diff options
Diffstat (limited to 'llvm')
| -rw-r--r-- | llvm/docs/CommandGuide/llvm-mca.rst | 10 | ||||
| -rw-r--r-- | llvm/test/tools/llvm-mca/X86/option-all-stats-1.s | 92 | ||||
| -rw-r--r-- | llvm/test/tools/llvm-mca/X86/option-all-stats-2.s | 93 | ||||
| -rw-r--r-- | llvm/test/tools/llvm-mca/X86/option-all-views-1.s | 116 | ||||
| -rw-r--r-- | llvm/test/tools/llvm-mca/X86/option-all-views-2.s | 141 | ||||
| -rw-r--r-- | llvm/tools/llvm-mca/llvm-mca.cpp | 38 |
6 files changed, 490 insertions, 0 deletions
diff --git a/llvm/docs/CommandGuide/llvm-mca.rst b/llvm/docs/CommandGuide/llvm-mca.rst index 63f2e65cd04..d6324c821c8 100644 --- a/llvm/docs/CommandGuide/llvm-mca.rst +++ b/llvm/docs/CommandGuide/llvm-mca.rst @@ -176,6 +176,16 @@ option specifies "``-``", then the output will also be sent to standard output. Enable the instruction info view. This is enabled by default. +.. option:: -all-stats + + Print all hardware statistics. This enables extra statistics related to the + dispatch logic, the hardware schedulers, the register file(s), and the retire + control unit. This option is disabled by default. + +.. option:: -all-views + + Enable all the view. + .. option:: -instruction-tables Prints resource pressure information based on the static information diff --git a/llvm/test/tools/llvm-mca/X86/option-all-stats-1.s b/llvm/test/tools/llvm-mca/X86/option-all-stats-1.s new file mode 100644 index 00000000000..bae6fb19c51 --- /dev/null +++ b/llvm/test/tools/llvm-mca/X86/option-all-stats-1.s @@ -0,0 +1,92 @@ +# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-stats < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-stats=true < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-stats=false < %s | FileCheck %s -check-prefix=ALL +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 < %s | FileCheck %s -check-prefix=ALL + +add %eax, %eax + +# ALL: Iterations: 100 +# ALL-NEXT: Instructions: 100 +# ALL-NEXT: Total Cycles: 103 +# ALL-NEXT: Dispatch Width: 2 +# ALL-NEXT: IPC: 0.97 + +# ALL: Instruction Info: +# ALL-NEXT: [1]: #uOps +# ALL-NEXT: [2]: Latency +# ALL-NEXT: [3]: RThroughput +# ALL-NEXT: [4]: MayLoad +# ALL-NEXT: [5]: MayStore +# ALL-NEXT: [6]: HasSideEffects + +# ALL: [1] [2] [3] [4] [5] [6] Instructions: +# ALL-NEXT: 1 1 0.50 addl %eax, %eax + +# FULLREPORT: Dynamic Dispatch Stall Cycles: +# FULLREPORT-NEXT: RAT - Register unavailable: 0 +# FULLREPORT-NEXT: RCU - Retire tokens unavailable: 0 +# FULLREPORT-NEXT: SCHEDQ - Scheduler full: 61 +# FULLREPORT-NEXT: LQ - Load queue full: 0 +# FULLREPORT-NEXT: SQ - Store queue full: 0 +# FULLREPORT-NEXT: GROUP - Static restrictions on the dispatch group: 0 + +# FULLREPORT: Dispatch Logic - number of cycles where we saw N instructions dispatched: +# FULLREPORT-NEXT: [# dispatched], [# cycles] +# FULLREPORT-NEXT: 0, 22 (21.4%) +# FULLREPORT-NEXT: 2, 19 (18.4%) +# FULLREPORT-NEXT: 1, 62 (60.2%) + +# FULLREPORT: Schedulers - number of cycles where we saw N instructions issued: +# FULLREPORT-NEXT: [# issued], [# cycles] +# FULLREPORT-NEXT: 0, 3 (2.9%) +# FULLREPORT-NEXT: 1, 100 (97.1%) + +# FULLREPORT: Scheduler's queue usage: +# FULLREPORT-NEXT: JALU01, 20/20 +# FULLREPORT-NEXT: JFPU01, 0/18 +# FULLREPORT-NEXT: JLSAGU, 0/12 + +# FULLREPORT: Retire Control Unit - number of cycles where we saw N instructions retired: +# FULLREPORT-NEXT: [# retired], [# cycles] +# FULLREPORT-NEXT: 0, 3 (2.9%) +# FULLREPORT-NEXT: 1, 100 (97.1%) + +# FULLREPORT: Register File statistics: +# FULLREPORT-NEXT: Total number of mappings created: 200 +# FULLREPORT-NEXT: Max number of mappings used: 44 + +# FULLREPORT: * Register File #1 -- FpuPRF: +# FULLREPORT-NEXT: Number of physical registers: 72 +# FULLREPORT-NEXT: Total number of mappings created: 0 +# FULLREPORT-NEXT: Max number of mappings used: 0 + +# FULLREPORT: * Register File #2 -- IntegerPRF: +# FULLREPORT-NEXT: Number of physical registers: 64 +# FULLREPORT-NEXT: Total number of mappings created: 200 +# FULLREPORT-NEXT: Max number of mappings used: 44 + +# FULLREPORT: Resources: +# FULLREPORT-NEXT: [0] - JALU0 +# FULLREPORT-NEXT: [1] - JALU1 +# FULLREPORT-NEXT: [2] - JDiv +# FULLREPORT-NEXT: [3] - JFPA +# FULLREPORT-NEXT: [4] - JFPM +# FULLREPORT-NEXT: [5] - JFPU0 +# FULLREPORT-NEXT: [6] - JFPU1 +# FULLREPORT-NEXT: [7] - JLAGU +# FULLREPORT-NEXT: [8] - JMul +# FULLREPORT-NEXT: [9] - JSAGU +# FULLREPORT-NEXT: [10] - JSTC +# FULLREPORT-NEXT: [11] - JVALU0 +# FULLREPORT-NEXT: [12] - JVALU1 +# FULLREPORT-NEXT: [13] - JVIMUL + +# FULLREPORT: Resource pressure per iteration: +# FULLREPORT-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] +# FULLREPORT-NEXT: 0.50 0.50 - - - - - - - - - - - - + +# FULLREPORT: Resource pressure by instruction: +# FULLREPORT-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: +# FULLREPORT-NEXT: 0.50 0.50 - - - - - - - - - - - - addl %eax, %eax + diff --git a/llvm/test/tools/llvm-mca/X86/option-all-stats-2.s b/llvm/test/tools/llvm-mca/X86/option-all-stats-2.s new file mode 100644 index 00000000000..1266d713d8c --- /dev/null +++ b/llvm/test/tools/llvm-mca/X86/option-all-stats-2.s @@ -0,0 +1,93 @@ +# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-stats -dispatch-stats=false < %s | FileCheck %s -check-prefix=ALL +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-stats < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULL +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-stats -dispatch-stats < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULL +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -dispatch-stats -all-stats < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULL +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -dispatch-stats=false -all-stats < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULL + +add %eax, %eax + +# ALL: Iterations: 100 +# ALL-NEXT: Instructions: 100 +# ALL-NEXT: Total Cycles: 103 +# ALL-NEXT: Dispatch Width: 2 +# ALL-NEXT: IPC: 0.97 + +# ALL: Instruction Info: +# ALL-NEXT: [1]: #uOps +# ALL-NEXT: [2]: Latency +# ALL-NEXT: [3]: RThroughput +# ALL-NEXT: [4]: MayLoad +# ALL-NEXT: [5]: MayStore +# ALL-NEXT: [6]: HasSideEffects + +# ALL: [1] [2] [3] [4] [5] [6] Instructions: +# ALL-NEXT: 1 1 0.50 addl %eax, %eax + +# FULL: Dynamic Dispatch Stall Cycles: +# FULL-NEXT: RAT - Register unavailable: 0 +# FULL-NEXT: RCU - Retire tokens unavailable: 0 +# FULL-NEXT: SCHEDQ - Scheduler full: 61 +# FULL-NEXT: LQ - Load queue full: 0 +# FULL-NEXT: SQ - Store queue full: 0 +# FULL-NEXT: GROUP - Static restrictions on the dispatch group: 0 + +# FULL: Dispatch Logic - number of cycles where we saw N instructions dispatched: +# FULL-NEXT: [# dispatched], [# cycles] +# FULL-NEXT: 0, 22 (21.4%) +# FULL-NEXT: 2, 19 (18.4%) +# FULL-NEXT: 1, 62 (60.2%) + +# FULL: Schedulers - number of cycles where we saw N instructions issued: +# FULL-NEXT: [# issued], [# cycles] +# FULL-NEXT: 0, 3 (2.9%) +# FULL-NEXT: 1, 100 (97.1%) + +# FULL: Scheduler's queue usage: +# FULL-NEXT: JALU01, 20/20 +# FULL-NEXT: JFPU01, 0/18 +# FULL-NEXT: JLSAGU, 0/12 + +# FULL: Retire Control Unit - number of cycles where we saw N instructions retired: +# FULL-NEXT: [# retired], [# cycles] +# FULL-NEXT: 0, 3 (2.9%) +# FULL-NEXT: 1, 100 (97.1%) + +# FULL: Register File statistics: +# FULL-NEXT: Total number of mappings created: 200 +# FULL-NEXT: Max number of mappings used: 44 + +# FULL: * Register File #1 -- FpuPRF: +# FULL-NEXT: Number of physical registers: 72 +# FULL-NEXT: Total number of mappings created: 0 +# FULL-NEXT: Max number of mappings used: 0 + +# FULL: * Register File #2 -- IntegerPRF: +# FULL-NEXT: Number of physical registers: 64 +# FULL-NEXT: Total number of mappings created: 200 +# FULL-NEXT: Max number of mappings used: 44 + +# FULL: Resources: +# FULL-NEXT: [0] - JALU0 +# FULL-NEXT: [1] - JALU1 +# FULL-NEXT: [2] - JDiv +# FULL-NEXT: [3] - JFPA +# FULL-NEXT: [4] - JFPM +# FULL-NEXT: [5] - JFPU0 +# FULL-NEXT: [6] - JFPU1 +# FULL-NEXT: [7] - JLAGU +# FULL-NEXT: [8] - JMul +# FULL-NEXT: [9] - JSAGU +# FULL-NEXT: [10] - JSTC +# FULL-NEXT: [11] - JVALU0 +# FULL-NEXT: [12] - JVALU1 +# FULL-NEXT: [13] - JVIMUL + +# FULL: Resource pressure per iteration: +# FULL-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] +# FULL-NEXT: 0.50 0.50 - - - - - - - - - - - - + +# FULL: Resource pressure by instruction: +# FULL-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: +# FULL-NEXT: 0.50 0.50 - - - - - - - - - - - - addl %eax, %eax + diff --git a/llvm/test/tools/llvm-mca/X86/option-all-views-1.s b/llvm/test/tools/llvm-mca/X86/option-all-views-1.s new file mode 100644 index 00000000000..5baaca3a29e --- /dev/null +++ b/llvm/test/tools/llvm-mca/X86/option-all-views-1.s @@ -0,0 +1,116 @@ +# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-views < %s | FileCheck %s -check-prefix=ALL -check-prefix=DEFAULTREPORT -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-views=true < %s | FileCheck %s -check-prefix=ALL -check-prefix=DEFAULTREPORT -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-views=false < %s | FileCheck %s -check-prefix=ALL -check-prefix=NOREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 < %s | FileCheck %s -check-prefix=ALL -check-prefix=DEFAULTREPORT + +add %eax, %eax + +# ALL: Iterations: 100 +# ALL-NEXT: Instructions: 100 +# ALL-NEXT: Total Cycles: 103 +# ALL-NEXT: Dispatch Width: 2 +# ALL-NEXT: IPC: 0.97 + +# DEFAULTREPORT: Instruction Info: +# DEFAULTREPORT-NEXT: [1]: #uOps +# DEFAULTREPORT-NEXT: [2]: Latency +# DEFAULTREPORT-NEXT: [3]: RThroughput +# DEFAULTREPORT-NEXT: [4]: MayLoad +# DEFAULTREPORT-NEXT: [5]: MayStore +# DEFAULTREPORT-NEXT: [6]: HasSideEffects + +# DEFAULTREPORT: [1] [2] [3] [4] [5] [6] Instructions: +# DEFAULTREPORT-NEXT: 1 1 0.50 addl %eax, %eax + +# FULLREPORT: Dynamic Dispatch Stall Cycles: +# FULLREPORT-NEXT: RAT - Register unavailable: 0 +# FULLREPORT-NEXT: RCU - Retire tokens unavailable: 0 +# FULLREPORT-NEXT: SCHEDQ - Scheduler full: 61 +# FULLREPORT-NEXT: LQ - Load queue full: 0 +# FULLREPORT-NEXT: SQ - Store queue full: 0 +# FULLREPORT-NEXT: GROUP - Static restrictions on the dispatch group: 0 + +# FULLREPORT: Dispatch Logic - number of cycles where we saw N instructions dispatched: +# FULLREPORT-NEXT: [# dispatched], [# cycles] +# FULLREPORT-NEXT: 0, 22 (21.4%) +# FULLREPORT-NEXT: 2, 19 (18.4%) +# FULLREPORT-NEXT: 1, 62 (60.2%) + +# FULLREPORT: Schedulers - number of cycles where we saw N instructions issued: +# FULLREPORT-NEXT: [# issued], [# cycles] +# FULLREPORT-NEXT: 0, 3 (2.9%) +# FULLREPORT-NEXT: 1, 100 (97.1%) + +# FULLREPORT: Scheduler's queue usage: +# FULLREPORT-NEXT: JALU01, 20/20 +# FULLREPORT-NEXT: JFPU01, 0/18 +# FULLREPORT-NEXT: JLSAGU, 0/12 + +# FULLREPORT: Retire Control Unit - number of cycles where we saw N instructions retired: +# FULLREPORT-NEXT: [# retired], [# cycles] +# FULLREPORT-NEXT: 0, 3 (2.9%) +# FULLREPORT-NEXT: 1, 100 (97.1%) + +# FULLREPORT: Register File statistics: +# FULLREPORT-NEXT: Total number of mappings created: 200 +# FULLREPORT-NEXT: Max number of mappings used: 44 + +# FULLREPORT: * Register File #1 -- FpuPRF: +# FULLREPORT-NEXT: Number of physical registers: 72 +# FULLREPORT-NEXT: Total number of mappings created: 0 +# FULLREPORT-NEXT: Max number of mappings used: 0 + +# FULLREPORT: * Register File #2 -- IntegerPRF: +# FULLREPORT-NEXT: Number of physical registers: 64 +# FULLREPORT-NEXT: Total number of mappings created: 200 +# FULLREPORT-NEXT: Max number of mappings used: 44 + +# FULLREPORT: Resources: +# FULLREPORT-NEXT: [0] - JALU0 +# FULLREPORT-NEXT: [1] - JALU1 +# FULLREPORT-NEXT: [2] - JDiv +# FULLREPORT-NEXT: [3] - JFPA +# FULLREPORT-NEXT: [4] - JFPM +# FULLREPORT-NEXT: [5] - JFPU0 +# FULLREPORT-NEXT: [6] - JFPU1 +# FULLREPORT-NEXT: [7] - JLAGU +# FULLREPORT-NEXT: [8] - JMul +# FULLREPORT-NEXT: [9] - JSAGU +# FULLREPORT-NEXT: [10] - JSTC +# FULLREPORT-NEXT: [11] - JVALU0 +# FULLREPORT-NEXT: [12] - JVALU1 +# FULLREPORT-NEXT: [13] - JVIMUL + +# FULLREPORT: Resource pressure per iteration: +# FULLREPORT-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] +# FULLREPORT-NEXT: 0.50 0.50 - - - - - - - - - - - - + +# FULLREPORT: Resource pressure by instruction: +# FULLREPORT-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: +# FULLREPORT-NEXT: 0.50 0.50 - - - - - - - - - - - - addl %eax, %eax + +# FULLREPORT: Timeline view: +# FULLREPORT-NEXT: 012 +# FULLREPORT-NEXT: Index 0123456789 + +# FULLREPORT: [0,0] DeER . . . addl %eax, %eax +# FULLREPORT-NEXT: [1,0] D=eER. . . addl %eax, %eax +# FULLREPORT-NEXT: [2,0] .D=eER . . addl %eax, %eax +# FULLREPORT-NEXT: [3,0] .D==eER . . addl %eax, %eax +# FULLREPORT-NEXT: [4,0] . D==eER . . addl %eax, %eax +# FULLREPORT-NEXT: [5,0] . D===eER . . addl %eax, %eax +# FULLREPORT-NEXT: [6,0] . D===eER. . addl %eax, %eax +# FULLREPORT-NEXT: [7,0] . D====eER . addl %eax, %eax +# FULLREPORT-NEXT: [8,0] . D====eER. addl %eax, %eax +# FULLREPORT-NEXT: [9,0] . D=====eER addl %eax, %eax + +# FULLREPORT: Average Wait times (based on the timeline view): +# FULLREPORT-NEXT: [0]: Executions +# FULLREPORT-NEXT: [1]: Average time spent waiting in a scheduler's queue +# FULLREPORT-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready +# FULLREPORT-NEXT: [3]: Average time elapsed from WB until retire stage + +# FULLREPORT: [0] [1] [2] [3] +# FULLREPORT-NEXT: 0. 10 3.5 0.1 0.0 addl %eax, %eax + diff --git a/llvm/test/tools/llvm-mca/X86/option-all-views-2.s b/llvm/test/tools/llvm-mca/X86/option-all-views-2.s new file mode 100644 index 00000000000..6780a5a6c50 --- /dev/null +++ b/llvm/test/tools/llvm-mca/X86/option-all-views-2.s @@ -0,0 +1,141 @@ +# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-views < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-views -resource-pressure < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -resource-pressure -all-views < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -resource-pressure=false -all-views < %s | FileCheck %s -check-prefix=ALL -check-prefix=FULLREPORT +# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -all-views -resource-pressure=false < %s | FileCheck %s -check-prefix=ALL -check-prefix=NORPV + +add %eax, %eax + +# ALL: Iterations: 100 +# ALL-NEXT: Instructions: 100 +# ALL-NEXT: Total Cycles: 103 +# ALL-NEXT: Dispatch Width: 2 +# ALL-NEXT: IPC: 0.97 + +# ALL: Instruction Info: +# ALL-NEXT: [1]: #uOps +# ALL-NEXT: [2]: Latency +# ALL-NEXT: [3]: RThroughput +# ALL-NEXT: [4]: MayLoad +# ALL-NEXT: [5]: MayStore +# ALL-NEXT: [6]: HasSideEffects + +# ALL: [1] [2] [3] [4] [5] [6] Instructions: +# ALL-NEXT: 1 1 0.50 addl %eax, %eax + +# ALL: Dynamic Dispatch Stall Cycles: +# ALL-NEXT: RAT - Register unavailable: 0 +# ALL-NEXT: RCU - Retire tokens unavailable: 0 +# ALL-NEXT: SCHEDQ - Scheduler full: 61 +# ALL-NEXT: LQ - Load queue full: 0 +# ALL-NEXT: SQ - Store queue full: 0 +# ALL-NEXT: GROUP - Static restrictions on the dispatch group: 0 + +# ALL: Dispatch Logic - number of cycles where we saw N instructions dispatched: +# ALL-NEXT: [# dispatched], [# cycles] +# ALL-NEXT: 0, 22 (21.4%) +# ALL-NEXT: 2, 19 (18.4%) +# ALL-NEXT: 1, 62 (60.2%) + +# ALL: Schedulers - number of cycles where we saw N instructions issued: +# ALL-NEXT: [# issued], [# cycles] +# ALL-NEXT: 0, 3 (2.9%) +# ALL-NEXT: 1, 100 (97.1%) + +# ALL: Scheduler's queue usage: +# ALL-NEXT: JALU01, 20/20 +# ALL-NEXT: JFPU01, 0/18 +# ALL-NEXT: JLSAGU, 0/12 + +# ALL: Retire Control Unit - number of cycles where we saw N instructions retired: +# ALL-NEXT: [# retired], [# cycles] +# ALL-NEXT: 0, 3 (2.9%) +# ALL-NEXT: 1, 100 (97.1%) + +# ALL: Register File statistics: +# ALL-NEXT: Total number of mappings created: 200 +# ALL-NEXT: Max number of mappings used: 44 + +# ALL: * Register File #1 -- FpuPRF: +# ALL-NEXT: Number of physical registers: 72 +# ALL-NEXT: Total number of mappings created: 0 +# ALL-NEXT: Max number of mappings used: 0 + +# ALL: * Register File #2 -- IntegerPRF: +# ALL-NEXT: Number of physical registers: 64 +# ALL-NEXT: Total number of mappings created: 200 +# ALL-NEXT: Max number of mappings used: 44 + +# FULLREPORT: Resources: +# FULLREPORT-NEXT: [0] - JALU0 +# FULLREPORT-NEXT: [1] - JALU1 +# FULLREPORT-NEXT: [2] - JDiv +# FULLREPORT-NEXT: [3] - JFPA +# FULLREPORT-NEXT: [4] - JFPM +# FULLREPORT-NEXT: [5] - JFPU0 +# FULLREPORT-NEXT: [6] - JFPU1 +# FULLREPORT-NEXT: [7] - JLAGU +# FULLREPORT-NEXT: [8] - JMul +# FULLREPORT-NEXT: [9] - JSAGU +# FULLREPORT-NEXT: [10] - JSTC +# FULLREPORT-NEXT: [11] - JVALU0 +# FULLREPORT-NEXT: [12] - JVALU1 +# FULLREPORT-NEXT: [13] - JVIMUL + +# NORPV: Timeline view: +# NORPV-NEXT: 012 +# NORPV-NEXT: Index 0123456789 + +# FULLREPORT: Resource pressure per iteration: +# FULLREPORT-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] +# FULLREPORT-NEXT: 0.50 0.50 - - - - - - - - - - - - + +# NORPV: [0,0] DeER . . . addl %eax, %eax +# NORPV-NEXT: [1,0] D=eER. . . addl %eax, %eax +# NORPV-NEXT: [2,0] .D=eER . . addl %eax, %eax +# NORPV-NEXT: [3,0] .D==eER . . addl %eax, %eax +# NORPV-NEXT: [4,0] . D==eER . . addl %eax, %eax +# NORPV-NEXT: [5,0] . D===eER . . addl %eax, %eax +# NORPV-NEXT: [6,0] . D===eER. . addl %eax, %eax +# NORPV-NEXT: [7,0] . D====eER . addl %eax, %eax +# NORPV-NEXT: [8,0] . D====eER. addl %eax, %eax +# NORPV-NEXT: [9,0] . D=====eER addl %eax, %eax + +# NORPV: Average Wait times (based on the timeline view): +# NORPV-NEXT: [0]: Executions +# NORPV-NEXT: [1]: Average time spent waiting in a scheduler's queue +# NORPV-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready +# NORPV-NEXT: [3]: Average time elapsed from WB until retire stage + +# FULLREPORT: Resource pressure by instruction: +# FULLREPORT-NEXT: [0] [1] [2] [3] [4] [5] [6] [7] [8] [9] [10] [11] [12] [13] Instructions: +# FULLREPORT-NEXT: 0.50 0.50 - - - - - - - - - - - - addl %eax, %eax + +# NORPV: [0] [1] [2] [3] +# NORPV-NEXT: 0. 10 3.5 0.1 0.0 addl %eax, %eax + +# FULLREPORT: Timeline view: +# FULLREPORT-NEXT: 012 +# FULLREPORT-NEXT: Index 0123456789 + +# FULLREPORT: [0,0] DeER . . . addl %eax, %eax +# FULLREPORT-NEXT: [1,0] D=eER. . . addl %eax, %eax +# FULLREPORT-NEXT: [2,0] .D=eER . . addl %eax, %eax +# FULLREPORT-NEXT: [3,0] .D==eER . . addl %eax, %eax +# FULLREPORT-NEXT: [4,0] . D==eER . . addl %eax, %eax +# FULLREPORT-NEXT: [5,0] . D===eER . . addl %eax, %eax +# FULLREPORT-NEXT: [6,0] . D===eER. . addl %eax, %eax +# FULLREPORT-NEXT: [7,0] . D====eER . addl %eax, %eax +# FULLREPORT-NEXT: [8,0] . D====eER. addl %eax, %eax +# FULLREPORT-NEXT: [9,0] . D=====eER addl %eax, %eax + +# FULLREPORT: Average Wait times (based on the timeline view): +# FULLREPORT-NEXT: [0]: Executions +# FULLREPORT-NEXT: [1]: Average time spent waiting in a scheduler's queue +# FULLREPORT-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready +# FULLREPORT-NEXT: [3]: Average time elapsed from WB until retire stage + +# FULLREPORT: [0] [1] [2] [3] +# FULLREPORT-NEXT: 0. 10 3.5 0.1 0.0 addl %eax, %eax + diff --git a/llvm/tools/llvm-mca/llvm-mca.cpp b/llvm/tools/llvm-mca/llvm-mca.cpp index 51d6ad1d984..451ea07ceb5 100644 --- a/llvm/tools/llvm-mca/llvm-mca.cpp +++ b/llvm/tools/llvm-mca/llvm-mca.cpp @@ -154,6 +154,15 @@ static cl::opt<bool> PrintInstructionInfoView( cl::desc("Print the instruction info view (enabled by default)"), cl::cat(ViewOptions), cl::init(true)); +static cl::opt<bool> EnableAllStats("all-stats", + cl::desc("Print all hardware statistics"), + cl::cat(ViewOptions), cl::init(false)); + +static cl::opt<bool> + EnableAllViews("all-views", + cl::desc("Print all views including hardware statistics"), + cl::cat(ViewOptions), cl::init(false)); + namespace { const Target *getTarget(const char *ProgName) { @@ -273,6 +282,32 @@ public: }; } // end of anonymous namespace +static void processOptionImpl(cl::opt<bool> &O, const cl::opt<bool> &Default) { + if (!O.getNumOccurrences() || O.getPosition() < Default.getPosition()) + O = Default.getValue(); +} + +static void processViewOptions() { + if (!EnableAllViews.getNumOccurrences() && + !EnableAllStats.getNumOccurrences()) + return; + + if (EnableAllViews.getNumOccurrences()) { + processOptionImpl(PrintResourcePressureView, EnableAllViews); + processOptionImpl(PrintTimelineView, EnableAllViews); + processOptionImpl(PrintInstructionInfoView, EnableAllViews); + } + + const cl::opt<bool> &Default = + EnableAllViews.getPosition() < EnableAllStats.getPosition() + ? EnableAllStats + : EnableAllViews; + processOptionImpl(PrintRegisterFileStats, Default); + processOptionImpl(PrintDispatchStats, Default); + processOptionImpl(PrintSchedulerStats, Default); + processOptionImpl(PrintRetireStats, Default); +} + int main(int argc, char **argv) { InitLLVM X(argc, argv); @@ -309,6 +344,9 @@ int main(int argc, char **argv) { return 1; } + // Apply overrides to llvm-mca specific options. + processViewOptions(); + SourceMgr SrcMgr; // Tell SrcMgr about this buffer, which is what the parser will pick up. |
