## This script checks that perf2bolt is reading pre-aggregated perf information ## correctly for a simple example. The perf.data of this example was generated ## with the following command: ## ## $ perf record -j any,u -e branch -o perf.data -- ./blarge ## ## blarge is the binary for "basicmath large inputs" taken from Mibench. ## Currently failing in MacOS / generating different hash for usqrt REQUIRES: system-linux RUN: yaml2obj %p/Inputs/blarge.yaml &> %t.exe RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated.txt -w %t.new \ RUN: --show-density --heatmap %t.hm \ RUN: --profile-density-threshold=9 --profile-density-cutoff-hot=970000 \ RUN: --profile-use-dfs | FileCheck %s --check-prefix=CHECK-P2B RUN: FileCheck --input-file %t.hm-section-hotness.csv --check-prefix=CHECK-HM %s CHECK-P2B: HEATMAP: building heat map CHECK-P2B: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile CHECK-P2B: BOLT-INFO: Functions with density >= 21.7 account for 97.00% total sample counts. CHECK-HM: .text, 0x400680, 0x401232, 100.0000, 4.2553, 0.0426 RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated.txt -w %t.new \ RUN: --show-density \ RUN: --profile-density-cutoff-hot=970000 \ RUN: --profile-use-dfs 2>&1 | FileCheck %s --check-prefix=CHECK-WARNING CHECK-WARNING: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile CHECK-WARNING: BOLT-WARNING: BOLT is estimated to optimize better with 2.8x more samples. CHECK-WARNING: BOLT-INFO: Functions with density >= 21.7 account for 97.00% total sample counts. RUN: llvm-bolt %t.exe -data %t -o %t.null | FileCheck %s RUN: llvm-bolt %t.exe -data %t.new -o %t.null | FileCheck %s RUN: llvm-bolt %t.exe -p %p/Inputs/pre-aggregated.txt --pa -o %t.null | FileCheck %s RUN: llvm-bolt %t.exe --pa -perfdata %p/Inputs/pre-aggregated.txt -perfdata %p/Inputs/pre-aggregated.txt -o %t.multi-perfdata.null | FileCheck %s --check-prefix=CHECK-MULTI RUN: llvm-bolt %t.exe --pa -p %p/Inputs/pre-aggregated.txt,%p/Inputs/pre-aggregated.txt -o %t.multi-perfdata-comma.null | FileCheck %s --check-prefix=CHECK-MULTI RUN: not llvm-bolt %t.exe --pa -p %p/Inputs/pre-aggregated.txt -p %t.missing -o %t.multi-perfdata-missing.null 2>&1 | FileCheck %s --check-prefix=CHECK-MISSING CHECK: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile CHECK-MULTI: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile CHECK-MISSING: {{.*}}missing': No such file or directory. RUN: FileCheck %s -check-prefix=PERF2BOLT --input-file %t RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.new ## Test --profile-format option with perf2bolt RUN: perf2bolt %t.exe -o %t.fdata --pa -p %p/Inputs/pre-aggregated.txt \ RUN: --profile-format=fdata RUN: FileCheck %s -check-prefix=PERF2BOLT --input-file %t.fdata RUN: perf2bolt %t.exe -o %t.yaml --pa -p %p/Inputs/pre-aggregated.txt \ RUN: --profile-format=yaml --profile-use-dfs RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.yaml ## Test --profile-format option with llvm-bolt --aggregate-only RUN: llvm-bolt %t.exe -o %t.bolt.fdata --pa -p %p/Inputs/pre-aggregated.txt \ RUN: --aggregate-only --profile-format=fdata RUN: FileCheck %s -check-prefix=PERF2BOLT --input-file %t.bolt.fdata RUN: llvm-bolt %t.exe -o %t.bolt.yaml --pa -p %p/Inputs/pre-aggregated.txt \ RUN: --aggregate-only --profile-format=yaml --profile-use-dfs RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.bolt.yaml ## Test pre-aggregated basic profile RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated-basic.txt -o %t.ba \ RUN: 2>&1 | FileCheck %s --check-prefix=BASIC-ERROR RUN: perf2bolt %t.exe -o %t --pa -p %p/Inputs/pre-aggregated-basic.txt -o %t.ba.nl \ RUN: -ba 2>&1 | FileCheck %s --check-prefix=BASIC-SUCCESS RUN: FileCheck %s --input-file %t.ba.nl --check-prefix CHECK-BASIC-BA BASIC-ERROR: BOLT-INFO: 0 out of 7 functions in the binary (0.0%) have non-empty execution profile BASIC-SUCCESS: BOLT-INFO: 4 out of 7 functions in the binary (57.1%) have non-empty execution profile CHECK-BASIC-BA: no_lbr cycles PERF2BOLT: 1 frame_dummy/1 1e 1 frame_dummy/1 0 0 1 PERF2BOLT-NEXT: 1 main 451 1 SolveCubic 0 0 2 PERF2BOLT-NEXT: 1 main 490 0 [unknown] 0 0 1 PERF2BOLT-NEXT: 1 main 537 0 [unknown] 0 0 1 PERF2BOLT-NEXT: 0 [unknown] 0 1 main 53c 0 2 PERF2BOLT-NEXT: 1 usqrt a 1 usqrt 10 0 22 PERF2BOLT-NEXT: 1 usqrt 30 1 usqrt 32 0 22 PERF2BOLT-NEXT: 1 usqrt 30 1 usqrt 39 4 33 PERF2BOLT-NEXT: 1 usqrt 35 1 usqrt 39 0 22 PERF2BOLT-NEXT: 1 usqrt 3d 1 usqrt 10 0 58 PERF2BOLT-NEXT: 1 usqrt 3d 1 usqrt 3f 0 22 NEWFORMAT: - name: 'frame_dummy/1' NEWFORMAT: fid: 3 NEWFORMAT: hash: 0x28C72085C0BD8D37 NEWFORMAT: exec: 1 NEWFORMAT: - name: usqrt NEWFORMAT: fid: 7 NEWFORMAT: exec: 0 NEWFORMAT: nblocks: 5 NEWFORMAT: blocks: NEWFORMAT: - bid: 0 NEWFORMAT: insns: 4 NEWFORMAT: succ: [ { bid: 1, cnt: 22 } ] NEWFORMAT: - bid: 1 NEWFORMAT: insns: 9 NEWFORMAT: succ: [ { bid: 3, cnt: 33, mis: 4 }, { bid: 2, cnt: 22 } ] NEWFORMAT: - bid: 2 NEWFORMAT: insns: 2 NEWFORMAT: succ: [ { bid: 3, cnt: 22 } ] NEWFORMAT: - bid: 3 NEWFORMAT: insns: 2 NEWFORMAT: succ: [ { bid: 1, cnt: 58 }, { bid: 4, cnt: 22 } ]