[llvm] [llvm-remarkutil] Add an instruction-mix tool (PR #140598)
Jon Roelofs via llvm-commits
llvm-commits at lists.llvm.org
Mon May 19 12:26:02 PDT 2025
https://github.com/jroelofs created https://github.com/llvm/llvm-project/pull/140598
The new tool constructs a histogram of instruction frequencies, optionally filtered by function name via a regex. It can display in either a human-readable table format, or machine-readable CSV.
>From e0dce31ff74e3265cb8ea12a71ecbdbce72357f5 Mon Sep 17 00:00:00 2001
From: Jon Roelofs <jonathan_roelofs at apple.com>
Date: Mon, 19 May 2025 12:18:12 -0700
Subject: [PATCH] [llvm-remarkutil] Add an instruction-mix tool
The new tool constructs a histogram of instruction frequencies, optionally
filtered by function name via a regex. It can display in either a
human-readable table format, or machine-readable CSV.
---
.../Inputs/instruction-mix.yaml | 27 ++++
.../llvm-remarkutil/broken-yaml-remark.test | 1 +
.../tools/llvm-remarkutil/empty-file.test | 5 +
.../llvm-remarkutil/instruction-mix.test | 22 +++
llvm/tools/llvm-remarkutil/CMakeLists.txt | 1 +
.../llvm-remarkutil/RemarkInstructionMix.cpp | 125 ++++++++++++++++++
6 files changed, 181 insertions(+)
create mode 100644 llvm/test/tools/llvm-remarkutil/Inputs/instruction-mix.yaml
create mode 100644 llvm/test/tools/llvm-remarkutil/instruction-mix.test
create mode 100644 llvm/tools/llvm-remarkutil/RemarkInstructionMix.cpp
diff --git a/llvm/test/tools/llvm-remarkutil/Inputs/instruction-mix.yaml b/llvm/test/tools/llvm-remarkutil/Inputs/instruction-mix.yaml
new file mode 100644
index 0000000000000..f798454d317fa
--- /dev/null
+++ b/llvm/test/tools/llvm-remarkutil/Inputs/instruction-mix.yaml
@@ -0,0 +1,27 @@
+--- !Analysis
+Pass: asm-printer
+Name: InstructionMix
+Function: home
+Args:
+ - INST_nop: '1'
+ - INST_add: '3'
+ - INST_mul: '5'
+...
+--- !Analysis
+Pass: asm-printer
+Name: InstructionMix
+Function: homeowner
+Args:
+ - INST_nop: '2'
+ - INST_add: '4'
+ - INST_mul: '6'
+...
+--- !Analysis
+Pass: asm-printer
+Name: InstructionMix
+Function: meow
+Args:
+ - INST_nop: '7'
+ - INST_add: '8'
+ - INST_mul: '9'
+...
diff --git a/llvm/test/tools/llvm-remarkutil/broken-yaml-remark.test b/llvm/test/tools/llvm-remarkutil/broken-yaml-remark.test
index 0f06506603363..464d0b80c4ad0 100644
--- a/llvm/test/tools/llvm-remarkutil/broken-yaml-remark.test
+++ b/llvm/test/tools/llvm-remarkutil/broken-yaml-remark.test
@@ -1,5 +1,6 @@
RUN: not llvm-remarkutil yaml2bitstream %p/Inputs/broken-remark -o - 2>&1 | FileCheck %s
RUN: not llvm-remarkutil instruction-count --parser=yaml %p/Inputs/broken-remark -o - 2>&1 | FileCheck %s
+RUN: not llvm-remarkutil instruction-mix --parser=yaml %p/Inputs/broken-remark -o - 2>&1 | FileCheck %s
RUN: not llvm-remarkutil annotation-count --parser=yaml --annotation-type=remark %p/Inputs/broken-remark -o - 2>&1 | FileCheck %s
RUN: not llvm-remarkutil count --parser=yaml %p/Inputs/broken-remark -o - 2>&1 | FileCheck %s
diff --git a/llvm/test/tools/llvm-remarkutil/empty-file.test b/llvm/test/tools/llvm-remarkutil/empty-file.test
index abbf8e02cfa30..bdc5fcf87f7bf 100644
--- a/llvm/test/tools/llvm-remarkutil/empty-file.test
+++ b/llvm/test/tools/llvm-remarkutil/empty-file.test
@@ -1,9 +1,11 @@
RUN: not llvm-remarkutil yaml2bitstream %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --check-prefix=YAMLPARSER
RUN: not llvm-remarkutil instruction-count --parser=yaml %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --check-prefix=YAMLPARSER
+RUN: not llvm-remarkutil instruction-mix --parser=yaml %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --check-prefix=YAMLPARSER
RUN: not llvm-remarkutil annotation-count --parser=yaml --annotation-type=remark %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --check-prefix=YAMLPARSER
RUN: not llvm-remarkutil count --parser=yaml %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --check-prefix=YAMLPARSER
RUN: llvm-remarkutil bitstream2yaml %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --allow-empty --check-prefix=BITSTREAM2YAML
RUN: llvm-remarkutil instruction-count --parser=bitstream %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --allow-empty --check-prefix=SIZEBITSTREAM
+RUN: llvm-remarkutil instruction-mix --parser=bitstream %p/Inputs/empty-file --report_style=csv -o - 2>&1 | FileCheck %s --allow-empty --check-prefix=MIXBITSTREAM
RUN: llvm-remarkutil annotation-count --parser=bitstream --annotation-type=remark %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --allow-empty --check-prefix=ANNOTATIONBITSTREAM
RUN: llvm-remarkutil count --parser=bitstream %p/Inputs/empty-file -o - 2>&1 | FileCheck %s --allow-empty --check-prefix=COUNTBITSTREAM
@@ -20,3 +22,6 @@ RUN: llvm-remarkutil count --parser=bitstream %p/Inputs/empty-file -o - 2>&1 | F
; COUNTBITSTREAM-LABEL: Source,Count
; COUNTBITSTREAM-EMPTY:
+
+; MIXBITSTREAM-LABEL: Instruction,Count
+; MIXBITSTREAM-EMPTY:
diff --git a/llvm/test/tools/llvm-remarkutil/instruction-mix.test b/llvm/test/tools/llvm-remarkutil/instruction-mix.test
new file mode 100644
index 0000000000000..8abb760ca37f9
--- /dev/null
+++ b/llvm/test/tools/llvm-remarkutil/instruction-mix.test
@@ -0,0 +1,22 @@
+RUN: llvm-remarkutil instruction-mix --parser=yaml %p/Inputs/instruction-mix.yaml | FileCheck %s
+RUN: llvm-remarkutil yaml2bitstream %p/Inputs/instruction-mix.yaml | llvm-remarkutil instruction-mix --parser=bitstream | FileCheck %s
+RUN: llvm-remarkutil instruction-mix --parser=yaml %p/Inputs/instruction-mix.yaml --report_style=human | FileCheck %s
+RUN: llvm-remarkutil instruction-mix --parser=yaml %p/Inputs/instruction-mix.yaml --report_style=csv | FileCheck %s --check-prefix=CSV
+RUN: llvm-remarkutil instruction-mix --parser=yaml %p/Inputs/instruction-mix.yaml --filter=meow | FileCheck %s --check-prefix=MEOW
+
+; CHECK-LABEL: Instruction Count
+; CHECK-NEXT: ----------- -----
+; CHECK-NEXT: mul 20
+; CHECK-NEXT: add 15
+; CHECK-NEXT: nop 10
+
+; CSV-LABEL: Instruction,Count
+; CSV-NEXT: mul,20
+; CSV-NEXT: add,15
+; CSV-NEXT: nop,10
+
+; MEOW: Instruction Count
+; MEOW-NEXT: ----------- -----
+; MEOW-NEXT: mul 15
+; MEOW-NEXT: add 12
+; MEOW-NEXT: nop 9
\ No newline at end of file
diff --git a/llvm/tools/llvm-remarkutil/CMakeLists.txt b/llvm/tools/llvm-remarkutil/CMakeLists.txt
index 48aeb9397cda1..ed398ad272024 100644
--- a/llvm/tools/llvm-remarkutil/CMakeLists.txt
+++ b/llvm/tools/llvm-remarkutil/CMakeLists.txt
@@ -8,6 +8,7 @@ add_llvm_tool(llvm-remarkutil
RemarkConvert.cpp
RemarkCount.cpp
RemarkCounter.cpp
+ RemarkInstructionMix.cpp
RemarkSizeDiff.cpp
RemarkUtil.cpp
RemarkUtilHelpers.cpp
diff --git a/llvm/tools/llvm-remarkutil/RemarkInstructionMix.cpp b/llvm/tools/llvm-remarkutil/RemarkInstructionMix.cpp
new file mode 100644
index 0000000000000..e4373640a75ee
--- /dev/null
+++ b/llvm/tools/llvm-remarkutil/RemarkInstructionMix.cpp
@@ -0,0 +1,125 @@
+
+#include "RemarkUtilHelpers.h"
+#include "RemarkUtilRegistry.h"
+
+#include "llvm/Support/Format.h"
+#include "llvm/Support/FormattedStream.h"
+#include "llvm/Support/Regex.h"
+
+#include <numeric>
+
+using namespace llvm;
+using namespace remarks;
+using namespace llvm::remarkutil;
+
+namespace instructionmix {
+
+static cl::SubCommand
+ InstructionMix("instruction-mix",
+ "Instruction Mix (requires asm-printer remarks)");
+
+static cl::opt<std::string>
+ FunctionFilter("filter", cl::sub(InstructionMix), cl::init(".*"),
+ cl::value_desc("filter_regex"),
+ cl::desc("regex to filter functions with"));
+
+enum ReportStyleOptions { human_output, csv_output };
+static cl::opt<ReportStyleOptions> ReportStyle(
+ "report_style", cl::sub(InstructionMix),
+ cl::init(ReportStyleOptions::human_output),
+ cl::desc("Choose the report output format:"),
+ cl::values(clEnumValN(human_output, "human", "Human-readable format"),
+ clEnumValN(csv_output, "csv", "CSV format")));
+
+INPUT_FORMAT_COMMAND_LINE_OPTIONS(InstructionMix)
+INPUT_OUTPUT_COMMAND_LINE_OPTIONS(InstructionMix)
+DEBUG_LOC_INFO_COMMAND_LINE_OPTIONS(InstructionMix)
+
+static Error tryInstructionMix() {
+ auto MaybeOF =
+ getOutputFileWithFlags(OutputFileName, sys::fs::OF_TextWithCRLF);
+ if (!MaybeOF)
+ return MaybeOF.takeError();
+
+ auto OF = std::move(*MaybeOF);
+ auto MaybeBuf = getInputMemoryBuffer(InputFileName);
+ if (!MaybeBuf)
+ return MaybeBuf.takeError();
+ auto MaybeParser = createRemarkParser(InputFormat, (*MaybeBuf)->getBuffer());
+ if (!MaybeParser)
+ return MaybeParser.takeError();
+
+ Regex Filter(FunctionFilter);
+
+ // Collect the histogram of instruction counts.
+ std::unordered_map<std::string, unsigned> Histogram;
+ auto &Parser = **MaybeParser;
+ auto MaybeRemark = Parser.next();
+ for (; MaybeRemark; MaybeRemark = Parser.next()) {
+ auto &Remark = **MaybeRemark;
+ if (Remark.RemarkName != "InstructionMix")
+ continue;
+ if (!Filter.match(Remark.FunctionName))
+ continue;
+ for (auto &Arg : Remark.Args) {
+ StringRef Key = Arg.Key;
+ if (!Key.consume_front("INST_"))
+ continue;
+ unsigned Val = 0;
+ bool ParseError = Arg.Val.getAsInteger(10, Val);
+ assert(!ParseError);
+ (void)ParseError;
+ Histogram[std::string(Key)] += Val;
+ }
+ }
+
+ // Sort it.
+ using MixEntry = std::pair<std::string, unsigned>;
+ llvm::SmallVector<MixEntry> Mix(Histogram.begin(), Histogram.end());
+ std::sort(Mix.begin(), Mix.end(), [](const auto &LHS, const auto &RHS) {
+ return LHS.second > RHS.second;
+ });
+
+ // Print the results.
+ switch (ReportStyle) {
+ case human_output: {
+ formatted_raw_ostream FOS(OF->os());
+ size_t MaxMnemonic =
+ std::accumulate(Mix.begin(), Mix.end(), StringRef("Instruction").size(),
+ [](size_t MaxMnemonic, const MixEntry &Elt) {
+ return std::max(MaxMnemonic, Elt.first.length());
+ });
+ unsigned MaxValue = std::accumulate(
+ Mix.begin(), Mix.end(), 0, [](unsigned MaxValue, const MixEntry &Elt) {
+ return std::max(MaxValue, Elt.second);
+ });
+ unsigned ValueWidth = log10(MaxValue) + 1;
+ FOS << "Instruction";
+ FOS.PadToColumn(MaxMnemonic + 1) << "Count\n";
+ FOS << "-----------";
+ FOS.PadToColumn(MaxMnemonic + 1) << "-----\n";
+ for (const auto &[Inst, Count] : Mix) {
+ FOS << Inst;
+ FOS.PadToColumn(MaxMnemonic + 1)
+ << " " << format_decimal(Count, ValueWidth) << "\n";
+ }
+ } break;
+ case csv_output: {
+ OF->os() << "Instruction,Count\n";
+ for (const auto &[Inst, Count] : Mix)
+ OF->os() << Inst << "," << Count << "\n";
+ } break;
+ }
+
+ auto E = MaybeRemark.takeError();
+ if (!E.isA<EndOfFileError>())
+ return E;
+ consumeError(std::move(E));
+ OF->keep();
+ return Error::success();
+}
+
+static CommandRegistration InstructionMixReg(&InstructionMix,
+ tryInstructionMix);
+
+} // namespace instructionmix
\ No newline at end of file
More information about the llvm-commits
mailing list