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

[NFC][X86][MCA] Barcelona: add load/store/load-store-throughput tests 

llvm-svn: 363775
This commit is contained in:
Roman Lebedev 2019-06-19 08:53:34 +00:00
parent 4358016b03
commit 9f9691c032
3 changed files with 1855 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

621
llvm/test/tools/llvm-mca/X86/Barcelona/load-store-throughput.s Normal file
View File

@ -0,0 +1,621 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -scheduler-stats -dispatch-stats -iterations=100 -timeline -timeline-max-iterations=1 < %s | FileCheck %s
# LLVM-MCA-BEGIN
movb %spl, (%rax)
movb (%rcx), %bpl
movb (%rdx), %sil
movb %dil, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movw %sp, (%rax)
movw (%rcx), %bp
movw (%rdx), %si
movw %di, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movl %esp, (%rax)
movl (%rcx), %ebp
movl (%rdx), %esi
movl %edi, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movq %rsp, (%rax)
movq (%rcx), %rbp
movq (%rdx), %rsi
movq %rdi, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movd %mm0, (%rax)
movd (%rcx), %mm1
movd (%rdx), %mm2
movd %mm3, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movaps %xmm0, (%rax)
movaps (%rcx), %xmm1
movaps (%rdx), %xmm2
movaps %xmm3, (%rbx)
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 208
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.92
# CHECK-NEXT: IPC: 1.92
# 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: 1 1 1.00 * movb %spl, (%rax)
# CHECK-NEXT: 1 5 0.50 * movb (%rcx), %bpl
# CHECK-NEXT: 1 5 0.50 * movb (%rdx), %sil
# CHECK-NEXT: 1 1 1.00 * movb %dil, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.7%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 34 (16.3%)
# CHECK-NEXT: 2, 148 (71.2%)
# CHECK-NEXT: 4, 26 (12.5%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (1.4%)
# CHECK-NEXT: 1, 10 (4.8%)
# CHECK-NEXT: 2, 195 (93.8%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 2.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movb %spl, (%rax)
# CHECK-NEXT: - - - - - - 1.00 - movb (%rcx), %bpl
# CHECK-NEXT: - - - - - - 0.95 0.05 movb (%rdx), %sil
# CHECK-NEXT: - - - - 1.00 - 0.05 0.95 movb %dil, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeER . . movb %spl, (%rax)
# CHECK-NEXT: [0,1] DeeeeeER . movb (%rcx), %bpl
# CHECK-NEXT: [0,2] D=eeeeeER. movb (%rdx), %sil
# CHECK-NEXT: [0,3] D======eER movb %dil, (%rbx)
# 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. 1 1.0 1.0 0.0 movb %spl, (%rax)
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movb (%rcx), %bpl
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movb (%rdx), %sil
# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movb %dil, (%rbx)
# CHECK: [1] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 208
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.92
# CHECK-NEXT: IPC: 1.92
# 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: 1 1 1.00 * movw %sp, (%rax)
# CHECK-NEXT: 1 5 0.50 * movw (%rcx), %bp
# CHECK-NEXT: 1 5 0.50 * movw (%rdx), %si
# CHECK-NEXT: 1 1 1.00 * movw %di, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.7%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 34 (16.3%)
# CHECK-NEXT: 2, 148 (71.2%)
# CHECK-NEXT: 4, 26 (12.5%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (1.4%)
# CHECK-NEXT: 1, 10 (4.8%)
# CHECK-NEXT: 2, 195 (93.8%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 2.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movw %sp, (%rax)
# CHECK-NEXT: - - - - - - 1.00 - movw (%rcx), %bp
# CHECK-NEXT: - - - - - - 0.95 0.05 movw (%rdx), %si
# CHECK-NEXT: - - - - 1.00 - 0.05 0.95 movw %di, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeER . . movw %sp, (%rax)
# CHECK-NEXT: [0,1] DeeeeeER . movw (%rcx), %bp
# CHECK-NEXT: [0,2] D=eeeeeER. movw (%rdx), %si
# CHECK-NEXT: [0,3] D======eER movw %di, (%rbx)
# 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. 1 1.0 1.0 0.0 movw %sp, (%rax)
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movw (%rcx), %bp
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movw (%rdx), %si
# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movw %di, (%rbx)
# CHECK: [2] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 208
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.92
# CHECK-NEXT: IPC: 1.92
# 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: 1 1 1.00 * movl %esp, (%rax)
# CHECK-NEXT: 1 5 0.50 * movl (%rcx), %ebp
# CHECK-NEXT: 1 5 0.50 * movl (%rdx), %esi
# CHECK-NEXT: 1 1 1.00 * movl %edi, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.7%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 34 (16.3%)
# CHECK-NEXT: 2, 148 (71.2%)
# CHECK-NEXT: 4, 26 (12.5%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (1.4%)
# CHECK-NEXT: 1, 10 (4.8%)
# CHECK-NEXT: 2, 195 (93.8%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 2.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movl %esp, (%rax)
# CHECK-NEXT: - - - - - - 1.00 - movl (%rcx), %ebp
# CHECK-NEXT: - - - - - - 0.95 0.05 movl (%rdx), %esi
# CHECK-NEXT: - - - - 1.00 - 0.05 0.95 movl %edi, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeER . . movl %esp, (%rax)
# CHECK-NEXT: [0,1] DeeeeeER . movl (%rcx), %ebp
# CHECK-NEXT: [0,2] D=eeeeeER. movl (%rdx), %esi
# CHECK-NEXT: [0,3] D======eER movl %edi, (%rbx)
# 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. 1 1.0 1.0 0.0 movl %esp, (%rax)
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movl (%rcx), %ebp
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movl (%rdx), %esi
# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movl %edi, (%rbx)
# CHECK: [3] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 208
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.92
# CHECK-NEXT: IPC: 1.92
# 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: 1 1 1.00 * movq %rsp, (%rax)
# CHECK-NEXT: 1 5 0.50 * movq (%rcx), %rbp
# CHECK-NEXT: 1 5 0.50 * movq (%rdx), %rsi
# CHECK-NEXT: 1 1 1.00 * movq %rdi, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.7%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 34 (16.3%)
# CHECK-NEXT: 2, 148 (71.2%)
# CHECK-NEXT: 4, 26 (12.5%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (1.4%)
# CHECK-NEXT: 1, 10 (4.8%)
# CHECK-NEXT: 2, 195 (93.8%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 2.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movq %rsp, (%rax)
# CHECK-NEXT: - - - - - - 1.00 - movq (%rcx), %rbp
# CHECK-NEXT: - - - - - - 0.95 0.05 movq (%rdx), %rsi
# CHECK-NEXT: - - - - 1.00 - 0.05 0.95 movq %rdi, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeER . . movq %rsp, (%rax)
# CHECK-NEXT: [0,1] DeeeeeER . movq (%rcx), %rbp
# CHECK-NEXT: [0,2] D=eeeeeER. movq (%rdx), %rsi
# CHECK-NEXT: [0,3] D======eER movq %rdi, (%rbx)
# 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. 1 1.0 1.0 0.0 movq %rsp, (%rax)
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movq (%rcx), %rbp
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movq (%rdx), %rsi
# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movq %rdi, (%rbx)
# CHECK: [4] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 208
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.92
# CHECK-NEXT: IPC: 1.92
# 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: 1 1 1.00 * U movd %mm0, (%rax)
# CHECK-NEXT: 1 5 0.50 * movd (%rcx), %mm1
# CHECK-NEXT: 1 5 0.50 * movd (%rdx), %mm2
# CHECK-NEXT: 1 1 1.00 * U movd %mm3, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.7%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 34 (16.3%)
# CHECK-NEXT: 2, 148 (71.2%)
# CHECK-NEXT: 4, 26 (12.5%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (1.4%)
# CHECK-NEXT: 1, 10 (4.8%)
# CHECK-NEXT: 2, 195 (93.8%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 2.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movd %mm0, (%rax)
# CHECK-NEXT: - - - - - - 1.00 - movd (%rcx), %mm1
# CHECK-NEXT: - - - - - - 0.95 0.05 movd (%rdx), %mm2
# CHECK-NEXT: - - - - 1.00 - 0.05 0.95 movd %mm3, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeER . . movd %mm0, (%rax)
# CHECK-NEXT: [0,1] DeeeeeER . movd (%rcx), %mm1
# CHECK-NEXT: [0,2] D=eeeeeER. movd (%rdx), %mm2
# CHECK-NEXT: [0,3] D======eER movd %mm3, (%rbx)
# 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. 1 1.0 1.0 0.0 movd %mm0, (%rax)
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movd (%rcx), %mm1
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movd (%rdx), %mm2
# CHECK-NEXT: 3. 1 7.0 0.0 0.0 movd %mm3, (%rbx)
# CHECK: [5] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 209
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.91
# CHECK-NEXT: IPC: 1.91
# 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: 1 1 1.00 * movaps %xmm0, (%rax)
# CHECK-NEXT: 1 6 0.50 * movaps (%rcx), %xmm1
# CHECK-NEXT: 1 6 0.50 * movaps (%rdx), %xmm2
# CHECK-NEXT: 1 1 1.00 * movaps %xmm3, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.3%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 35 (16.7%)
# CHECK-NEXT: 2, 148 (70.8%)
# CHECK-NEXT: 4, 26 (12.4%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (1.4%)
# CHECK-NEXT: 1, 12 (5.7%)
# CHECK-NEXT: 2, 194 (92.8%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 2.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movaps %xmm0, (%rax)
# CHECK-NEXT: - - - - - - 1.00 - movaps (%rcx), %xmm1
# CHECK-NEXT: - - - - - - 0.94 0.06 movaps (%rdx), %xmm2
# CHECK-NEXT: - - - - 1.00 - 0.06 0.94 movaps %xmm3, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: 0
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeER . . movaps %xmm0, (%rax)
# CHECK-NEXT: [0,1] DeeeeeeER . movaps (%rcx), %xmm1
# CHECK-NEXT: [0,2] D=eeeeeeER. movaps (%rdx), %xmm2
# CHECK-NEXT: [0,3] D=======eER movaps %xmm3, (%rbx)
# 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. 1 1.0 1.0 0.0 movaps %xmm0, (%rax)
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movaps (%rcx), %xmm1
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movaps (%rdx), %xmm2
# CHECK-NEXT: 3. 1 8.0 0.0 0.0 movaps %xmm3, (%rbx)

614
llvm/test/tools/llvm-mca/X86/Barcelona/load-throughput.s Normal file
View File

@ -0,0 +1,614 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -scheduler-stats -dispatch-stats -iterations=100 -timeline -timeline-max-iterations=1 < %s | FileCheck %s
# LLVM-MCA-BEGIN
movb (%rax), %spl
movb (%rcx), %bpl
movb (%rdx), %sil
movb (%rbx), %dil
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movw (%rax), %sp
movw (%rcx), %bp
movw (%rdx), %si
movw (%rbx), %di
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movl (%rax), %esp
movl (%rcx), %ebp
movl (%rdx), %esi
movl (%rbx), %edi
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movq (%rax), %rsp
movq (%rcx), %rbp
movq (%rdx), %rsi
movq (%rbx), %rdi
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movd (%rax), %mm0
movd (%rcx), %mm1
movd (%rdx), %mm2
movd (%rbx), %mm3
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movaps (%rax), %xmm0
movaps (%rcx), %xmm1
movaps (%rdx), %xmm2
movaps (%rbx), %xmm3
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 207
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.93
# CHECK-NEXT: IPC: 1.93
# 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: 1 5 0.50 * movb (%rax), %spl
# CHECK-NEXT: 1 5 0.50 * movb (%rcx), %bpl
# CHECK-NEXT: 1 5 0.50 * movb (%rdx), %sil
# CHECK-NEXT: 1 5 0.50 * movb (%rbx), %dil
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (71.0%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 33 (15.9%)
# CHECK-NEXT: 2, 148 (71.5%)
# CHECK-NEXT: 4, 26 (12.6%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 7 (3.4%)
# CHECK-NEXT: 2, 200 (96.6%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - - - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - - - - 1.00 movb (%rax), %spl
# CHECK-NEXT: - - - - - - 1.00 - movb (%rcx), %bpl
# CHECK-NEXT: - - - - - - - 1.00 movb (%rdx), %sil
# CHECK-NEXT: - - - - - - 1.00 - movb (%rbx), %dil
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeeeeeER. movb (%rax), %spl
# CHECK-NEXT: [0,1] DeeeeeER. movb (%rcx), %bpl
# CHECK-NEXT: [0,2] D=eeeeeER movb (%rdx), %sil
# CHECK-NEXT: [0,3] D=eeeeeER movb (%rbx), %dil
# 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. 1 1.0 1.0 0.0 movb (%rax), %spl
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movb (%rcx), %bpl
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movb (%rdx), %sil
# CHECK-NEXT: 3. 1 2.0 2.0 0.0 movb (%rbx), %dil
# CHECK: [1] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 207
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.93
# CHECK-NEXT: IPC: 1.93
# 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: 1 5 0.50 * movw (%rax), %sp
# CHECK-NEXT: 1 5 0.50 * movw (%rcx), %bp
# CHECK-NEXT: 1 5 0.50 * movw (%rdx), %si
# CHECK-NEXT: 1 5 0.50 * movw (%rbx), %di
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (71.0%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 33 (15.9%)
# CHECK-NEXT: 2, 148 (71.5%)
# CHECK-NEXT: 4, 26 (12.6%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 7 (3.4%)
# CHECK-NEXT: 2, 200 (96.6%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - - - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - - - - 1.00 movw (%rax), %sp
# CHECK-NEXT: - - - - - - 1.00 - movw (%rcx), %bp
# CHECK-NEXT: - - - - - - - 1.00 movw (%rdx), %si
# CHECK-NEXT: - - - - - - 1.00 - movw (%rbx), %di
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeeeeeER. movw (%rax), %sp
# CHECK-NEXT: [0,1] DeeeeeER. movw (%rcx), %bp
# CHECK-NEXT: [0,2] D=eeeeeER movw (%rdx), %si
# CHECK-NEXT: [0,3] D=eeeeeER movw (%rbx), %di
# 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. 1 1.0 1.0 0.0 movw (%rax), %sp
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movw (%rcx), %bp
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movw (%rdx), %si
# CHECK-NEXT: 3. 1 2.0 2.0 0.0 movw (%rbx), %di
# CHECK: [2] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 207
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.93
# CHECK-NEXT: IPC: 1.93
# 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: 1 5 0.50 * movl (%rax), %esp
# CHECK-NEXT: 1 5 0.50 * movl (%rcx), %ebp
# CHECK-NEXT: 1 5 0.50 * movl (%rdx), %esi
# CHECK-NEXT: 1 5 0.50 * movl (%rbx), %edi
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (71.0%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 33 (15.9%)
# CHECK-NEXT: 2, 148 (71.5%)
# CHECK-NEXT: 4, 26 (12.6%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 7 (3.4%)
# CHECK-NEXT: 2, 200 (96.6%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - - - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - - - - 1.00 movl (%rax), %esp
# CHECK-NEXT: - - - - - - 1.00 - movl (%rcx), %ebp
# CHECK-NEXT: - - - - - - - 1.00 movl (%rdx), %esi
# CHECK-NEXT: - - - - - - 1.00 - movl (%rbx), %edi
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeeeeeER. movl (%rax), %esp
# CHECK-NEXT: [0,1] DeeeeeER. movl (%rcx), %ebp
# CHECK-NEXT: [0,2] D=eeeeeER movl (%rdx), %esi
# CHECK-NEXT: [0,3] D=eeeeeER movl (%rbx), %edi
# 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. 1 1.0 1.0 0.0 movl (%rax), %esp
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movl (%rcx), %ebp
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movl (%rdx), %esi
# CHECK-NEXT: 3. 1 2.0 2.0 0.0 movl (%rbx), %edi
# CHECK: [3] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 207
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.93
# CHECK-NEXT: IPC: 1.93
# 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: 1 5 0.50 * movq (%rax), %rsp
# CHECK-NEXT: 1 5 0.50 * movq (%rcx), %rbp
# CHECK-NEXT: 1 5 0.50 * movq (%rdx), %rsi
# CHECK-NEXT: 1 5 0.50 * movq (%rbx), %rdi
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (71.0%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 33 (15.9%)
# CHECK-NEXT: 2, 148 (71.5%)
# CHECK-NEXT: 4, 26 (12.6%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 7 (3.4%)
# CHECK-NEXT: 2, 200 (96.6%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - - - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - - - - 1.00 movq (%rax), %rsp
# CHECK-NEXT: - - - - - - 1.00 - movq (%rcx), %rbp
# CHECK-NEXT: - - - - - - - 1.00 movq (%rdx), %rsi
# CHECK-NEXT: - - - - - - 1.00 - movq (%rbx), %rdi
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeeeeeER. movq (%rax), %rsp
# CHECK-NEXT: [0,1] DeeeeeER. movq (%rcx), %rbp
# CHECK-NEXT: [0,2] D=eeeeeER movq (%rdx), %rsi
# CHECK-NEXT: [0,3] D=eeeeeER movq (%rbx), %rdi
# 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. 1 1.0 1.0 0.0 movq (%rax), %rsp
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movq (%rcx), %rbp
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movq (%rdx), %rsi
# CHECK-NEXT: 3. 1 2.0 2.0 0.0 movq (%rbx), %rdi
# CHECK: [4] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 207
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.93
# CHECK-NEXT: IPC: 1.93
# 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: 1 5 0.50 * movd (%rax), %mm0
# CHECK-NEXT: 1 5 0.50 * movd (%rcx), %mm1
# CHECK-NEXT: 1 5 0.50 * movd (%rdx), %mm2
# CHECK-NEXT: 1 5 0.50 * movd (%rbx), %mm3
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (71.0%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 33 (15.9%)
# CHECK-NEXT: 2, 148 (71.5%)
# CHECK-NEXT: 4, 26 (12.6%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 7 (3.4%)
# CHECK-NEXT: 2, 200 (96.6%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - - - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - - - - 1.00 movd (%rax), %mm0
# CHECK-NEXT: - - - - - - 1.00 - movd (%rcx), %mm1
# CHECK-NEXT: - - - - - - - 1.00 movd (%rdx), %mm2
# CHECK-NEXT: - - - - - - 1.00 - movd (%rbx), %mm3
# CHECK: Timeline view:
# CHECK-NEXT: Index 012345678
# CHECK: [0,0] DeeeeeER. movd (%rax), %mm0
# CHECK-NEXT: [0,1] DeeeeeER. movd (%rcx), %mm1
# CHECK-NEXT: [0,2] D=eeeeeER movd (%rdx), %mm2
# CHECK-NEXT: [0,3] D=eeeeeER movd (%rbx), %mm3
# 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. 1 1.0 1.0 0.0 movd (%rax), %mm0
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movd (%rcx), %mm1
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movd (%rdx), %mm2
# CHECK-NEXT: 3. 1 2.0 2.0 0.0 movd (%rbx), %mm3
# CHECK: [5] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 208
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 1.92
# CHECK-NEXT: IPC: 1.92
# 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: 1 6 0.50 * movaps (%rax), %xmm0
# CHECK-NEXT: 1 6 0.50 * movaps (%rcx), %xmm1
# CHECK-NEXT: 1 6 0.50 * movaps (%rdx), %xmm2
# CHECK-NEXT: 1 6 0.50 * movaps (%rbx), %xmm3
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 147 (70.7%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 34 (16.3%)
# CHECK-NEXT: 2, 148 (71.2%)
# CHECK-NEXT: 4, 26 (12.5%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 8 (3.8%)
# CHECK-NEXT: 2, 200 (96.2%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 45 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - - - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - - - - 1.00 movaps (%rax), %xmm0
# CHECK-NEXT: - - - - - - 1.00 - movaps (%rcx), %xmm1
# CHECK-NEXT: - - - - - - - 1.00 movaps (%rdx), %xmm2
# CHECK-NEXT: - - - - - - 1.00 - movaps (%rbx), %xmm3
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456789
# CHECK: [0,0] DeeeeeeER. movaps (%rax), %xmm0
# CHECK-NEXT: [0,1] DeeeeeeER. movaps (%rcx), %xmm1
# CHECK-NEXT: [0,2] D=eeeeeeER movaps (%rdx), %xmm2
# CHECK-NEXT: [0,3] D=eeeeeeER movaps (%rbx), %xmm3
# 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. 1 1.0 1.0 0.0 movaps (%rax), %xmm0
# CHECK-NEXT: 1. 1 1.0 1.0 0.0 movaps (%rcx), %xmm1
# CHECK-NEXT: 2. 1 2.0 2.0 0.0 movaps (%rdx), %xmm2
# CHECK-NEXT: 3. 1 2.0 2.0 0.0 movaps (%rbx), %xmm3

620
llvm/test/tools/llvm-mca/X86/Barcelona/store-throughput.s Normal file
View File

@ -0,0 +1,620 @@
# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -scheduler-stats -dispatch-stats -iterations=100 -timeline -timeline-max-iterations=1 -noalias=true < %s | FileCheck %s
# LLVM-MCA-BEGIN
movb %spl, (%rax)
movb %bpl, (%rcx)
movb %sil, (%rdx)
movb %dil, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movw %sp, (%rax)
movw %bp, (%rcx)
movw %si, (%rdx)
movw %di, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movl %esp, (%rax)
movl %ebp, (%rcx)
movl %esi, (%rdx)
movl %edi, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movq %rsp, (%rax)
movq %rbp, (%rcx)
movq %rsi, (%rdx)
movq %rdi, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movd %mm0, (%rax)
movd %mm1, (%rcx)
movd %mm2, (%rdx)
movd %mm3, (%rbx)
# LLVM-MCA-END
# LLVM-MCA-BEGIN
movaps %xmm0, (%rax)
movaps %xmm1, (%rcx)
movaps %xmm2, (%rdx)
movaps %xmm3, (%rbx)
# LLVM-MCA-END
# CHECK: [0] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 403
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.99
# CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 4.0
# 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: 1 1 1.00 * movb %spl, (%rax)
# CHECK-NEXT: 1 1 1.00 * movb %bpl, (%rcx)
# CHECK-NEXT: 1 1 1.00 * movb %sil, (%rdx)
# CHECK-NEXT: 1 1 1.00 * movb %dil, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 329 (81.6%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 56 (13.9%)
# CHECK-NEXT: 1, 329 (81.6%)
# CHECK-NEXT: 3, 1 (0.2%)
# CHECK-NEXT: 4, 17 (4.2%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (0.7%)
# CHECK-NEXT: 1, 400 (99.3%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 49 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 4.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movb %spl, (%rax)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movb %bpl, (%rcx)
# CHECK-NEXT: - - - - 1.00 - - 1.00 movb %sil, (%rdx)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movb %dil, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. movb %spl, (%rax)
# CHECK-NEXT: [0,1] D=eER.. movb %bpl, (%rcx)
# CHECK-NEXT: [0,2] D==eER. movb %sil, (%rdx)
# CHECK-NEXT: [0,3] D===eER movb %dil, (%rbx)
# 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. 1 1.0 1.0 0.0 movb %spl, (%rax)
# CHECK-NEXT: 1. 1 2.0 0.0 0.0 movb %bpl, (%rcx)
# CHECK-NEXT: 2. 1 3.0 0.0 0.0 movb %sil, (%rdx)
# CHECK-NEXT: 3. 1 4.0 0.0 0.0 movb %dil, (%rbx)
# CHECK: [1] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 403
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.99
# CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 4.0
# 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: 1 1 1.00 * movw %sp, (%rax)
# CHECK-NEXT: 1 1 1.00 * movw %bp, (%rcx)
# CHECK-NEXT: 1 1 1.00 * movw %si, (%rdx)
# CHECK-NEXT: 1 1 1.00 * movw %di, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 329 (81.6%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 56 (13.9%)
# CHECK-NEXT: 1, 329 (81.6%)
# CHECK-NEXT: 3, 1 (0.2%)
# CHECK-NEXT: 4, 17 (4.2%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (0.7%)
# CHECK-NEXT: 1, 400 (99.3%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 49 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 4.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movw %sp, (%rax)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movw %bp, (%rcx)
# CHECK-NEXT: - - - - 1.00 - - 1.00 movw %si, (%rdx)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movw %di, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. movw %sp, (%rax)
# CHECK-NEXT: [0,1] D=eER.. movw %bp, (%rcx)
# CHECK-NEXT: [0,2] D==eER. movw %si, (%rdx)
# CHECK-NEXT: [0,3] D===eER movw %di, (%rbx)
# 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. 1 1.0 1.0 0.0 movw %sp, (%rax)
# CHECK-NEXT: 1. 1 2.0 0.0 0.0 movw %bp, (%rcx)
# CHECK-NEXT: 2. 1 3.0 0.0 0.0 movw %si, (%rdx)
# CHECK-NEXT: 3. 1 4.0 0.0 0.0 movw %di, (%rbx)
# CHECK: [2] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 403
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.99
# CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 4.0
# 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: 1 1 1.00 * movl %esp, (%rax)
# CHECK-NEXT: 1 1 1.00 * movl %ebp, (%rcx)
# CHECK-NEXT: 1 1 1.00 * movl %esi, (%rdx)
# CHECK-NEXT: 1 1 1.00 * movl %edi, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 329 (81.6%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 56 (13.9%)
# CHECK-NEXT: 1, 329 (81.6%)
# CHECK-NEXT: 3, 1 (0.2%)
# CHECK-NEXT: 4, 17 (4.2%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (0.7%)
# CHECK-NEXT: 1, 400 (99.3%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 49 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 4.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movl %esp, (%rax)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movl %ebp, (%rcx)
# CHECK-NEXT: - - - - 1.00 - - 1.00 movl %esi, (%rdx)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movl %edi, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. movl %esp, (%rax)
# CHECK-NEXT: [0,1] D=eER.. movl %ebp, (%rcx)
# CHECK-NEXT: [0,2] D==eER. movl %esi, (%rdx)
# CHECK-NEXT: [0,3] D===eER movl %edi, (%rbx)
# 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. 1 1.0 1.0 0.0 movl %esp, (%rax)
# CHECK-NEXT: 1. 1 2.0 0.0 0.0 movl %ebp, (%rcx)
# CHECK-NEXT: 2. 1 3.0 0.0 0.0 movl %esi, (%rdx)
# CHECK-NEXT: 3. 1 4.0 0.0 0.0 movl %edi, (%rbx)
# CHECK: [3] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 403
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.99
# CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 4.0
# 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: 1 1 1.00 * movq %rsp, (%rax)
# CHECK-NEXT: 1 1 1.00 * movq %rbp, (%rcx)
# CHECK-NEXT: 1 1 1.00 * movq %rsi, (%rdx)
# CHECK-NEXT: 1 1 1.00 * movq %rdi, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 329 (81.6%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 56 (13.9%)
# CHECK-NEXT: 1, 329 (81.6%)
# CHECK-NEXT: 3, 1 (0.2%)
# CHECK-NEXT: 4, 17 (4.2%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (0.7%)
# CHECK-NEXT: 1, 400 (99.3%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 49 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 4.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movq %rsp, (%rax)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movq %rbp, (%rcx)
# CHECK-NEXT: - - - - 1.00 - - 1.00 movq %rsi, (%rdx)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movq %rdi, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. movq %rsp, (%rax)
# CHECK-NEXT: [0,1] D=eER.. movq %rbp, (%rcx)
# CHECK-NEXT: [0,2] D==eER. movq %rsi, (%rdx)
# CHECK-NEXT: [0,3] D===eER movq %rdi, (%rbx)
# 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. 1 1.0 1.0 0.0 movq %rsp, (%rax)
# CHECK-NEXT: 1. 1 2.0 0.0 0.0 movq %rbp, (%rcx)
# CHECK-NEXT: 2. 1 3.0 0.0 0.0 movq %rsi, (%rdx)
# CHECK-NEXT: 3. 1 4.0 0.0 0.0 movq %rdi, (%rbx)
# CHECK: [4] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 403
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.99
# CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 4.0
# 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: 1 1 1.00 * U movd %mm0, (%rax)
# CHECK-NEXT: 1 1 1.00 * U movd %mm1, (%rcx)
# CHECK-NEXT: 1 1 1.00 * U movd %mm2, (%rdx)
# CHECK-NEXT: 1 1 1.00 * U movd %mm3, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 329 (81.6%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 56 (13.9%)
# CHECK-NEXT: 1, 329 (81.6%)
# CHECK-NEXT: 3, 1 (0.2%)
# CHECK-NEXT: 4, 17 (4.2%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (0.7%)
# CHECK-NEXT: 1, 400 (99.3%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 49 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 4.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movd %mm0, (%rax)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movd %mm1, (%rcx)
# CHECK-NEXT: - - - - 1.00 - - 1.00 movd %mm2, (%rdx)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movd %mm3, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. movd %mm0, (%rax)
# CHECK-NEXT: [0,1] D=eER.. movd %mm1, (%rcx)
# CHECK-NEXT: [0,2] D==eER. movd %mm2, (%rdx)
# CHECK-NEXT: [0,3] D===eER movd %mm3, (%rbx)
# 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. 1 1.0 1.0 0.0 movd %mm0, (%rax)
# CHECK-NEXT: 1. 1 2.0 0.0 0.0 movd %mm1, (%rcx)
# CHECK-NEXT: 2. 1 3.0 0.0 0.0 movd %mm2, (%rdx)
# CHECK-NEXT: 3. 1 4.0 0.0 0.0 movd %mm3, (%rbx)
# CHECK: [5] Code Region
# CHECK: Iterations: 100
# CHECK-NEXT: Instructions: 400
# CHECK-NEXT: Total Cycles: 403
# CHECK-NEXT: Total uOps: 400
# CHECK: Dispatch Width: 4
# CHECK-NEXT: uOps Per Cycle: 0.99
# CHECK-NEXT: IPC: 0.99
# CHECK-NEXT: Block RThroughput: 4.0
# 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: 1 1 1.00 * movaps %xmm0, (%rax)
# CHECK-NEXT: 1 1 1.00 * movaps %xmm1, (%rcx)
# CHECK-NEXT: 1 1 1.00 * movaps %xmm2, (%rdx)
# CHECK-NEXT: 1 1 1.00 * movaps %xmm3, (%rbx)
# CHECK: Dynamic Dispatch Stall Cycles:
# CHECK-NEXT: RAT - Register unavailable: 0
# CHECK-NEXT: RCU - Retire tokens unavailable: 0
# CHECK-NEXT: SCHEDQ - Scheduler full: 329 (81.6%)
# CHECK-NEXT: LQ - Load queue full: 0
# CHECK-NEXT: SQ - Store queue full: 0
# CHECK-NEXT: GROUP - Static restrictions on the dispatch group: 0
# CHECK: Dispatch Logic - number of cycles where we saw N micro opcodes dispatched:
# CHECK-NEXT: [# dispatched], [# cycles]
# CHECK-NEXT: 0, 56 (13.9%)
# CHECK-NEXT: 1, 329 (81.6%)
# CHECK-NEXT: 3, 1 (0.2%)
# CHECK-NEXT: 4, 17 (4.2%)
# CHECK: Schedulers - number of cycles where we saw N micro opcodes issued:
# CHECK-NEXT: [# issued], [# cycles]
# CHECK-NEXT: 0, 3 (0.7%)
# CHECK-NEXT: 1, 400 (99.3%)
# CHECK: Scheduler's queue usage:
# CHECK-NEXT: [1] Resource name.
# CHECK-NEXT: [2] Average number of used buffer entries.
# CHECK-NEXT: [3] Maximum number of used buffer entries.
# CHECK-NEXT: [4] Total number of buffer entries.
# CHECK: [1] [2] [3] [4]
# CHECK-NEXT: SBPortAny 49 54 54
# CHECK: Resources:
# CHECK-NEXT: [0] - SBDivider
# CHECK-NEXT: [1] - SBFPDivider
# CHECK-NEXT: [2] - SBPort0
# CHECK-NEXT: [3] - SBPort1
# CHECK-NEXT: [4] - SBPort4
# CHECK-NEXT: [5] - SBPort5
# CHECK-NEXT: [6.0] - SBPort23
# CHECK-NEXT: [6.1] - SBPort23
# CHECK: Resource pressure per iteration:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1]
# CHECK-NEXT: - - - - 4.00 - 2.00 2.00
# CHECK: Resource pressure by instruction:
# CHECK-NEXT: [0] [1] [2] [3] [4] [5] [6.0] [6.1] Instructions:
# CHECK-NEXT: - - - - 1.00 - - 1.00 movaps %xmm0, (%rax)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movaps %xmm1, (%rcx)
# CHECK-NEXT: - - - - 1.00 - - 1.00 movaps %xmm2, (%rdx)
# CHECK-NEXT: - - - - 1.00 - 1.00 - movaps %xmm3, (%rbx)
# CHECK: Timeline view:
# CHECK-NEXT: Index 0123456
# CHECK: [0,0] DeER .. movaps %xmm0, (%rax)
# CHECK-NEXT: [0,1] D=eER.. movaps %xmm1, (%rcx)
# CHECK-NEXT: [0,2] D==eER. movaps %xmm2, (%rdx)
# CHECK-NEXT: [0,3] D===eER movaps %xmm3, (%rbx)
# 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. 1 1.0 1.0 0.0 movaps %xmm0, (%rax)
# CHECK-NEXT: 1. 1 2.0 0.0 0.0 movaps %xmm1, (%rcx)
# CHECK-NEXT: 2. 1 3.0 0.0 0.0 movaps %xmm2, (%rdx)
# CHECK-NEXT: 3. 1 4.0 0.0 0.0 movaps %xmm3, (%rbx)