RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
Code Issues Projects Releases Wiki Activity

[NFC][X86][MCA] AMD Zen 3: add same-reg AVX YMM VPSUB{B,W,D,Q} tests

Browse Source
This commit is contained in:
Roman Lebedev 2021-05-14 17:08:45 +03:00
parent 7a8c45f4d0
commit 554780708a
1 changed files with 384 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

384
test/tools/llvm-mca/X86/Znver3/zero-idioms-avx-ymm.s
View File

@ -31,6 +31,26 @@ vpandn %ymm0, %ymm0, %ymm0
vpandn %ymm1, %ymm0, %ymm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpsubb %ymm0, %ymm0, %ymm0
vpsubb %ymm1, %ymm0, %ymm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpsubw %ymm0, %ymm0, %ymm0
vpsubw %ymm1, %ymm0, %ymm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpsubd %ymm0, %ymm0, %ymm0
vpsubd %ymm1, %ymm0, %ymm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpsubq %ymm0, %ymm0, %ymm0
vpsubq %ymm1, %ymm0, %ymm0
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 10000
@ -576,3 +596,367 @@ vpandn %ymm1, %ymm0, %ymm0
# 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>
# CHECK: [6] Code Region
# CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003
# 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: 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 1 0.25 vpsubb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpsubb %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000
# CHECK-NEXT: Max number of mappings used: 66
# 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: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192
# CHECK-NEXT: Total number of mappings created: 0
# CHECK-NEXT: Max number of mappings used: 0
# CHECK: Resources:
# CHECK-NEXT: [0] - Zn3AGU0
# CHECK-NEXT: [1] - Zn3AGU1
# CHECK-NEXT: [2] - Zn3AGU2
# CHECK-NEXT: [3] - Zn3ALU0
# CHECK-NEXT: [4] - Zn3ALU1
# CHECK-NEXT: [5] - Zn3ALU2
# CHECK-NEXT: [6] - Zn3ALU3
# CHECK-NEXT: [7] - Zn3BRU1
# CHECK-NEXT: [8] - Zn3FPP0
# CHECK-NEXT: [9] - Zn3FPP1
# CHECK-NEXT: [10] - Zn3FPP2
# CHECK-NEXT: [11] - Zn3FPP3
# CHECK-NEXT: [12.0] - Zn3FPP45
# CHECK-NEXT: [12.1] - Zn3FPP45
# CHECK-NEXT: [13] - Zn3FPSt
# CHECK-NEXT: [14.0] - Zn3LSU
# CHECK-NEXT: [14.1] - Zn3LSU
# CHECK-NEXT: [14.2] - Zn3LSU
# CHECK-NEXT: [15.0] - Zn3Load
# CHECK-NEXT: [15.1] - Zn3Load
# CHECK-NEXT: [15.2] - Zn3Load
# CHECK-NEXT: [16.0] - Zn3Store
# CHECK-NEXT: [16.1] - Zn3Store
# 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: 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 - - - - - - - - - - - vpsubb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - vpsubb %ymm1, %ymm0, %ymm0
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. vpsubb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpsubb %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpsubb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpsubb %ymm1, %ymm0, %ymm0
# 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. 2 2.0 0.5 0.0 vpsubb %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpsubb %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
# CHECK: [7] Code Region
# CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003
# 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: 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 1 0.25 vpsubw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpsubw %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000
# CHECK-NEXT: Max number of mappings used: 66
# 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: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192
# CHECK-NEXT: Total number of mappings created: 0
# CHECK-NEXT: Max number of mappings used: 0
# CHECK: Resources:
# CHECK-NEXT: [0] - Zn3AGU0
# CHECK-NEXT: [1] - Zn3AGU1
# CHECK-NEXT: [2] - Zn3AGU2
# CHECK-NEXT: [3] - Zn3ALU0
# CHECK-NEXT: [4] - Zn3ALU1
# CHECK-NEXT: [5] - Zn3ALU2
# CHECK-NEXT: [6] - Zn3ALU3
# CHECK-NEXT: [7] - Zn3BRU1
# CHECK-NEXT: [8] - Zn3FPP0
# CHECK-NEXT: [9] - Zn3FPP1
# CHECK-NEXT: [10] - Zn3FPP2
# CHECK-NEXT: [11] - Zn3FPP3
# CHECK-NEXT: [12.0] - Zn3FPP45
# CHECK-NEXT: [12.1] - Zn3FPP45
# CHECK-NEXT: [13] - Zn3FPSt
# CHECK-NEXT: [14.0] - Zn3LSU
# CHECK-NEXT: [14.1] - Zn3LSU
# CHECK-NEXT: [14.2] - Zn3LSU
# CHECK-NEXT: [15.0] - Zn3Load
# CHECK-NEXT: [15.1] - Zn3Load
# CHECK-NEXT: [15.2] - Zn3Load
# CHECK-NEXT: [16.0] - Zn3Store
# CHECK-NEXT: [16.1] - Zn3Store
# 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: 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 - - - - - - - - - - - vpsubw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - vpsubw %ymm1, %ymm0, %ymm0
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. vpsubw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpsubw %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpsubw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpsubw %ymm1, %ymm0, %ymm0
# 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. 2 2.0 0.5 0.0 vpsubw %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpsubw %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
# CHECK: [8] Code Region
# CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003
# 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: 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 1 0.25 vpsubd %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpsubd %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000
# CHECK-NEXT: Max number of mappings used: 66
# 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: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192
# CHECK-NEXT: Total number of mappings created: 0
# CHECK-NEXT: Max number of mappings used: 0
# CHECK: Resources:
# CHECK-NEXT: [0] - Zn3AGU0
# CHECK-NEXT: [1] - Zn3AGU1
# CHECK-NEXT: [2] - Zn3AGU2
# CHECK-NEXT: [3] - Zn3ALU0
# CHECK-NEXT: [4] - Zn3ALU1
# CHECK-NEXT: [5] - Zn3ALU2
# CHECK-NEXT: [6] - Zn3ALU3
# CHECK-NEXT: [7] - Zn3BRU1
# CHECK-NEXT: [8] - Zn3FPP0
# CHECK-NEXT: [9] - Zn3FPP1
# CHECK-NEXT: [10] - Zn3FPP2
# CHECK-NEXT: [11] - Zn3FPP3
# CHECK-NEXT: [12.0] - Zn3FPP45
# CHECK-NEXT: [12.1] - Zn3FPP45
# CHECK-NEXT: [13] - Zn3FPSt
# CHECK-NEXT: [14.0] - Zn3LSU
# CHECK-NEXT: [14.1] - Zn3LSU
# CHECK-NEXT: [14.2] - Zn3LSU
# CHECK-NEXT: [15.0] - Zn3Load
# CHECK-NEXT: [15.1] - Zn3Load
# CHECK-NEXT: [15.2] - Zn3Load
# CHECK-NEXT: [16.0] - Zn3Store
# CHECK-NEXT: [16.1] - Zn3Store
# 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: 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 - - - - - - - - - - - vpsubd %ymm0, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - vpsubd %ymm1, %ymm0, %ymm0
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. vpsubd %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpsubd %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpsubd %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpsubd %ymm1, %ymm0, %ymm0
# 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. 2 2.0 0.5 0.0 vpsubd %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpsubd %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
# CHECK: [9] Code Region
# CHECK: Iterations: 10000
# CHECK-NEXT: Instructions: 20000
# CHECK-NEXT: Total Cycles: 20003
# 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: 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 1 0.25 vpsubq %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1 1 0.25 vpsubq %ymm1, %ymm0, %ymm0
# CHECK: Register File statistics:
# CHECK-NEXT: Total number of mappings created: 20000
# CHECK-NEXT: Max number of mappings used: 66
# 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: * Register File #2 -- Zn3IntegerPRF:
# CHECK-NEXT: Number of physical registers: 192
# CHECK-NEXT: Total number of mappings created: 0
# CHECK-NEXT: Max number of mappings used: 0
# CHECK: Resources:
# CHECK-NEXT: [0] - Zn3AGU0
# CHECK-NEXT: [1] - Zn3AGU1
# CHECK-NEXT: [2] - Zn3AGU2
# CHECK-NEXT: [3] - Zn3ALU0
# CHECK-NEXT: [4] - Zn3ALU1
# CHECK-NEXT: [5] - Zn3ALU2
# CHECK-NEXT: [6] - Zn3ALU3
# CHECK-NEXT: [7] - Zn3BRU1
# CHECK-NEXT: [8] - Zn3FPP0
# CHECK-NEXT: [9] - Zn3FPP1
# CHECK-NEXT: [10] - Zn3FPP2
# CHECK-NEXT: [11] - Zn3FPP3
# CHECK-NEXT: [12.0] - Zn3FPP45
# CHECK-NEXT: [12.1] - Zn3FPP45
# CHECK-NEXT: [13] - Zn3FPSt
# CHECK-NEXT: [14.0] - Zn3LSU
# CHECK-NEXT: [14.1] - Zn3LSU
# CHECK-NEXT: [14.2] - Zn3LSU
# CHECK-NEXT: [15.0] - Zn3Load
# CHECK-NEXT: [15.1] - Zn3Load
# CHECK-NEXT: [15.2] - Zn3Load
# CHECK-NEXT: [16.0] - Zn3Store
# CHECK-NEXT: [16.1] - Zn3Store
# 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: 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 - - - - - - - - - - - vpsubq %ymm0, %ymm0, %ymm0
# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - vpsubq %ymm1, %ymm0, %ymm0
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. vpsubq %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [0,1] D=eER.. vpsubq %ymm1, %ymm0, %ymm0
# CHECK-NEXT: [1,0] D==eER. vpsubq %ymm0, %ymm0, %ymm0
# CHECK-NEXT: [1,1] D===eER vpsubq %ymm1, %ymm0, %ymm0
# 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. 2 2.0 0.5 0.0 vpsubq %ymm0, %ymm0, %ymm0
# CHECK-NEXT: 1. 2 3.0 0.0 0.0 vpsubq %ymm1, %ymm0, %ymm0
# CHECK-NEXT: 2 2.5 0.3 0.0 <total>