEXT: uOps Per Cycle: 4.00
# CHECK-NEXT: IPC: 1.00 # CHECK-NEXT: IPC: 4.00
# CHECK-NEXT: Block RThroughput: 0.5 # CHECK-NEXT: Block RThroughput: 0.5
# CHECK: Instruction Info: # CHECK: Instruction Info:
@ -996,13 +996,13 @@ vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: 1 1 0.25 vpxor %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics: # CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000 # CHECK-NEXT: Total number of mappings created: 10000
# CHECK-NEXT: Max number of mappings used: 66 # CHECK-NEXT: Max number of mappings used: 37
# CHECK: * Register File #1 -- Zn3FpPRF: # CHECK: * Register File #1 -- Zn3FpPRF:
# CHECK-NEXT: Number of physical registers: 160 # CHECK-NEXT: Number of physical registers: 160
# CHECK-NEXT: Total number of mappings created: 20000 # CHECK-NEXT: Total number of mappings created: 10000
# CHECK-NEXT: Max number of mappings used: 66 # CHECK-NEXT: Max number of mappings used: 37
# CHECK: * Register File #2 -- Zn3IntegerPRF: # CHECK: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192 # CHECK-NEXT: Number of physical registers: 192
@ -1044,12 +1044,12 @@ vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - - - 0.50 0.50 - - - - - - - - - - - vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: - - - - - - - - - - 0.50 0.50 - - - - - - - - - - - vpxor %ymm1, %ymm0, %ymm0
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: Index 0123456 # CHECK-NEXT: Index 01234
# CHECK: [0,0] DeER .. vpsubsb %ymm0, %ymm0, %ymm0 # CHECK: [0,0] DeER. vpsubsb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: [0,1] D=eER vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpsubsb %ymm0, %ymm0, %ymm0 # CHECK-NEXT: [1,0] DeE-R vpsubsb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: [1,1] D=eER vpxor %ymm1, %ymm0, %ymm0
# 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
@ -1058,20 +1058,20 @@ vpxor %ymm1, %ymm0, %ymm0
# 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. 2 2.0 0.5 0.0 vpsubsb %ymm0, %ymm0, %ymm0 # CHECK-NEXT: 0. 2 1.0 1.0 0.5 vpsubsb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: 1. 2 2.0 0.0 0.0 vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total> # CHECK-NEXT: 2 1.5 0.5 0.3 <total>
# CHECK: [11] Code Region # CHECK: [11] Code Region
# CHECK: Iterations: 10000 # CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000 # CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003 # CHECK-NEXT: Total Cycles: 5004
# CHECK-NEXT: Total uOps: 20000 # CHECK-NEXT: Total uOps: 20000
# CHECK: Dispatch Width: 6 # CHECK: Dispatch Width: 6
# CHECK-NEXT: uOps Per Cycle: 1.00 # CHECK-NEXT: uOps Per Cycle: 4.00
# CHECK-NEXT: IPC: 1.00 # CHECK-NEXT: IPC: 4.00
# CHECK-NEXT: Block RThroughput: 0.5 # CHECK-NEXT: Block RThroughput: 0.5
# CHECK: Instruction Info: # CHECK: Instruction Info:
@ -1087,13 +1087,13 @@ vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: 1 1 0.25 vpxor %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics: # CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000 # CHECK-NEXT: Total number of mappings created: 10000
# CHECK-NEXT: Max number of mappings used: 66 # CHECK-NEXT: Max number of mappings used: 37
# CHECK: * Register File #1 -- Zn3FpPRF: # CHECK: * Register File #1 -- Zn3FpPRF:
# CHECK-NEXT: Number of physical registers: 160 # CHECK-NEXT: Number of physical registers: 160
# CHECK-NEXT: Total number of mappings created: 20000 # CHECK-NEXT: Total number of mappings created: 10000
# CHECK-NEXT: Max number of mappings used: 66 # CHECK-NEXT: Max number of mappings used: 37
# CHECK: * Register File #2 -- Zn3IntegerPRF: # CHECK: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192 # CHECK-NEXT: Number of physical registers: 192
@ -1135,12 +1135,12 @@ vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - - - 0.50 0.50 - - - - - - - - - - - vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: - - - - - - - - - - 0.50 0.50 - - - - - - - - - - - vpxor %ymm1, %ymm0, %ymm0
# CHECK: Timeline view: # CHECK: Timeline view:
# CHECK-NEXT: Index 0123456 # CHECK-NEXT: Index 01234
# CHECK: [0,0] DeER .. vpsubsw %ymm0, %ymm0, %ymm0 # CHECK: [0,0] DeER. vpsubsw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: [0,1] D=eER vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpsubsw %ymm0, %ymm0, %ymm0 # CHECK-NEXT: [1,0] DeE-R vpsubsw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: [1,1] D=eER vpxor %ymm1, %ymm0, %ymm0
# 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
@ -1149,6 +1149,6 @@ vpxor %ymm1, %ymm0, %ymm0
# 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. 2 2.0 0.5 0.0 vpsubsw %ymm0, %ymm0, %ymm0 # CHECK-NEXT: 0. 2 1.0 1.0 0.5 vpsubsw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpxor %ymm1, %ymm0, %ymm0 # CHECK-NEXT: 1. 2 2.0 0.0 0.0 vpxor %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total> # CHECK-NEXT: 2 1.5 0.5 0.3 <total>