Skip to content

[SYCL][Driver] Support bfloat16 devicelib selection when multiple AOT targets specified #16494

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
againull merged 15 commits into from
Jan 31, 2025
Merged

[SYCL][Driver] Support bfloat16 devicelib selection when multiple AOT targets specified #16494

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
27512df
[SYCL] Select Native Bfloat16 devicelib in AOT
jinge90 Dec 31, 2024
becaba8
Merge remote-tracking branch 'upstream/sycl' into link_native_bf16_aot
jinge90 Dec 31, 2024
223f5e0
[SYCL][Driver] Select Native bfloat16 when all AOT targets specified …
jinge90 Dec 31, 2024
21fb49e
Update clang/test/Driver/sycl-device-lib-bfloat16.cpp
jinge90 Jan 3, 2025
b1fe3b3
Update clang/test/Driver/sycl-device-lib-bfloat16.cpp
jinge90 Jan 3, 2025
3c8b6d7
Update clang/test/Driver/sycl-device-lib-bfloat16.cpp
jinge90 Jan 3, 2025
d6dd9e2
Update clang/test/Driver/sycl-device-lib-bfloat16.cpp
jinge90 Jan 3, 2025
45ae7e4
Support mix use of '-device xxx' and fsycl-targets=
jinge90 Jan 11, 2025
2cfd4ab
Merge remote-tracking branch 'upstream/sycl' into link_native_bf16_aot
jinge90 Jan 11, 2025
34e4819
Merge remote-tracking branch 'upstream/sycl' into link_native_bf16_aot
jinge90 Jan 17, 2025
b3b2a38
Update clang/lib/Driver/ToolChains/SYCL.cpp
jinge90 Jan 17, 2025
55f0e7c
Merge remote-tracking branch 'origin/link_native_bf16_aot' into link_…
jinge90 Jan 17, 2025
64ba41b
Merge remote-tracking branch 'upstream/sycl' into link_native_bf16_aot
jinge90 Jan 20, 2025
23dc1de
add test for -Xsycl-target-backend
jinge90 Jan 20, 2025
c049ddd
add intel_gpu_dg2_*
jinge90 Jan 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
84 changes: 67 additions & 17 deletions clang/lib/Driver/ToolChains/SYCL.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,12 @@
#include "clang/Driver/DriverDiagnostic.h"
#include "clang/Driver/InputInfo.h"
#include "clang/Driver/Options.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/Option/Option.h"
#include "llvm/SYCLLowerIR/DeviceConfigFile.hpp"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Path.h"
#include "llvm/SYCLLowerIR/DeviceConfigFile.hpp"
#include <algorithm>
#include <sstream>

Expand Down Expand Up @@ -299,6 +300,11 @@ bool SYCL::shouldDoPerObjectFileLinking(const Compilation &C) {
// Return whether to use native bfloat16 library.
static bool selectBfloatLibs(const llvm::Triple &Triple, const Compilation &C,
bool &UseNative) {

static llvm::SmallSet<StringRef, 8> GPUArchsWithNBF16{
"intel_gpu_pvc", "intel_gpu_acm_g10", "intel_gpu_acm_g11",
"intel_gpu_acm_g12", "intel_gpu_dg2_10", "intel_gpu_dg2_11",
"intel_dg2_g12", "intel_gpu_bmg_g21"};
const llvm::opt::ArgList &Args = C.getArgs();
bool NeedLibs = false;

Expand All @@ -324,32 +330,75 @@ static bool selectBfloatLibs(const llvm::Triple &Triple, const Compilation &C,
}
}

UseNative = false;

// Check for intel_gpu_pvc as the target
if (Arg *SYCLTarget = Args.getLastArg(options::OPT_fsycl_targets_EQ)) {
if (SYCLTarget->getValues().size() == 1) {
StringRef SYCLTargetStr = SYCLTarget->getValue();
if (SYCLTargetStr == "intel_gpu_pvc")
UseNative = true;
}
}

auto checkBF = [](StringRef Device) {
return Device.starts_with("pvc") || Device.starts_with("ats");
};
// We need to select fallback/native bfloat16 devicelib in AOT compilation
// targetting for Intel GPU devices. Users have 2 ways to apply AOT,
// 1). clang++ -fsycl -fsycl-targets=spir64_gen -Xs "-device pvc,...,"
// 2). clang++ -fsycl -fsycl-targets=intel_gpu_pvc,...
// 3). clang++ -fsycl -fsycl-targets=spir64_gen,intel_gpu_pvc,...
// -Xsycl-target-backend=spir64_gen "-device dg2"

std::string Params;
for (const auto &Arg : TargArgs) {
Params += " ";
Params += Arg;
}

auto checkBF = [](StringRef Device) {
return Device.starts_with("pvc") || Device.starts_with("ats") ||
Device.starts_with("dg2") || Device.starts_with("bmg");
};

auto checkSpirvJIT = [](StringRef Target) {
return Target.starts_with("spir64-") || Target.starts_with("spirv64-") ||
(Target == "spir64") || (Target == "spirv64");
};

size_t DevicesPos = Params.find("-device ");
if (!UseNative && DevicesPos != std::string::npos) {
// "-device xxx" is used to specify AOT target device, so user must apply
// -Xs "-device xxx" or -Xsycl-target-backend=spir64_gen "-device xxx"
if (DevicesPos != std::string::npos) {
UseNative = true;
std::istringstream Devices(Params.substr(DevicesPos + 8));
for (std::string S; std::getline(Devices, S, ',');)
UseNative &= checkBF(S);

// When "-device XXX" is applied to specify GPU type, user can still
// add -fsycl-targets=intel_gpu_pvc..., native bfloat16 devicelib can
// only be linked when all GPU types specified support.
// We need to filter CPU and FPGA target here and only focus on GPU
// device.
if (Arg *SYCLTarget = Args.getLastArg(options::OPT_fsycl_targets_EQ)) {
for (auto TargetsV : SYCLTarget->getValues()) {
if (!checkSpirvJIT(StringRef(TargetsV)) &&
!StringRef(TargetsV).starts_with("spir64_gen") &&
!StringRef(TargetsV).starts_with("spir64_x86_64") &&
!StringRef(TargetsV).starts_with("spir64_fpga") &&
!GPUArchsWithNBF16.contains(StringRef(TargetsV))) {
UseNative = false;
break;
}
}
}

return NeedLibs;

} else {
// -fsycl-targets=intel_gpu_xxx is used to specify AOT target device.
// Multiple Intel GPU devices can be specified, native bfloat16 devicelib
// can be involved only when all GPU deivces specified support native
// bfloat16 native conversion.
UseNative = true;

if (Arg *SYCLTarget = Args.getLastArg(options::OPT_fsycl_targets_EQ)) {
for (auto TargetsV : SYCLTarget->getValues()) {
if (!checkSpirvJIT(StringRef(TargetsV)) &&
!GPUArchsWithNBF16.contains(StringRef(TargetsV))) {
UseNative = false;
break;
}
}
}
return NeedLibs;
}
}
return NeedLibs;
Expand Down Expand Up @@ -505,7 +554,8 @@ SYCL::getDeviceLibraries(const Compilation &C, const llvm::Triple &TargetTriple,
}

if (TargetTriple.isNVPTX() && IgnoreSingleLibs)
LibraryList.push_back(Args.MakeArgString("devicelib-nvptx64-nvidia-cuda.bc"));
LibraryList.push_back(
Args.MakeArgString("devicelib-nvptx64-nvidia-cuda.bc"));

if (TargetTriple.isAMDGCN() && IgnoreSingleLibs)
LibraryList.push_back(Args.MakeArgString("devicelib-amdgcn-amd-amdhsa.bc"));
Expand Down
106 changes: 106 additions & 0 deletions clang/test/Driver/sycl-device-lib-bfloat16.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,95 @@
// RUN: --sysroot=%S/Inputs/SYCL -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-FALLBACK


// Test AOT-DG2 compilation uses native libs + native libs.
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE

// Test AOT-PVC + AOT-DG2 compilation uses native libs + native libs.
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NATIVE

// Test AOT-PVC + AOT-DG1 compilation uses native libs + native libs.
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_dg1,intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-FALLBACK


// Test AOT-PVC + JIT compilation uses native libs + no libs
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spirv64 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64-unknown-unknown \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spirv64-unknown-unknown \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE

// Test test AOT-DG1 + JIT compilation uses native libs + no libs
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_dg1,spir64 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_dg1,spirv64 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_dg1,spir64-unknown-unknown \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_dg1,spirv64-unknown-unknown \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE

// Test test AOT-PVC + JIT compilation + AOT-DG2 uses native libs + no libs + native libs
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64,intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE-NATIVE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spirv64,intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE-NATIVE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64-unknown-unknown,intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE-NATIVE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spirv64-unknown-unknown,intel_gpu_acm_g10 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NONE-NATIVE

// Test test AOT-PVC + JIT compilation + AOT-DG1 uses fallback libs + no libs + fallback libs
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64,intel_gpu_dg1 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE-FALLBACK
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spirv64,intel_gpu_dg1 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE-FALLBACK
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64-unknown-unknown,intel_gpu_dg1 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE-FALLBACK
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spirv64-unknown-unknown,intel_gpu_dg1 \
// RUN: --sysroot=%S/Inputs/SYCL %s -### 2>&1 \
// RUN: | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-NONE-FALLBACK

// Test test AOT-PVC + AOT-DG1 specified via different options, uses fallback libs
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64_gen \
// RUN: --sysroot=%S/Inputs/SYCL -Xsycl-target-backend=spir64_gen "-device dg1" \
// RUN: %s -### 2>&1 | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-FALLBACK
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_dg1,spir64_gen \
// RUN: --sysroot=%S/Inputs/SYCL -Xsycl-target-backend=spir64_gen "-device pvc" \
// RUN: %s -### 2>&1 | FileCheck %s -check-prefix=BFLOAT16-FALLBACK-FALLBACK

// Test test AOT-PVC + AOT-BMG specified via different options, uses native libs
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_bmg_g21,spir64_gen \
// RUN: --sysroot=%S/Inputs/SYCL -Xsycl-target-backend=spir64_gen "-device pvc" \
// RUN: %s -### 2>&1 | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NATIVE
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_pvc,spir64_gen \
// RUN: --sysroot=%S/Inputs/SYCL -Xsycl-target-backend=spir64_gen "-device bmg-g21-a0" \
// RUN: %s -### 2>&1 | FileCheck %s -check-prefix=BFLOAT16-NATIVE-NATIVE

// BFLOAT16-NOT: llvm-link{{.*}} "{{.*}}libsycl-{{fallback|native}}-bfloat16.bc"

// BFLOAT16-NATIVE: llvm-link{{.*}} "{{.*}}libsycl-native-bfloat16.bc"
Expand All @@ -85,3 +174,20 @@

// BFLOAT16-FALLBACK-FALLBACK: llvm-link{{.*}} "{{.*}}libsycl-fallback-bfloat16.bc"
// BFLOAT16-FALLBACK-FALLBACK: "{{.*}}libsycl-fallback-bfloat16.bc"

// BFLOAT16-NATIVE-NATIVE: llvm-link{{.*}} "{{.*}}libsycl-native-bfloat16.bc"
// BFLOAT16-NATIVE-NATIVE: llvm-link{{.*}} "{{.*}}libsycl-native-bfloat16.bc"

// BFLOAT16-NATIVE-NONE: llvm-link{{.*}} "{{.*}}libsycl-native-bfloat16.bc"
// BFLOAT16-NATIVE-NONE-NOT: llvm-link{{.*}} "{{.*}}-bfloat16.bc"

// BFLOAT16-FALLBACK-NONE: llvm-link{{.*}} "{{.*}}libsycl-fallback-bfloat16.bc"
// BFLOAT16-FALLBACK-NONE-NOT: llvm-link{{.*}} "{{.*}}-bfloat16.bc"

// BFLOAT16-NATIVE-NONE-NATIVE: llvm-link{{.*}} "{{.*}}libsycl-native-bfloat16.bc"
// BFLOAT16-NATIVE-NONE-NATIVE-NOT: llvm-link{{.*}} "{{.*}}-bfloat16.bc"
// BFLOAT16-NATIVE-NONE-NATIVE: llvm-link{{.*}} "{{.*}}libsycl-native-bfloat16.bc"

// BFLOAT16-FALLBACK-NONE-FALLBACK: llvm-link{{.*}} "{{.*}}libsycl-fallback-bfloat16.bc"
// BFLOAT16-FALLBACK-NONE-FALLBACK-NOT: llvm-link{{.*}} "{{.*}}-bfloat16.bc"
// BFLOAT16-FALLBACK-NONE-FALLBACK: llvm-link{{.*}} "{{.*}}libsycl-fallback-bfloat16.bc"
Loading