intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-13 19:08:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BOLT] Add --ba flag to deprecate --nl (#164257)

Browse Source 
The `--nl` flag, originally for Non-LBR mode, is deprecated and will be
replaced by `--basic-events` (alias `--ba`).

`--nl` remains as a deprecated alias for backward compatibility.
This commit is contained in:
Paschalis Mpeis
2025-10-23 10:13:28 +01:00
committed by GitHub
parent 7f66c31fab
commit ae6cb98b29
8 changed files with 30 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
bolt/README.md
View File

@@ -164,7 +164,7 @@ $ perf2bolt -p perf.data -o perf.fdata <executable>
This command will aggregate branch data from `perf.data` and store it in a
format that is both more compact and more resilient to binary modifications.
If the profile was collected without brstacks, you will need to add `-nl` flag to
If the profile was collected without brstacks, you will need to add `-ba` flag to
the command line above.
### Step 3: Optimize with BOLT

2
bolt/docs/Heatmaps.md
View File

@@ -21,7 +21,7 @@ $ perf record -e cycles:u -j any,u [-p PID|-a] -- sleep <interval>
```
Running with brstack (`-j any,u` or `-b`) is recommended. Heatmaps can be generated
from basic events by using the llvm-bolt-heatmap option `-nl` (no brstack) but
from basic events by using the llvm-bolt-heatmap option `-ba` (basic events) but
such heatmaps do not have the coverage provided by brstack and may only be useful
for finding event hotspots at larger code block granularities.

4
bolt/docs/index.rst
View File

@@ -205,8 +205,8 @@ This command will aggregate branch data from ``perf.data`` and store it
in a format that is both more compact and more resilient to binary
modifications.
If the profile was collected without LBRs, you will need to add ``-nl``
flag to the command line above.
If the profile was collected without brstacks, you will need to add `-ba` flag to
the command line above.
Step 3: Optimize with BOLT
~~~~~~~~~~~~~~~~~~~~~~~~~~

23
bolt/lib/Profile/DataAggregator.cpp
View File

@@ -45,10 +45,23 @@ using namespace bolt;
namespace opts {
static cl::opt<bool>
BasicAggregation("nl",
cl::desc("aggregate basic samples (without brstack info)"),
BasicAggregation("basic-events",
cl::desc("aggregate basic events (without brstack info)"),
cl::cat(AggregatorCategory));
static cl::alias BasicAggregationAlias("ba",
cl::desc("Alias for --basic-events"),
cl::aliasopt(BasicAggregation));
static cl::opt<bool> DeprecatedBasicAggregationNl(
"nl", cl::desc("Alias for --basic-events (deprecated. Use --ba)"),
cl::cat(AggregatorCategory), cl::ReallyHidden,
cl::callback([](const bool &Enabled) {
errs()
<< "BOLT-WARNING: '-nl' is deprecated, please use '--ba' instead.\n";
BasicAggregation = Enabled;
}));
cl::opt<bool> ArmSPE("spe", cl::desc("Enable Arm SPE mode."),
cl::cat(AggregatorCategory));
@@ -1433,7 +1446,7 @@ std::error_code DataAggregator::printLBRHeatMap() {
"Cannot build heatmap.";
} else {
errs() << "HEATMAP-ERROR: no brstack traces detected in profile. "
"Cannot build heatmap. Use -nl for building heatmap from "
"Cannot build heatmap. Use -ba for building heatmap from "
"basic events.\n";
}
exit(1);
@@ -1629,8 +1642,8 @@ std::error_code DataAggregator::parseBranchEvents() {
<< "PERF2BOLT-WARNING: all recorded samples for this binary lack "
"brstack. Record profile with perf record -j any or run "
"perf2bolt "
"in non-brstack mode with -nl (the performance improvement in "
"-nl "
"in non-brstack mode with -ba (the performance improvement in "
"-ba "
"mode may be limited)\n";
else
errs()

2
bolt/test/X86/nolbr.s
View File

@@ -10,7 +10,7 @@
# RUN: FileCheck %s --input-file %t.fdata --check-prefix=CHECK-FDATA
# RUN: llvm-strip --strip-unneeded %t.o
# RUN: %clang %cflags %t.o -o %t.exe -Wl,-q -nostdlib
# RUN: llvm-bolt %t.exe -o %t.out --data %t.fdata --dyno-stats -nl \
# RUN: llvm-bolt %t.exe -o %t.out --data %t.fdata --dyno-stats -ba \
# RUN: --print-only=_start 2>&1 | FileCheck %s --check-prefix=CHECK-BOLT
# CHECK-FDATA: no_lbr

6
bolt/test/X86/pre-aggregated-perf.test
View File

@@ -61,11 +61,11 @@ RUN: FileCheck %s -check-prefix=NEWFORMAT --input-file %t.bolt.yaml
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: -nl 2>&1 | FileCheck %s --check-prefix=BASIC-SUCCESS
RUN: FileCheck %s --input-file %t.ba.nl --check-prefix CHECK-BASIC-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-NL: no_lbr cycles
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

4
bolt/test/perf2bolt/perf_test.test
View File

@@ -4,7 +4,7 @@ REQUIRES: system-linux, perf
RUN: %clang %S/Inputs/perf_test.c -fuse-ld=lld -pie -Wl,--script=%S/Inputs/perf_test.lds -o %t
RUN: perf record -Fmax -e cycles:u -o %t2 -- %t
RUN: perf2bolt %t -p=%t2 -o %t3 -nl -ignore-build-id --show-density \
RUN: perf2bolt %t -p=%t2 -o %t3 -ba -ignore-build-id --show-density \
RUN: --heatmap %t.hm 2>&1 | FileCheck %s
RUN: FileCheck %s --input-file %t.hm-section-hotness.csv --check-prefix=CHECK-HM
@@ -15,7 +15,7 @@ CHECK: BOLT-INFO: Functions with density >= {{.*}} account for 99.00% total samp
RUN: %clang %S/Inputs/perf_test.c -no-pie -fuse-ld=lld -o %t4
RUN: perf record -Fmax -e cycles:u -o %t5 -- %t4
RUN: perf2bolt %t4 -p=%t5 -o %t6 -nl -ignore-build-id --show-density \
RUN: perf2bolt %t4 -p=%t5 -o %t6 -ba -ignore-build-id --show-density \
RUN: --heatmap %t.hm2 2>&1 | FileCheck %s
RUN: FileCheck %s --input-file %t.hm2-section-hotness.csv --check-prefix=CHECK-HM

4
clang/utils/perf-training/perf-helper.py
View File

@@ -133,7 +133,7 @@ def perf2bolt(args):
"--profile-format=yaml",
]
if not opts.lbr:
p2b_args += ["-nl"]
p2b_args += ["-ba"]
p2b_args += ["-p"]
for filename in findFilesWithExtension(opts.path, "perf.data"):
subprocess.check_call(p2b_args + [filename, "-o", filename + ".fdata"])
@@ -722,7 +722,7 @@ def bolt_optimize(args):
"-dyno-stats",
"-use-gnu-stack",
"-update-debug-sections",
"-nl" if opts.method == "PERF" else "",
"-ba" if opts.method == "PERF" else "",
]
print("Running: " + " ".join(args))
process = subprocess.run(