[clang] [llvm] [HIP] add --offload-compression-level= option (PR #83605)
Yaxun Liu via cfe-commits
cfe-commits at lists.llvm.org
Fri Mar 8 13:44:35 PST 2024
https://github.com/yxsamliu updated https://github.com/llvm/llvm-project/pull/83605
>From c46a3ce625a34a497cd0b14631cb755b903e93d6 Mon Sep 17 00:00:00 2001
From: "Yaxun (Sam) Liu" <yaxun.liu at amd.com>
Date: Fri, 1 Mar 2024 13:16:45 -0500
Subject: [PATCH] [HIP] add --offload-compression-level= option
Added --offload-compression-level= option to clang and -compression-level=
option to clang-offload-bundler and clang-linker-wrapper for
controlling compression level.
Added support of long distance matching (LDM) for llvm::zstd which is off
by default. Enable it for clang-offload-bundler by default since it
improves compression rate in general.
Change default compression level to 3 for zstd for clang-offload-bundler
since it works well for bundle entry size from 1KB to 32MB, which should
cover most of the clang-offload-bundler usage. Users can still specify
compression level by -compression-level= option if necessary.
Change-Id: I5e2d7abcaa11a2a37a5e798476e3f572bba11cab
---
clang/include/clang/Driver/OffloadBundler.h | 6 +-
clang/include/clang/Driver/Options.td | 4 +
clang/lib/Driver/OffloadBundler.cpp | 111 ++++++++++++++----
clang/lib/Driver/ToolChains/Clang.cpp | 11 +-
clang/lib/Driver/ToolChains/CommonArgs.cpp | 12 ++
clang/lib/Driver/ToolChains/CommonArgs.h | 2 +
clang/lib/Driver/ToolChains/HIPUtility.cpp | 7 +-
.../test/Driver/clang-offload-bundler-zlib.c | 21 +++-
.../test/Driver/clang-offload-bundler-zstd.c | 19 ++-
.../test/Driver/hip-offload-compress-zlib.hip | 7 +-
.../test/Driver/hip-offload-compress-zstd.hip | 5 +-
clang/test/Driver/linker-wrapper.c | 5 +-
.../ClangLinkerWrapper.cpp | 3 +
.../clang-linker-wrapper/LinkerWrapperOpts.td | 2 +
.../ClangOffloadBundler.cpp | 5 +
llvm/include/llvm/Support/Compression.h | 5 +-
llvm/lib/Support/Compression.cpp | 43 +++++--
17 files changed, 204 insertions(+), 64 deletions(-)
diff --git a/clang/include/clang/Driver/OffloadBundler.h b/clang/include/clang/Driver/OffloadBundler.h
index 84349abe185fa4..65d33bfbd2825f 100644
--- a/clang/include/clang/Driver/OffloadBundler.h
+++ b/clang/include/clang/Driver/OffloadBundler.h
@@ -17,6 +17,7 @@
#ifndef LLVM_CLANG_DRIVER_OFFLOADBUNDLER_H
#define LLVM_CLANG_DRIVER_OFFLOADBUNDLER_H
+#include "llvm/Support/Compression.h"
#include "llvm/Support/Error.h"
#include "llvm/TargetParser/Triple.h"
#include <llvm/Support/MemoryBuffer.h>
@@ -36,6 +37,8 @@ class OffloadBundlerConfig {
bool HipOpenmpCompatible = false;
bool Compress = false;
bool Verbose = false;
+ llvm::compression::Format CompressionFormat;
+ int CompressionLevel;
unsigned BundleAlignment = 1;
unsigned HostInputIndex = ~0u;
@@ -116,7 +119,8 @@ class CompressedOffloadBundle {
public:
static llvm::Expected<std::unique_ptr<llvm::MemoryBuffer>>
- compress(const llvm::MemoryBuffer &Input, bool Verbose = false);
+ compress(llvm::compression::Params P, const llvm::MemoryBuffer &Input,
+ bool Verbose = false);
static llvm::Expected<std::unique_ptr<llvm::MemoryBuffer>>
decompress(const llvm::MemoryBuffer &Input, bool Verbose = false);
};
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 5b3d366dbcf91b..2d26a7983f397b 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -1264,6 +1264,10 @@ def fno_gpu_sanitize : Flag<["-"], "fno-gpu-sanitize">, Group<f_Group>;
def offload_compress : Flag<["--"], "offload-compress">,
HelpText<"Compress offload device binaries (HIP only)">;
def no_offload_compress : Flag<["--"], "no-offload-compress">;
+
+def offload_compression_level_EQ : Joined<["--"], "offload-compression-level=">,
+ Flags<[HelpHidden]>,
+ HelpText<"Compression level for offload device binaries (HIP only)">;
}
// CUDA options
diff --git a/clang/lib/Driver/OffloadBundler.cpp b/clang/lib/Driver/OffloadBundler.cpp
index f9eadfaec88dec..77c89356bc76bb 100644
--- a/clang/lib/Driver/OffloadBundler.cpp
+++ b/clang/lib/Driver/OffloadBundler.cpp
@@ -924,6 +924,17 @@ CreateFileHandler(MemoryBuffer &FirstInput,
}
OffloadBundlerConfig::OffloadBundlerConfig() {
+ if (llvm::compression::zstd::isAvailable()) {
+ CompressionFormat = llvm::compression::Format::Zstd;
+ // Compression level 3 is usually sufficient for zstd since long distance
+ // matching is enabled.
+ CompressionLevel = 3;
+ } else if (llvm::compression::zlib::isAvailable()) {
+ CompressionFormat = llvm::compression::Format::Zlib;
+ // Use default level for zlib since higher level does not have significant
+ // improvement.
+ CompressionLevel = llvm::compression::zlib::DefaultCompression;
+ }
auto IgnoreEnvVarOpt =
llvm::sys::Process::GetEnv("OFFLOAD_BUNDLER_IGNORE_ENV_VAR");
if (IgnoreEnvVarOpt.has_value() && IgnoreEnvVarOpt.value() == "1")
@@ -937,11 +948,41 @@ OffloadBundlerConfig::OffloadBundlerConfig() {
llvm::sys::Process::GetEnv("OFFLOAD_BUNDLER_COMPRESS");
if (CompressEnvVarOpt.has_value())
Compress = CompressEnvVarOpt.value() == "1";
+
+ auto CompressionLevelEnvVarOpt =
+ llvm::sys::Process::GetEnv("OFFLOAD_BUNDLER_COMPRESSION_LEVEL");
+ if (CompressionLevelEnvVarOpt.has_value()) {
+ llvm::StringRef CompressionLevelStr = CompressionLevelEnvVarOpt.value();
+ int Level;
+ if (!CompressionLevelStr.getAsInteger(10, Level))
+ CompressionLevel = Level;
+ else
+ llvm::errs()
+ << "Warning: Invalid value for OFFLOAD_BUNDLER_COMPRESSION_LEVEL: "
+ << CompressionLevelStr.str() << ". Ignoring it.\n";
+ }
+}
+
+// Utility function to format numbers with commas
+static std::string formatWithCommas(unsigned long long Value) {
+ std::string Num = std::to_string(Value);
+ int InsertPosition = Num.length() - 3;
+ while (InsertPosition > 0) {
+ Num.insert(InsertPosition, ",");
+ InsertPosition -= 3;
+ }
+ return Num;
}
llvm::Expected<std::unique_ptr<llvm::MemoryBuffer>>
-CompressedOffloadBundle::compress(const llvm::MemoryBuffer &Input,
+CompressedOffloadBundle::compress(llvm::compression::Params P,
+ const llvm::MemoryBuffer &Input,
bool Verbose) {
+ if (!llvm::compression::zstd::isAvailable() &&
+ !llvm::compression::zlib::isAvailable())
+ return createStringError(llvm::inconvertibleErrorCode(),
+ "Compression not supported");
+
llvm::Timer HashTimer("Hash Calculation Timer", "Hash calculation time",
ClangOffloadBundlerTimerGroup);
if (Verbose)
@@ -959,25 +1000,15 @@ CompressedOffloadBundle::compress(const llvm::MemoryBuffer &Input,
reinterpret_cast<const uint8_t *>(Input.getBuffer().data()),
Input.getBuffer().size());
- llvm::compression::Format CompressionFormat;
-
- if (llvm::compression::zstd::isAvailable())
- CompressionFormat = llvm::compression::Format::Zstd;
- else if (llvm::compression::zlib::isAvailable())
- CompressionFormat = llvm::compression::Format::Zlib;
- else
- return createStringError(llvm::inconvertibleErrorCode(),
- "Compression not supported");
-
llvm::Timer CompressTimer("Compression Timer", "Compression time",
ClangOffloadBundlerTimerGroup);
if (Verbose)
CompressTimer.startTimer();
- llvm::compression::compress(CompressionFormat, BufferUint8, CompressedBuffer);
+ llvm::compression::compress(P, BufferUint8, CompressedBuffer);
if (Verbose)
CompressTimer.stopTimer();
- uint16_t CompressionMethod = static_cast<uint16_t>(CompressionFormat);
+ uint16_t CompressionMethod = static_cast<uint16_t>(P.format);
uint32_t UncompressedSize = Input.getBuffer().size();
SmallVector<char, 0> FinalBuffer;
@@ -995,17 +1026,29 @@ CompressedOffloadBundle::compress(const llvm::MemoryBuffer &Input,
if (Verbose) {
auto MethodUsed =
- CompressionFormat == llvm::compression::Format::Zstd ? "zstd" : "zlib";
+ P.format == llvm::compression::Format::Zstd ? "zstd" : "zlib";
+ double CompressionRate =
+ static_cast<double>(UncompressedSize) / CompressedBuffer.size();
+ double CompressionTimeSeconds = CompressTimer.getTotalTime().getWallTime();
+ double CompressionSpeedMBs =
+ (UncompressedSize / (1024.0 * 1024.0)) / CompressionTimeSeconds;
+
llvm::errs() << "Compressed bundle format version: " << Version << "\n"
<< "Compression method used: " << MethodUsed << "\n"
- << "Binary size before compression: " << UncompressedSize
- << " bytes\n"
- << "Binary size after compression: " << CompressedBuffer.size()
- << " bytes\n"
+ << "Compression level: " << P.level << "\n"
+ << "Binary size before compression: "
+ << formatWithCommas(UncompressedSize) << " bytes\n"
+ << "Binary size after compression: "
+ << formatWithCommas(CompressedBuffer.size()) << " bytes\n"
+ << "Compression rate: "
+ << llvm::format("%.2lf", CompressionRate) << "\n"
+ << "Compression ratio: "
+ << llvm::format("%.2lf%%", 100.0 / CompressionRate) << "\n"
+ << "Compression speed: "
+ << llvm::format("%.2lf MB/s", CompressionSpeedMBs) << "\n"
<< "Truncated MD5 hash: "
<< llvm::format_hex(TruncatedHash, 16) << "\n";
}
-
return llvm::MemoryBuffer::getMemBufferCopy(
llvm::StringRef(FinalBuffer.data(), FinalBuffer.size()));
}
@@ -1070,7 +1113,10 @@ CompressedOffloadBundle::decompress(const llvm::MemoryBuffer &Input,
if (Verbose) {
DecompressTimer.stopTimer();
- // Recalculate MD5 hash
+ double DecompressionTimeSeconds =
+ DecompressTimer.getTotalTime().getWallTime();
+
+ // Recalculate MD5 hash for integrity check
llvm::Timer HashRecalcTimer("Hash Recalculation Timer",
"Hash recalculation time",
ClangOffloadBundlerTimerGroup);
@@ -1084,16 +1130,27 @@ CompressedOffloadBundle::decompress(const llvm::MemoryBuffer &Input,
HashRecalcTimer.stopTimer();
bool HashMatch = (StoredHash == RecalculatedHash);
+ double CompressionRate =
+ static_cast<double>(UncompressedSize) / CompressedData.size();
+ double DecompressionSpeedMBs =
+ (UncompressedSize / (1024.0 * 1024.0)) / DecompressionTimeSeconds;
+
llvm::errs() << "Compressed bundle format version: " << ThisVersion << "\n"
<< "Decompression method: "
<< (CompressionFormat == llvm::compression::Format::Zlib
? "zlib"
: "zstd")
<< "\n"
- << "Size before decompression: " << CompressedData.size()
- << " bytes\n"
- << "Size after decompression: " << UncompressedSize
- << " bytes\n"
+ << "Size before decompression: "
+ << formatWithCommas(CompressedData.size()) << " bytes\n"
+ << "Size after decompression: "
+ << formatWithCommas(UncompressedSize) << " bytes\n"
+ << "Compression rate: "
+ << llvm::format("%.2lf", CompressionRate) << "\n"
+ << "Compression ratio: "
+ << llvm::format("%.2lf%%", 100.0 / CompressionRate) << "\n"
+ << "Decompression speed: "
+ << llvm::format("%.2lf MB/s", DecompressionSpeedMBs) << "\n"
<< "Stored hash: " << llvm::format_hex(StoredHash, 16) << "\n"
<< "Recalculated hash: "
<< llvm::format_hex(RecalculatedHash, 16) << "\n"
@@ -1287,8 +1344,10 @@ Error OffloadBundler::BundleFiles() {
std::unique_ptr<llvm::MemoryBuffer> BufferMemory =
llvm::MemoryBuffer::getMemBufferCopy(
llvm::StringRef(Buffer.data(), Buffer.size()));
- auto CompressionResult =
- CompressedOffloadBundle::compress(*BufferMemory, BundlerConfig.Verbose);
+ auto CompressionResult = CompressedOffloadBundle::compress(
+ {BundlerConfig.CompressionFormat, BundlerConfig.CompressionLevel,
+ /*zstdEnableLdm=*/true},
+ *BufferMemory, BundlerConfig.Verbose);
if (auto Error = CompressionResult.takeError())
return Error;
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index fa17f6295d6ea7..7fe784ca076f6c 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -8524,7 +8524,6 @@ void ClangAs::ConstructJob(Compilation &C, const JobAction &JA,
}
// Begin OffloadBundler
-
void OffloadBundler::ConstructJob(Compilation &C, const JobAction &JA,
const InputInfo &Output,
const InputInfoList &Inputs,
@@ -8622,11 +8621,7 @@ void OffloadBundler::ConstructJob(Compilation &C, const JobAction &JA,
}
CmdArgs.push_back(TCArgs.MakeArgString(UB));
}
- if (TCArgs.hasFlag(options::OPT_offload_compress,
- options::OPT_no_offload_compress, false))
- CmdArgs.push_back("-compress");
- if (TCArgs.hasArg(options::OPT_v))
- CmdArgs.push_back("-verbose");
+ addOffloadCompressArgs(TCArgs, CmdArgs);
// All the inputs are encoded as commands.
C.addCommand(std::make_unique<Command>(
JA, *this, ResponseFileSupport::None(),
@@ -8895,9 +8890,7 @@ void LinkerWrapper::ConstructJob(Compilation &C, const JobAction &JA,
for (const char *LinkArg : LinkCommand->getArguments())
CmdArgs.push_back(LinkArg);
- if (Args.hasFlag(options::OPT_offload_compress,
- options::OPT_no_offload_compress, false))
- CmdArgs.push_back("--compress");
+ addOffloadCompressArgs(Args, CmdArgs);
const char *Exec =
Args.MakeArgString(getToolChain().GetProgramPath("clang-linker-wrapper"));
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp b/clang/lib/Driver/ToolChains/CommonArgs.cpp
index 7f0f78b41e79ed..100e71245394d8 100644
--- a/clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -2863,3 +2863,15 @@ void tools::addOutlineAtomicsArgs(const Driver &D, const ToolChain &TC,
CmdArgs.push_back("+outline-atomics");
}
}
+
+void tools::addOffloadCompressArgs(const llvm::opt::ArgList &TCArgs,
+ llvm::opt::ArgStringList &CmdArgs) {
+ if (TCArgs.hasFlag(options::OPT_offload_compress,
+ options::OPT_no_offload_compress, false))
+ CmdArgs.push_back("-compress");
+ if (TCArgs.hasArg(options::OPT_v))
+ CmdArgs.push_back("-verbose");
+ if (auto *Arg = TCArgs.getLastArg(options::OPT_offload_compression_level_EQ))
+ CmdArgs.push_back(
+ TCArgs.MakeArgString(Twine("-compression-level=") + Arg->getValue()));
+}
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.h b/clang/lib/Driver/ToolChains/CommonArgs.h
index b8f649aab4bdd2..bb37be4bd6ea05 100644
--- a/clang/lib/Driver/ToolChains/CommonArgs.h
+++ b/clang/lib/Driver/ToolChains/CommonArgs.h
@@ -221,6 +221,8 @@ void addOutlineAtomicsArgs(const Driver &D, const ToolChain &TC,
const llvm::opt::ArgList &Args,
llvm::opt::ArgStringList &CmdArgs,
const llvm::Triple &Triple);
+void addOffloadCompressArgs(const llvm::opt::ArgList &TCArgs,
+ llvm::opt::ArgStringList &CmdArgs);
} // end namespace tools
} // end namespace driver
diff --git a/clang/lib/Driver/ToolChains/HIPUtility.cpp b/clang/lib/Driver/ToolChains/HIPUtility.cpp
index fcecf2e1313bb5..08c647dfcb6f72 100644
--- a/clang/lib/Driver/ToolChains/HIPUtility.cpp
+++ b/clang/lib/Driver/ToolChains/HIPUtility.cpp
@@ -7,6 +7,7 @@
//===----------------------------------------------------------------------===//
#include "HIPUtility.h"
+#include "Clang.h"
#include "CommonArgs.h"
#include "clang/Driver/Compilation.h"
#include "clang/Driver/Options.h"
@@ -258,11 +259,7 @@ void HIP::constructHIPFatbinCommand(Compilation &C, const JobAction &JA,
Args.MakeArgString(std::string("-output=").append(Output));
BundlerArgs.push_back(BundlerOutputArg);
- if (Args.hasFlag(options::OPT_offload_compress,
- options::OPT_no_offload_compress, false))
- BundlerArgs.push_back("-compress");
- if (Args.hasArg(options::OPT_v))
- BundlerArgs.push_back("-verbose");
+ addOffloadCompressArgs(Args, BundlerArgs);
const char *Bundler = Args.MakeArgString(
T.getToolChain().GetProgramPath("clang-offload-bundler"));
diff --git a/clang/test/Driver/clang-offload-bundler-zlib.c b/clang/test/Driver/clang-offload-bundler-zlib.c
index a57ee6da9a86a6..15b60341a8dbde 100644
--- a/clang/test/Driver/clang-offload-bundler-zlib.c
+++ b/clang/test/Driver/clang-offload-bundler-zlib.c
@@ -1,4 +1,4 @@
-// REQUIRES: zlib
+// REQUIRES: zlib && !zstd
// REQUIRES: x86-registered-target
// UNSUPPORTED: target={{.*}}-darwin{{.*}}, target={{.*}}-aix{{.*}}
@@ -34,13 +34,28 @@
// RUN: diff %t.tgt2 %t.res.tgt2
//
-// COMPRESS: Compression method used:
-// DECOMPRESS: Decompression method:
+// COMPRESS: Compression method used: zlib
+// COMPRESS: Compression level: 6
+// DECOMPRESS: Decompression method: zlib
+// DECOMPRESS: Hashes match: Yes
// NOHOST-NOT: host-
// NOHOST-DAG: hip-amdgcn-amd-amdhsa--gfx900
// NOHOST-DAG: hip-amdgcn-amd-amdhsa--gfx906
//
+// Check -compression-level= option
+
+// RUN: clang-offload-bundler -type=bc -targets=hip-amdgcn-amd-amdhsa--gfx900,hip-amdgcn-amd-amdhsa--gfx906 \
+// RUN: -input=%t.tgt1 -input=%t.tgt2 -output=%t.hip.bundle.bc -compress -verbose -compression-level=9 2>&1 | \
+// RUN: FileCheck -check-prefix=LEVEL %s
+// RUN: clang-offload-bundler -type=bc -targets=hip-amdgcn-amd-amdhsa--gfx900,hip-amdgcn-amd-amdhsa--gfx906 \
+// RUN: -output=%t.res.tgt1 -output=%t.res.tgt2 -input=%t.hip.bundle.bc -unbundle
+// RUN: diff %t.tgt1 %t.res.tgt1
+// RUN: diff %t.tgt2 %t.res.tgt2
+//
+// LEVEL: Compression method used: zlib
+// LEVEL: Compression level: 9
+
//
// Check -bundle-align option.
//
diff --git a/clang/test/Driver/clang-offload-bundler-zstd.c b/clang/test/Driver/clang-offload-bundler-zstd.c
index 3b577d4d166a3f..c1eb3f6e7ebd07 100644
--- a/clang/test/Driver/clang-offload-bundler-zstd.c
+++ b/clang/test/Driver/clang-offload-bundler-zstd.c
@@ -31,13 +31,28 @@
// RUN: diff %t.tgt1 %t.res.tgt1
// RUN: diff %t.tgt2 %t.res.tgt2
//
-// COMPRESS: Compression method used
-// DECOMPRESS: Decompression method
+// COMPRESS: Compression method used: zstd
+// COMPRESS: Compression level: 20
+// DECOMPRESS: Decompression method: zstd
+// DECOMPRESS: Hashes match: Yes
// NOHOST-NOT: host-
// NOHOST-DAG: hip-amdgcn-amd-amdhsa--gfx900
// NOHOST-DAG: hip-amdgcn-amd-amdhsa--gfx906
//
+// Check -compression-level= option
+
+// RUN: clang-offload-bundler -type=bc -targets=hip-amdgcn-amd-amdhsa--gfx900,hip-amdgcn-amd-amdhsa--gfx906 \
+// RUN: -input=%t.tgt1 -input=%t.tgt2 -output=%t.hip.bundle.bc -compress -verbose -compression-level=9 2>&1 | \
+// RUN: FileCheck -check-prefix=LEVEL %s
+// RUN: clang-offload-bundler -type=bc -targets=hip-amdgcn-amd-amdhsa--gfx900,hip-amdgcn-amd-amdhsa--gfx906 \
+// RUN: -output=%t.res.tgt1 -output=%t.res.tgt2 -input=%t.hip.bundle.bc -unbundle
+// RUN: diff %t.tgt1 %t.res.tgt1
+// RUN: diff %t.tgt2 %t.res.tgt2
+//
+// LEVEL: Compression method used: zstd
+// LEVEL: Compression level: 9
+
//
// Check -bundle-align option.
//
diff --git a/clang/test/Driver/hip-offload-compress-zlib.hip b/clang/test/Driver/hip-offload-compress-zlib.hip
index 7a269c566bb93c..c1566c5f192c2d 100644
--- a/clang/test/Driver/hip-offload-compress-zlib.hip
+++ b/clang/test/Driver/hip-offload-compress-zlib.hip
@@ -1,4 +1,4 @@
-// REQUIRES: zlib
+// REQUIRES: zlib && !zstd
// REQUIRES: x86-registered-target
// REQUIRES: amdgpu-registered-target
@@ -9,13 +9,14 @@
// RUN: -x hip --offload-arch=gfx1100 --offload-arch=gfx1101 \
// RUN: --no-offload-new-driver -fgpu-rdc -nogpuinc -nogpulib \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: --offload-compress --offload-device-only --gpu-bundle-output \
+// RUN: --offload-compress --offload-compression-level=9 \
+// RUN: --offload-device-only --gpu-bundle-output \
// RUN: -o %t.bc \
// RUN: 2>&1 | FileCheck %s
// CHECK: clang-offload-bundler{{.*}} -type=bc
// CHECK-SAME: -targets={{.*}}hip-amdgcn-amd-amdhsa-gfx1100,hip-amdgcn-amd-amdhsa-gfx1101
-// CHECK-SAME: -compress -verbose
+// CHECK-SAME: -compress -verbose -compression-level=9
// CHECK: Compressed bundle format
// Test uncompress of bundled bitcode.
diff --git a/clang/test/Driver/hip-offload-compress-zstd.hip b/clang/test/Driver/hip-offload-compress-zstd.hip
index fa7fb3b6d5b5cb..ede7d59f113c86 100644
--- a/clang/test/Driver/hip-offload-compress-zstd.hip
+++ b/clang/test/Driver/hip-offload-compress-zstd.hip
@@ -9,13 +9,14 @@
// RUN: -x hip --offload-arch=gfx1100 --offload-arch=gfx1101 \
// RUN: --no-offload-new-driver -fgpu-rdc -nogpuinc -nogpulib \
// RUN: %S/Inputs/hip_multiple_inputs/a.cu \
-// RUN: --offload-compress --offload-device-only --gpu-bundle-output \
+// RUN: --offload-compress --offload-compression-level=9 \
+// RUN: --offload-device-only --gpu-bundle-output \
// RUN: -o %t.bc \
// RUN: 2>&1 | FileCheck %s
// CHECK: clang-offload-bundler{{.*}} -type=bc
// CHECK-SAME: -targets={{.*}}hip-amdgcn-amd-amdhsa-gfx1100,hip-amdgcn-amd-amdhsa-gfx1101
-// CHECK-SAME: -compress -verbose
+// CHECK-SAME: -compress -verbose -compression-level=9
// CHECK: Compressed bundle format
// Test uncompress of bundled bitcode.
diff --git a/clang/test/Driver/linker-wrapper.c b/clang/test/Driver/linker-wrapper.c
index 0e6fd80b429846..cbf24d4ce3a824 100644
--- a/clang/test/Driver/linker-wrapper.c
+++ b/clang/test/Driver/linker-wrapper.c
@@ -114,12 +114,13 @@ __attribute__((visibility("protected"), used)) int x;
// RUN: --image=file=%t.elf.o,kind=hip,triple=amdgcn-amd-amdhsa,arch=gfx908
// RUN: %clang -cc1 %s -triple x86_64-unknown-linux-gnu -emit-obj -o %t.o \
// RUN: -fembed-offload-object=%t.out
-// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu --compress \
+// RUN: clang-linker-wrapper --dry-run --host-triple=x86_64-unknown-linux-gnu \
+// RUN: --compress --compression-level=6 \
// RUN: --linker-path=/usr/bin/ld %t.o -o a.out 2>&1 | FileCheck %s --check-prefix=HIP
// HIP: clang{{.*}} -o [[IMG_GFX908:.+]] --target=amdgcn-amd-amdhsa -mcpu=gfx908
// HIP: clang{{.*}} -o [[IMG_GFX90A:.+]] --target=amdgcn-amd-amdhsa -mcpu=gfx90a
-// HIP: clang-offload-bundler{{.*}}-type=o -bundle-align=4096 -compress -targets=host-x86_64-unknown-linux,hipv4-amdgcn-amd-amdhsa--gfx90a,hipv4-amdgcn-amd-amdhsa--gfx908 -input=/dev/null -input=[[IMG_GFX90A]] -input=[[IMG_GFX908]] -output={{.*}}.hipfb
+// HIP: clang-offload-bundler{{.*}}-type=o -bundle-align=4096 -compress -compression-level=6 -targets=host-x86_64-unknown-linux,hipv4-amdgcn-amd-amdhsa--gfx90a,hipv4-amdgcn-amd-amdhsa--gfx908 -input=/dev/null -input=[[IMG_GFX90A]] -input=[[IMG_GFX908]] -output={{.*}}.hipfb
// RUN: clang-offload-packager -o %t.out \
// RUN: --image=file=%t.elf.o,kind=openmp,triple=amdgcn-amd-amdhsa,arch=gfx908 \
diff --git a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
index 7e6e289c50d872..535ef42c78c463 100644
--- a/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
+++ b/clang/tools/clang-linker-wrapper/ClangLinkerWrapper.cpp
@@ -407,6 +407,9 @@ fatbinary(ArrayRef<std::pair<StringRef, StringRef>> InputFiles,
if (Args.hasArg(OPT_compress))
CmdArgs.push_back("-compress");
+ if (auto *Arg = Args.getLastArg(OPT_compression_level_eq))
+ CmdArgs.push_back(
+ Args.MakeArgString(Twine("-compression-level=") + Arg->getValue()));
SmallVector<StringRef> Targets = {"-targets=host-x86_64-unknown-linux"};
for (const auto &[File, Arch] : InputFiles)
diff --git a/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td b/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td
index 473fb19d922385..0a8bd541c45242 100644
--- a/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td
+++ b/clang/tools/clang-linker-wrapper/LinkerWrapperOpts.td
@@ -60,6 +60,8 @@ def save_temps : Flag<["--"], "save-temps">,
Flags<[WrapperOnlyOption]>, HelpText<"Save intermediate results">;
def compress : Flag<["--"], "compress">,
Flags<[WrapperOnlyOption]>, HelpText<"Compress bundled files">;
+def compression_level_eq : Joined<["--"], "compression-level=">,
+ Flags<[WrapperOnlyOption]>, HelpText<"Specify the compression level (integer)">;
def wrapper_time_trace_eq : Joined<["--"], "wrapper-time-trace=">,
Flags<[WrapperOnlyOption]>, MetaVarName<"<file>">,
diff --git a/clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp b/clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp
index ec67e24552e9c9..e336417586f70b 100644
--- a/clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp
+++ b/clang/tools/clang-offload-bundler/ClangOffloadBundler.cpp
@@ -145,6 +145,9 @@ int main(int argc, const char **argv) {
cl::init(false), cl::cat(ClangOffloadBundlerCategory));
cl::opt<bool> Verbose("verbose", cl::desc("Print debug information.\n"),
cl::init(false), cl::cat(ClangOffloadBundlerCategory));
+ cl::opt<int> CompressionLevel(
+ "compression-level", cl::desc("Specify the compression level (integer)"),
+ cl::value_desc("n"), cl::Optional, cl::cat(ClangOffloadBundlerCategory));
// Process commandline options and report errors
sys::PrintStackTraceOnErrorSignal(argv[0]);
@@ -178,6 +181,8 @@ int main(int argc, const char **argv) {
BundlerConfig.Compress = Compress;
if (Verbose.getNumOccurrences() > 0)
BundlerConfig.Verbose = Verbose;
+ if (CompressionLevel.getNumOccurrences() > 0)
+ BundlerConfig.CompressionLevel = CompressionLevel;
BundlerConfig.TargetNames = TargetNames;
BundlerConfig.InputFileNames = InputFileNames;
diff --git a/llvm/include/llvm/Support/Compression.h b/llvm/include/llvm/Support/Compression.h
index c3ba3274d6ed87..2a8da9e96d356f 100644
--- a/llvm/include/llvm/Support/Compression.h
+++ b/llvm/include/llvm/Support/Compression.h
@@ -63,7 +63,7 @@ bool isAvailable();
void compress(ArrayRef<uint8_t> Input,
SmallVectorImpl<uint8_t> &CompressedBuffer,
- int Level = DefaultCompression);
+ int Level = DefaultCompression, bool EnableLdm = false);
Error decompress(ArrayRef<uint8_t> Input, uint8_t *Output,
size_t &UncompressedSize);
@@ -94,10 +94,13 @@ struct Params {
constexpr Params(Format F)
: format(F), level(F == Format::Zlib ? zlib::DefaultCompression
: zstd::DefaultCompression) {}
+ constexpr Params(Format F, int L, bool Ldm = false)
+ : format(F), level(L), zstdEnableLdm(Ldm) {}
Params(DebugCompressionType Type) : Params(formatFor(Type)) {}
Format format;
int level;
+ bool zstdEnableLdm = false; // Enable zstd long distance matching
// This may support multi-threading for zstd in the future. Note that
// different threads may produce different output, so be careful if certain
// output determinism is desired.
diff --git a/llvm/lib/Support/Compression.cpp b/llvm/lib/Support/Compression.cpp
index 8e57ba798f5207..badaf68ab59cd0 100644
--- a/llvm/lib/Support/Compression.cpp
+++ b/llvm/lib/Support/Compression.cpp
@@ -50,7 +50,7 @@ void compression::compress(Params P, ArrayRef<uint8_t> Input,
zlib::compress(Input, Output, P.level);
break;
case compression::Format::Zstd:
- zstd::compress(Input, Output, P.level);
+ zstd::compress(Input, Output, P.level, P.zstdEnableLdm);
break;
}
}
@@ -163,17 +163,39 @@ Error zlib::decompress(ArrayRef<uint8_t> Input,
bool zstd::isAvailable() { return true; }
+#include <zstd.h> // Ensure ZSTD library is included
+
void zstd::compress(ArrayRef<uint8_t> Input,
- SmallVectorImpl<uint8_t> &CompressedBuffer, int Level) {
- unsigned long CompressedBufferSize = ::ZSTD_compressBound(Input.size());
+ SmallVectorImpl<uint8_t> &CompressedBuffer, int Level,
+ bool EnableLdm) {
+ ZSTD_CCtx *Cctx = ZSTD_createCCtx();
+ if (!Cctx)
+ report_bad_alloc_error("Failed to create ZSTD_CCtx");
+
+ if (ZSTD_isError(ZSTD_CCtx_setParameter(
+ Cctx, ZSTD_c_enableLongDistanceMatching, EnableLdm ? 1 : 0))) {
+ ZSTD_freeCCtx(Cctx);
+ report_bad_alloc_error("Failed to set ZSTD_c_enableLongDistanceMatching");
+ }
+
+ if (ZSTD_isError(
+ ZSTD_CCtx_setParameter(Cctx, ZSTD_c_compressionLevel, Level))) {
+ ZSTD_freeCCtx(Cctx);
+ report_bad_alloc_error("Failed to set ZSTD_c_compressionLevel");
+ }
+
+ unsigned long CompressedBufferSize = ZSTD_compressBound(Input.size());
CompressedBuffer.resize_for_overwrite(CompressedBufferSize);
- unsigned long CompressedSize =
- ::ZSTD_compress((char *)CompressedBuffer.data(), CompressedBufferSize,
- (const char *)Input.data(), Input.size(), Level);
+
+ size_t const CompressedSize =
+ ZSTD_compress2(Cctx, CompressedBuffer.data(), CompressedBufferSize,
+ Input.data(), Input.size());
+
+ ZSTD_freeCCtx(Cctx);
+
if (ZSTD_isError(CompressedSize))
- report_bad_alloc_error("Allocation failed");
- // Tell MemorySanitizer that zstd output buffer is fully initialized.
- // This avoids a false report when running LLVM with uninstrumented ZLib.
+ report_bad_alloc_error("Compression failed");
+
__msan_unpoison(CompressedBuffer.data(), CompressedSize);
if (CompressedSize < CompressedBuffer.size())
CompressedBuffer.truncate(CompressedSize);
@@ -205,7 +227,8 @@ Error zstd::decompress(ArrayRef<uint8_t> Input,
#else
bool zstd::isAvailable() { return false; }
void zstd::compress(ArrayRef<uint8_t> Input,
- SmallVectorImpl<uint8_t> &CompressedBuffer, int Level) {
+ SmallVectorImpl<uint8_t> &CompressedBuffer, int Level,
+ bool EnableLdm) {
llvm_unreachable("zstd::compress is unavailable");
}
Error zstd::decompress(ArrayRef<uint8_t> Input, uint8_t *Output,
More information about the cfe-commits
mailing list