[llvm] ba225ce - [NFC][X86][MCA] AMD Zen 3: add tests for same-reg MMX PCMPEQ
Roman Lebedev via llvm-commits
llvm-commits at lists.llvm.org
Mon May 10 13:49:55 PDT 2021
Author: Roman Lebedev
Date: 2021-05-10T23:49:25+03:00
New Revision: ba225ce961b4ec5e4d64b393b042bbaae5e9b41b
URL: https://github.com/llvm/llvm-project/commit/ba225ce961b4ec5e4d64b393b042bbaae5e9b41b
DIFF: https://github.com/llvm/llvm-project/commit/ba225ce961b4ec5e4d64b393b042bbaae5e9b41b.diff
LOG: [NFC][X86][MCA] AMD Zen 3: add tests for same-reg MMX PCMPEQ
Added:
llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s
Modified:
Removed:
################################################################################
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s
new file mode 100644
index 000000000000..f339f692efa1
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/one-idioms-mmx.s
@@ -0,0 +1,290 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver3 -timeline -timeline-max-iterations=2 -register-file-stats -iterations=1000 < %s | FileCheck %s
+
+# LLVM-MCA-BEGIN
+pcmpeqb %mm0, %mm0
+paddb %mm0, %mm0
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+pcmpeqw %mm0, %mm0
+paddw %mm0, %mm0
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+pcmpeqd %mm0, %mm0
+paddd %mm0, %mm0
+# LLVM-MCA-END
+
+# CHECK: [0] Code Region
+
+# CHECK: Iterations: 1000
+# CHECK-NEXT: Instructions: 2000
+# CHECK-NEXT: Total Cycles: 2003
+# CHECK-NEXT: Total uOps: 2000
+
+# 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 pcmpeqb %mm0, %mm0
+# CHECK-NEXT: 1 1 0.25 paddb %mm0, %mm0
+
+# CHECK: Register File statistics:
+# CHECK-NEXT: Total number of mappings created: 2000
+# 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: 2000
+# 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 - - - - - - - - - - - pcmpeqb %mm0, %mm0
+# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - paddb %mm0, %mm0
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456
+
+# CHECK: [0,0] DeER .. pcmpeqb %mm0, %mm0
+# CHECK-NEXT: [0,1] D=eER.. paddb %mm0, %mm0
+# CHECK-NEXT: [1,0] D==eER. pcmpeqb %mm0, %mm0
+# CHECK-NEXT: [1,1] D===eER paddb %mm0, %mm0
+
+# 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 pcmpeqb %mm0, %mm0
+# CHECK-NEXT: 1. 2 3.0 0.0 0.0 paddb %mm0, %mm0
+# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
+
+# CHECK: [1] Code Region
+
+# CHECK: Iterations: 1000
+# CHECK-NEXT: Instructions: 2000
+# CHECK-NEXT: Total Cycles: 2003
+# CHECK-NEXT: Total uOps: 2000
+
+# 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 pcmpeqw %mm0, %mm0
+# CHECK-NEXT: 1 1 0.25 paddw %mm0, %mm0
+
+# CHECK: Register File statistics:
+# CHECK-NEXT: Total number of mappings created: 2000
+# 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: 2000
+# 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 - - - - - - - - - - - pcmpeqw %mm0, %mm0
+# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - paddw %mm0, %mm0
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456
+
+# CHECK: [0,0] DeER .. pcmpeqw %mm0, %mm0
+# CHECK-NEXT: [0,1] D=eER.. paddw %mm0, %mm0
+# CHECK-NEXT: [1,0] D==eER. pcmpeqw %mm0, %mm0
+# CHECK-NEXT: [1,1] D===eER paddw %mm0, %mm0
+
+# 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 pcmpeqw %mm0, %mm0
+# CHECK-NEXT: 1. 2 3.0 0.0 0.0 paddw %mm0, %mm0
+# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
+
+# CHECK: [2] Code Region
+
+# CHECK: Iterations: 1000
+# CHECK-NEXT: Instructions: 2000
+# CHECK-NEXT: Total Cycles: 2003
+# CHECK-NEXT: Total uOps: 2000
+
+# 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 pcmpeqd %mm0, %mm0
+# CHECK-NEXT: 1 1 0.25 paddd %mm0, %mm0
+
+# CHECK: Register File statistics:
+# CHECK-NEXT: Total number of mappings created: 2000
+# 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: 2000
+# 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 - - - - - - - - - - - pcmpeqd %mm0, %mm0
+# CHECK-NEXT: - - - - - - - - 0.50 - 0.50 - - - - - - - - - - - - paddd %mm0, %mm0
+
+# CHECK: Timeline view:
+# CHECK-NEXT: Index 0123456
+
+# CHECK: [0,0] DeER .. pcmpeqd %mm0, %mm0
+# CHECK-NEXT: [0,1] D=eER.. paddd %mm0, %mm0
+# CHECK-NEXT: [1,0] D==eER. pcmpeqd %mm0, %mm0
+# CHECK-NEXT: [1,1] D===eER paddd %mm0, %mm0
+
+# 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 pcmpeqd %mm0, %mm0
+# CHECK-NEXT: 1. 2 3.0 0.0 0.0 paddd %mm0, %mm0
+# CHECK-NEXT: 2 2.5 0.3 0.0 <total>
More information about the llvm-commits
mailing list