LLVM-PROFDATA(1)

📦 version 23.1.3, in centos-stream 9

💅 LLVM-PROFDATA(1) — the `llvm-profdata` glow-up from the LLVM manual ✨

🎀 NAME

llvm-profdata — Profile data tool. That's the whole vibe: it's a small utility for working with profile data files, and it's literally here to make your profile files make sense. No cap.

✨ SYNOPSIS

llvm-profdata command [args...]

🫶 DESCRIPTION

The llvm-profdata tool is a small utility for working with profile data files. It's giving “small but mighty” and it wants to be your profile-data bestie. 💖

👑 COMMANDS

merge
show
overlap
order

🎀 MERGE

🦋 SYNOPSIS

llvm-profdata merge [options] [filename...]

🌸 DESCRIPTION

llvm-profdata merge takes several profile data files generated by PGO instrumentation and merges them together into a single indexed profile data file. That's the main character move. 👑

By default, profile data is merged without modification. This means the relative importance of each input file is proportional to the number of samples or counts it contains. In general, input from a longer training run will be interpreted as relatively more important than a shorter run. Depending on the nature of the training runs, it may be useful to adjust the weight given to each input file by using the -weighted-input option. Weighted input is the glow-up here.

Profiles passed in via -weighted-input, -input-files, or via positional arguments are processed once for each time they are seen. Yes, once per appearance — it's counting, not deduping.

✨ OPTIONS ✨

--help — Print a summary of command line options. A little help never hurts, bestie. 🫶
--output=<output>, -o — Specify the output file name. Output cannot be - as the resulting indexed profile data can't be written to standard output. So no piping the indexed profile to stdout — it's not that kind of party.
--weighted-input=<weight,filename> — Specify an input file name along with a weight. The profile counts of the supplied filename will be scaled (multiplied) by the supplied weight, where weight is a decimal integer >= 1. Input files specified without using this option are assigned a default weight of 1. Examples are shown below. This is how you tell one profile it's the favorite child.
--input-files=<path>, -f — Specify a file which contains a list of files to merge. The entries in this file are newline-separated. Lines starting with # are skipped. Entries may be of the form <filename> or <weight>,<filename>. List-ception, but make it profile merging.
--remapping-file=<path>, -r — Specify a file which contains a remapping from symbol names in the input profile to the symbol names that should be used in the output profile. The file should consist of lines of the form <input-symbol> <output-symbol>. Blank lines and lines starting with # are skipped.

The llvm-cxxmap tool can be used to generate the symbol remapping file. Symbol remapping: because names change and we adapt.

--instr (default) — Specify that the input profile is an instrumentation-based profile. Default behavior, already slaying.
--sample — Specify that the input profile is a sample-based profile.

The format of the generated file can be generated in one of three ways:

--binary (default) — Emit the profile using a binary encoding. For instrumentation-based profile the output format is the indexed binary format.
--extbinary — Emit the profile using an extensible binary encoding. This option can only be used with sample-based profile. The extensible binary encoding can be more compact with compression enabled and can be loaded faster than the default binary encoding.
--text — Emit the profile in text mode. This option can also be used with both sample-based and instrumentation-based profile. When this option is used the profile will be dumped in the text format that is parsable by the profile reader.
--gcc — Emit the profile using GCC's gcov format (Not yet supported).
--sparse[=true|false] — Do not emit function records with 0 execution count. Can only be used in conjunction with -instr. Defaults to false, since it can inhibit compiler optimization during PGO. Careful: this can mess with optimization, so don't just flip it for fun.
--num-threads=<N>, -j — Use N threads to perform profile merging. When N=0, llvm-profdata auto-detects an appropriate number of threads to use. This is the default. Multi-threaded merging: because waiting is not the vibe.
--failure-mode=[any|all] — Set the failure mode. There are two options: 'any' causes the merge command to fail if any profiles are invalid, and 'all' causes the merge command to fail only if all profiles are invalid. If 'all' is set, information from any invalid profiles is excluded from the final merged product. The default failure mode is 'any'. Choose your chaos: fail fast-ish or fail only when everything is cursed.
--prof-sym-list=<path> — Specify a file which contains a list of symbols to generate profile symbol list in the profile. This option can only be used with sample-based profile in extbinary format. The entries in this file are newline-separated. Symbol list, but only for the extbinary sample-profile girlies.
--compress-all-sections=[true|false] — Compress all sections when writing the profile. This option can only be used with sample-based profile in extbinary format. Compression: smaller file, same energy.
--use-md5=[true|false] — Use MD5 to represent string in name table when writing the profile. This option can only be used with sample-based profile in extbinary format. MD5 in the name table, if that's your thing.
--gen-partial-profile=[true|false] — Mark the profile to be a partial profile which only provides partial profile coverage for the optimized target. This option can only be used with sample-based profile in extbinary format. Partial profile, partial coverage, full vibe.
--split-layout=[true|false] — Split the profile data section to two with one containing sample profiles with inlined functions and the other not. This option can only be used with sample-based profile in extbinary format. Two sections, one with inlined functions and one without. Organized.
--convert-sample-profile-layout=[nest|flat] — Convert the merged profile into a profile with a new layout. Supported layout are nest (Nested profile, the input should be CS flat profile) and flat (Profile with nested inlinees flattened out). nest vs flat: pick your layout era.
--supplement-instr-with-sample=<file> — Supplement an instrumentation profile with sample profile. The sample profile is the input of the flag. Output will be in instrumentation format (only works with -instr). Instrumentation + samples, a collab.
--zero-counter-threshold=<float> — For the function which is cold in instr profile but hot in sample profile, if the ratio of the number of zero counters divided by the total number of counters is above the threshold, the profile of the function will be regarded as being harmful for performance and will be dropped. Cold in instr, hot in sample, too many zero counters? Dropped. It's giving “not helping, bestie.”
--instr-prof-cold-threshold=<int> — User specified cold threshold for instr profile which will override the cold threshold got from profile summary. Your threshold, your rules.
--suppl-min-size-threshold=<int> — If the size of a function is smaller than the threshold, assume it can be inlined by PGO early inliner and it will not be adjusted based on sample profile. Tiny functions get the early-inliner assumption.
--debug-info=<path> — Specify the executable or .dSYM that contains debug info for the raw profile. When --debug-info-correlate or --profile-correlate=debug-info was used for instrumentation, use this option to correlate the raw profile. Debug info correlation, unlocked.
--binary-file=<path> — Specify the executable that contains profile data and profile name sections for the raw profile. When -profile-correlate=binary was used for instrumentation, use this option to correlate the raw profile. Binary correlation: point it at the executable.
--debuginfod — Use debuginfod to find the associated executables that contain profile data and name sections for the raw profiles to correlate them. When -profile-correlate=binary was used for instrumentation, this option can be used for correlation. debuginfod does the finding for you.
--debug-file-directory=<dir> — Use provided local directories to search for executables that contain profile data and name sections for the raw profiles to correlate them. When -profile-correlate=binary was used for instrumentation, this option can be used for correlation. Local directory search, no cap.
--correlate=<kind> — Specify the correlation kind (debug_info or binary) to use when -debuginfod or -debug-file-directory=<dir> option is provided. Pick the correlation kind when you're using the finder options.
--temporal-profile-trace-reservoir-size — The maximum number of temporal profile traces to be stored in the output profile. If more traces are added, we will use reservoir sampling to select which traces to keep. Note that changing this value between different merge invocations on the same indexed profile could result in sample bias. The default value is 100. Reservoir sampling: only 100 traces stay by default, and changing this between merge invocations on the same indexed profile can bias your samples.
--temporal-profile-max-trace-length — The maximum number of functions in a single temporal profile trace. Longer traces will be truncated. The default value is 1000. Trace too long? Truncated at 1000 functions by default.
--function=<string> — Only keep functions matching the regex in the output, all others are erased from the profile. Regex filter, keep-only mode.
--no-function=<string> — Remove functions matching the regex from the profile. If both --function and --no-function are specified and a function matches both, it is removed. If both filters match, removal wins. Bye.

🍓 EXAMPLES

🌸 Basic Usage

Merge three profiles:

llvm-profdata merge foo.profdata bar.profdata baz.profdata -output merged.profdata

🦋 Weighted Input

The input file foo.profdata is especially important, multiply its counts by 10:

llvm-profdata merge --weighted-input=10,foo.profdata bar.profdata baz.profdata --output merged.profdata

Exactly equivalent to the previous invocation (explicit form; useful for programmatic invocation):

llvm-profdata merge --weighted-input=10,foo.profdata --weighted-input=1,bar.profdata --weighted-input=1,baz.profdata --output merged.profdata

SHOW 💅

SYNOPSIS ✨

llvm-profdata show [options] [filename]

DESCRIPTION 🫶

Okay so llvm-profdata show is the main character that takes a profile data file and spills all the tea about the profile counters — for the file itself and for any of the specified function(s). 💖

If filename is omitted or is -, then llvm-profdata show reads its input from standard input. No cap.

OPTIONS 🎀

--all-functions — print details for every single function. Literally all of them.
--binary-ids — print embedded binary ids in a profile.
--counts — print the counter values for the displayed functions.
--show-format=<text|json|yaml> — emit output in the selected format if it's supported by the provided profile type.
--function=<string> — print details for a function if the function's name contains the given string.
--help — print a summary of command line options.
--output=<output>, -o — specify the output file name. If output is - or it isn't specified, then the output is sent to standard output.
--instr — this is the default, and it says the input profile is an instrumentation-based profile.
--text — instruct the profile dumper to show profile counts in the text format of the instrumentation-based profile data representation. By default, the profile information is dumped in a more human-readable form (also in text) with annotations.
--topn=<n> — instruct the profile dumper to show the top n functions with the hottest basic blocks in the summary section. By default, the topn functions are not dumped.
--sample — specify that the input profile is a sample-based profile.
--memop-sizes — show the profiled sizes of the memory intrinsic calls for shown functions.
--value-cutoff=<n> — show only those functions whose max count values are greater or equal to n. By default, the value-cutoff is set to 0.
--list-below-cutoff — only output names of functions whose max count value are below the cutoff value.
--profile-version — print profile version.
--showcs — only show context sensitive profile counts. The default is to filter all context sensitive profile counts.
--show-prof-sym-list=[true|false] — show profile symbol list if it exists in the profile. This option is only meaningful for sample-based profile in extbinary format.
--show-sec-info-only=[true|false] — show basic information about each section in the profile. This option is only meaningful for sample-based profile in extbinary format.
--debug-info=<path> — specify the executable or .dSYM that contains debug info for the raw profile. When --debug-info-correlate or --profile-correlate=debug-info was used for instrumentation, use this option to show the correlated functions from the raw profile.
--covered — show only the functions that have been executed, i.e., functions with non-zero counts.

OVERLAP 🌸

SYNOPSIS ✨

llvm-profdata overlap [options] [base profile file] [test profile file]

DESCRIPTION 💖

llvm-profdata overlap takes two profile data files and displays the overlap of counter distribution between the whole files and between any of the specified functions. It's giving comparison, but make it profile data.

In this command, overlap is defined as follows: suppose base profile file has the following counts:

{c1_1, c1_2, ..., c1_n, c1_u_1, c2_u_2, ..., c2_u_s}

and test profile file has:

{c2_1, c2_2, ..., c2_n, c2_v_1, c2_v_2, ..., c2_v_t}

Here c{1|2}_i (i = 1 .. n) are matched counters and c1_u_i (i = 1 .. s) and c2_v_i (i = 1 .. v) are unmatched counters (or counters only existing in) base profile file and test profile file, respectively. Let:

sum_1 = c1_1 + c1_2 +  ... + c1_n +  c1_u_1 + c2_u_2 + ... + c2_u_s
sum_2 = c2_1 + c2_2 + ... + c2_n + c2_v_1 + c2_v_2 + ... + c2_v_t
overlap = min(c1_1/sum_1, c2_1/sum_2) + min(c1_2/sum_1, c2_2/sum_2) + ...  + min(c1_n/sum_1, c2_n/sum_2)

The result overlap distribution is a percentage number, ranging from 0.0% to 100.0%, where 0.0% means there is no overlap and 100.0% means a perfect overlap. 👑

Here's an example: if base profile file has counts of {400, 600}, and test profile file has matched counts of {60000, 40000}, the overlap is 80%. Math ate, fr fr. 🔥

OPTIONS 🎀

--function=<string> — print details for a function if the function's name contains the given string.
--help — print a summary of command line options.
--output=<output>, -o — specify the output file name. If output is - or it isn't specified, then the output is sent to standard output.
--value-cutoff=<n> — show only those functions whose max count values are greater or equal to n. By default, the value-cutoff is set to max of unsigned long long.
--cs — only show overlap for the context sensitive profile counts. The default is to show non-context sensitive profile counts.

ORDER 🦋

SYNOPSIS ✨

llvm-profdata order [options] [filename]

DESCRIPTION 💜

llvm-profdata order uses temporal profiling traces from a profile and finds a function order that reduces the number of page faults for those traces. This output can be directly passed to lld via --symbol-ordering-file= for ELF or -order-file for Mach-O. If the traces found in the profile are representative of the real world, then this order should improve startup performance. Iconic behavior, honestly. ⭐

OPTIONS 🎀

--help — print a summary of command line options.
--output=<output>, -o — specify the output file name. If output is - or it isn't specified, then the output is sent to standard output.

EXIT STATUS 💀

llvm-profdata returns 1 if the command is omitted or is invalid, if it cannot read input files, or if there is a mismatch between their data. So like… bestie, check your inputs before you come for this tool. 😭

AUTHOR 🫶

Maintained by the LLVM Team (https://llvm.org/).

COPYRIGHT 🌈

2003-2026, LLVM Project

💖 And that's the whole manual, bestie — the footer says page 23, dated 2026-10-06, title LLVM-PROFDATA(1). Slay and goodbye. 💅✨

📦 where this page comes from

centos-stream 9: llvm 23.1.3-1.el9 · Apache-2.0 WITH LLVM-exception OR NCSA
centos-stream 9: llvm 23.1.3-1.el9 · Apache-2.0 WITH LLVM-exception OR NCSA
💖 girlified by deepseek-ai/DeepSeek-V4.1-Flash-1017 on 2026-11-04: a language model's rewrite of the original, under its terms

LLVM-PROFDATA(1)

💅 LLVM-PROFDATA(1) — the llvm-profdata glow-up from the LLVM manual ✨

🎀 NAME

✨ SYNOPSIS

🫶 DESCRIPTION

👑 COMMANDS

🎀 MERGE

🦋 SYNOPSIS

🌸 DESCRIPTION

✨ OPTIONS ✨

🍓 EXAMPLES

🌸 Basic Usage

🦋 Weighted Input

SHOW 💅

SYNOPSIS ✨

DESCRIPTION 🫶

OPTIONS 🎀

OVERLAP 🌸

SYNOPSIS ✨

DESCRIPTION 💖

OPTIONS 🎀

ORDER 🦋

SYNOPSIS ✨

DESCRIPTION 💜

OPTIONS 🎀

EXIT STATUS 💀

AUTHOR 🫶

COPYRIGHT 🌈

💅 LLVM-PROFDATA(1) — the `llvm-profdata` glow-up from the LLVM manual ✨