maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[MCA] Add tests for int-to-fpu transfer delays. NFC 

llvm-svn: 351822
This commit is contained in:
Andrea Di Biagio 2019-01-22 13:59:08 +00:00
parent c4fe72c015
commit a4d1ffc269
3 changed files with 612 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

220
llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-1.s Normal file
View File

@ -0,0 +1,220 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=500 < %s | FileCheck %s
# Throughput for all the code snippet below should be 1.00 IPC.
# LLVM-MCA-BEGIN
vpinsrb $0, %eax, %xmm0, %xmm0
vpinsrb $1, %eax, %xmm0, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpinsrw $0, %eax, %xmm0, %xmm0
vpinsrw $1, %eax, %xmm0, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpinsrd $0, %eax, %xmm0, %xmm0
vpinsrd $1, %eax, %xmm0, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vpinsrq $0, %rax, %xmm0, %xmm0
vpinsrq $1, %rax, %xmm0, %xmm0
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 1000
# CHECK-NEXT: Total Cycles: 7003
# CHECK-NEXT: Total uOps: 2000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.29
# CHECK-NEXT: IPC: 0.14
# CHECK-NEXT: Block RThroughput: 2.0
# 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: 2 7 0.50 vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: 2 7 0.50 vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - 1.00 1.00 - - - - 1.00 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK: [1] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 1000
# CHECK-NEXT: Total Cycles: 7003
# CHECK-NEXT: Total uOps: 2000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.29
# CHECK-NEXT: IPC: 0.14
# CHECK-NEXT: Block RThroughput: 2.0
# 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: 2 7 0.50 vpinsrw $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: 2 7 0.50 vpinsrw $1, %eax, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - 1.00 1.00 - - - - 1.00 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpinsrw $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpinsrw $1, %eax, %xmm0, %xmm0
# CHECK: [2] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 1000
# CHECK-NEXT: Total Cycles: 7003
# CHECK-NEXT: Total uOps: 2000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.29
# CHECK-NEXT: IPC: 0.14
# CHECK-NEXT: Block RThroughput: 2.0
# 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: 2 7 0.50 vpinsrd $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: 2 7 0.50 vpinsrd $1, %eax, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - 1.00 1.00 - - - - 1.00 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpinsrd $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpinsrd $1, %eax, %xmm0, %xmm0
# CHECK: [3] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 1000
# CHECK-NEXT: Total Cycles: 7003
# CHECK-NEXT: Total uOps: 2000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.29
# CHECK-NEXT: IPC: 0.14
# CHECK-NEXT: Block RThroughput: 2.0
# 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: 2 7 0.50 vpinsrq $0, %rax, %xmm0, %xmm0
# CHECK-NEXT: 2 7 0.50 vpinsrq $1, %rax, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - 1.00 1.00 - - - - 1.00 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpinsrq $0, %rax, %xmm0, %xmm0
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpinsrq $1, %rax, %xmm0, %xmm0

310
llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-2.s Normal file
View File

@ -0,0 +1,310 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=500 < %s | FileCheck %s
# Throughput for all the code snippet below should tend to 1.00 IPC.
# LLVM-MCA-BEGIN
vcvtsi2ss %ecx, %xmm0, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
vcvtsi2sd %ecx, %xmm0, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
cvtsi2ss %ecx, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
cvtsi2sd %ecx, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movd %ecx, %xmm0
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movq %rcx, %xmm0
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 500
# CHECK-NEXT: Total Cycles: 4503
# CHECK-NEXT: Total uOps: 1000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.22
# CHECK-NEXT: IPC: 0.11
# CHECK-NEXT: Block RThroughput: 1.0
# 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: 2 9 1.00 vcvtsi2ssl %ecx, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvtsi2ssl %ecx, %xmm0, %xmm0
# CHECK: [1] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 500
# CHECK-NEXT: Total Cycles: 4503
# CHECK-NEXT: Total uOps: 1000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.22
# CHECK-NEXT: IPC: 0.11
# CHECK-NEXT: Block RThroughput: 1.0
# 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: 2 9 1.00 vcvtsi2sdl %ecx, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - vcvtsi2sdl %ecx, %xmm0, %xmm0
# CHECK: [2] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 500
# CHECK-NEXT: Total Cycles: 511
# CHECK-NEXT: Total uOps: 1000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96
# CHECK-NEXT: IPC: 0.98
# CHECK-NEXT: Block RThroughput: 1.0
# 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: 2 9 1.00 cvtsi2ssl %ecx, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - cvtsi2ssl %ecx, %xmm0
# CHECK: [3] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 500
# CHECK-NEXT: Total Cycles: 511
# CHECK-NEXT: Total uOps: 1000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96
# CHECK-NEXT: IPC: 0.98
# CHECK-NEXT: Block RThroughput: 1.0
# 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: 2 9 1.00 cvtsi2sdl %ecx, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: - - - - - - 1.00 - - - 1.00 - - - cvtsi2sdl %ecx, %xmm0
# CHECK: [4] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 500
# CHECK-NEXT: Total Cycles: 510
# CHECK-NEXT: Total uOps: 1000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96
# CHECK-NEXT: IPC: 0.98
# CHECK-NEXT: Block RThroughput: 1.0
# 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: 2 8 0.50 movd %ecx, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# 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] [13] Instructions:
# CHECK-NEXT: - - - 0.50 0.50 0.50 0.50 - - - - - - - movd %ecx, %xmm0
# CHECK: [5] Code Region
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 500
# CHECK-NEXT: Total Cycles: 510
# CHECK-NEXT: Total uOps: 1000
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 1.96
# CHECK-NEXT: IPC: 0.98
# CHECK-NEXT: Block RThroughput: 1.0
# 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: 2 8 0.50 movq %rcx, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# 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] [13] Instructions:
# CHECK-NEXT: - - - 0.50 0.50 0.50 0.50 - - - - - - - movq %rcx, %xmm0

82
llvm/test/tools/llvm-mca/X86/BtVer2/int-to-fpu-forwarding-3.s Normal file
View File

@ -0,0 +1,82 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -iterations=500 -timeline -timeline-max-iterations=3 < %s | FileCheck %s
# Throughput for the code snippet below should tend to 1.00 IPC.
add %eax, %eax
vpinsrb $0, %eax, %xmm0, %xmm0
vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK: Iterations: 500
# CHECK-NEXT: Instructions: 1500
# CHECK-NEXT: Total Cycles: 7004
# CHECK-NEXT: Total uOps: 2500
# CHECK: Dispatch Width: 2
# CHECK-NEXT: uOps Per Cycle: 0.36
# CHECK-NEXT: IPC: 0.21
# CHECK-NEXT: Block RThroughput: 2.5
# 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 0.50 addl %eax, %eax
# CHECK-NEXT: 2 7 0.50 vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: 2 7 0.50 vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK: Resources:
# CHECK-NEXT: [0] - JALU0
# CHECK-NEXT: [1] - JALU1
# CHECK-NEXT: [2] - JDiv
# CHECK-NEXT: [3] - JFPA
# CHECK-NEXT: [4] - JFPM
# CHECK-NEXT: [5] - JFPU0
# CHECK-NEXT: [6] - JFPU1
# CHECK-NEXT: [7] - JLAGU
# CHECK-NEXT: [8] - JMul
# CHECK-NEXT: [9] - JSAGU
# CHECK-NEXT: [10] - JSTC
# CHECK-NEXT: [11] - JVALU0
# CHECK-NEXT: [12] - JVALU1
# CHECK-NEXT: [13] - JVIMUL
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13]
# CHECK-NEXT: 0.50 0.50 - - - 1.00 1.00 - - - - 1.00 1.00 -
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions:
# CHECK-NEXT: 0.50 0.50 - - - - - - - - - - - - addl %eax, %eax
# CHECK-NEXT: - - - - - - 1.00 - - - - - 1.00 - vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: - - - - - 1.00 - - - - - 1.00 - - vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK: Timeline view:
# CHECK-NEXT: 0123456789 0123456789
# CHECK-NEXT: Index 0123456789 0123456789 012345
# CHECK: [0,0] DeER . . . . . . . . . addl %eax, %eax
# CHECK-NEXT: [0,1] .DeeeeeeeER . . . . . . . vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: [0,2] . D======eeeeeeeER . . . . . . vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK-NEXT: [1,0] . DeE-----------R . . . . . . addl %eax, %eax
# CHECK-NEXT: [1,1] . D===========eeeeeeeER. . . . . vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: [1,2] . D=================eeeeeeeER . . . vpinsrb $1, %eax, %xmm0, %xmm0
# CHECK-NEXT: [2,0] . .DeE----------------------R . . . addl %eax, %eax
# CHECK-NEXT: [2,1] . . D======================eeeeeeeER . . vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: [2,2] . . D============================eeeeeeeER vpinsrb $1, %eax, %xmm0, %xmm0
# 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. 3 1.0 1.0 11.0 addl %eax, %eax
# CHECK-NEXT: 1. 3 12.0 0.0 0.0 vpinsrb $0, %eax, %xmm0, %xmm0
# CHECK-NEXT: 2. 3 18.0 0.0 0.0 vpinsrb $1, %eax, %xmm0, %xmm0