[SYCL] Add support to propagate compile flags to device backend compiler #8763
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,18 @@ | ||
| // RUN: %clangxx %s -O0 -S -o %t.ll -fsycl-device-only | ||
| // RUN: FileCheck %s --input-file %t.ll -check-prefixes=CHECK-IR | ||
| // CHECK-IR: define {{.*}} spir_kernel void @{{.*}}main{{.*}}sycl{{.*}}handler{{.*}}() #[[ATTR:[0-9]+]] | ||
| // CHECK-IR: attributes #[[ATTR]] = { {{.*}} "sycl-optlevel"="0" {{.*}}} | ||
|
|
||
| // This test checks adding of the attribute 'sycl-optlevel' | ||
| // by the clang front-end | ||
|
|
||
| #include <sycl/sycl.hpp> | ||
|
|
||
| int main() { | ||
| sycl::queue q; | ||
| q.submit([&](sycl::handler &h) { | ||
| h.single_task([=]() {}); | ||
| }); | ||
| return 0; | ||
| } | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| //===----- SYCLAddOptLevelAttribute.h - SYCLAddOptLevelAttribute Pass -----===// | ||
| // | ||
| // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. | ||
| // See https://llvm.org/LICENSE.txt for license information. | ||
| // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception | ||
| // | ||
| //===----------------------------------------------------------------------===// | ||
| // | ||
| // Pass adds 'sycl-optlevel' function attribute based on optimization level | ||
| // passed in. | ||
| // | ||
| //===----------------------------------------------------------------------===// | ||
| // | ||
| #ifndef LLVM_SYCL_ADD_OPT_LEVEL_ATTRIBUTE_H | ||
| #define LLVM_SYCL_ADD_OPT_LEVEL_ATTRIBUTE_H | ||
|
|
||
| #include "llvm/IR/PassManager.h" | ||
|
|
||
| namespace llvm { | ||
|
|
||
| class SYCLAddOptLevelAttributePass | ||
| : public PassInfoMixin<SYCLAddOptLevelAttributePass> { | ||
| public: | ||
| SYCLAddOptLevelAttributePass(int OptLevel = -1) : OptLevel{OptLevel} {}; | ||
| PreservedAnalyses run(Module &M, ModuleAnalysisManager &); | ||
|
|
||
| private: | ||
| int OptLevel; | ||
| }; | ||
|
|
||
| } // namespace llvm | ||
|
|
||
| #endif // LLVM_SYCL_ADD_OPT_LEVEL_ATTRIBUTE_H |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,30 @@ | ||
| //===---- SYCLAddOptLevelAttribute.cpp - SYCLAddOptLevelAttribute Pass ---===// | ||
| // | ||
| // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. | ||
| // See https://llvm.org/LICENSE.txt for license information. | ||
| // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception | ||
| // | ||
| //===---------------------------------------------------------------------===// | ||
| // | ||
| // Pass adds 'sycl-optlevel' function attribute based on optimization level | ||
| // passed in. | ||
| //===---------------------------------------------------------------------===// | ||
|
|
||
| #include "llvm/SYCLLowerIR/SYCLAddOptLevelAttribute.h" | ||
|
|
||
| #include "llvm/IR/Module.h" | ||
|
|
||
| using namespace llvm; | ||
|
|
||
| PreservedAnalyses | ||
| SYCLAddOptLevelAttributePass::run(Module &M, ModuleAnalysisManager &MAM) { | ||
| // Here, we add a function attribute 'sycl-optlevel' to store the | ||
| // optimization level. | ||
| assert(OptLevel >= 0 && "Invalid optimization level!"); | ||
| for (Function &F : M.functions()) { | ||
| if (F.isDeclaration()) | ||
| continue; | ||
| F.addFnAttr("sycl-optlevel", std::to_string(OptLevel)); | ||
| } | ||
| return PreservedAnalyses::all(); | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -10,29 +10,29 @@ | |
| ; RUN: sycl-post-link -split=auto -symbols -S < %s -o %t.table | ||
| ; RUN: FileCheck %s -input-file=%t_0.ll --check-prefixes CHECK-M0-IR \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_2.ll --check-prefixes CHECK-M1-IR \ | ||
|
There was a problem hiding this comment. These test updates were triggered by the fact that the order of the entries in the .table file changed due to the addition of the new entry in the list optional kernel features. A better way to NOT depend on the order of the entries is required in the long run. There was a problem hiding this comment. FYI: that unstable ordering is going to be fixed in #8833. That PR will also allow to simplify your changes to device code split down to a single line of code |
||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_1.ll --check-prefixes CHECK-M2-IR \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_0.sym --check-prefixes CHECK-M0-SYMS \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_2.sym --check-prefixes CHECK-M1-SYMS \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_1.sym --check-prefixes CHECK-M2-SYMS \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
|
|
||
| ; RUN: sycl-post-link -split=source -symbols -S < %s -o %t.table | ||
| ; RUN: FileCheck %s -input-file=%t_0.ll --check-prefixes CHECK-M0-IR \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_2.ll --check-prefixes CHECK-M1-IR \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_1.ll --check-prefixes CHECK-M2-IR \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_0.sym --check-prefixes CHECK-M0-SYMS \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_2.sym --check-prefixes CHECK-M1-SYMS \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
| ; RUN: FileCheck %s -input-file=%t_1.sym --check-prefixes CHECK-M2-SYMS \ | ||
| ; RUN: --implicit-check-not kernel0 --implicit-check-not kernel1 | ||
|
|
||
| ; RUN: sycl-post-link -split=kernel -symbols -S < %s -o %t.table | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,46 @@ | ||
| ; This test checks parsing of the attribute 'sycl-optlevel' | ||
| ; by the sycl-post-link-tool: | ||
| ; In addition to splitting requested by user, the kernels are also split based | ||
| ; on their optimization levels. | ||
| ; sycl-post-link adds 'optLevel' property to the device binary | ||
|
|
||
| ; RUN: sycl-post-link -split=source -symbols -S < %s -o %t.table | ||
| ; RUN: FileCheck %s -input-file=%t.table | ||
| ; RUN: FileCheck %s -input-file=%t_0.prop --check-prefixes CHECK-OPT-LEVEL-PROP-0 | ||
| ; RUN: FileCheck %s -input-file=%t_1.prop --check-prefixes CHECK-OPT-LEVEL-PROP-1 | ||
|
|
||
| ; CHECK: [Code|Properties|Symbols] | ||
| ; CHECK: {{.*}}_0.ll|{{.*}}_0.prop|{{.*}}_0.sym | ||
| ; CHECK: {{.*}}_1.ll|{{.*}}_1.prop|{{.*}}_1.sym | ||
|
|
||
| ; CHECK-OPT-LEVEL-PROP-0: optLevel=1|0 | ||
| ; CHECK-OPT-LEVEL-PROP-1: optLevel=1|2 | ||
|
|
||
| target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-n8:16:32:64" | ||
| target triple = "spir64-unknown-unknown" | ||
|
|
||
| define dso_local spir_func noundef i32 @_Z3fooii(i32 noundef %a, i32 noundef %b) local_unnamed_addr #0 { | ||
| entry: | ||
| %sub = sub nsw i32 %a, %b | ||
| ret i32 %sub | ||
| } | ||
|
|
||
| define dso_local spir_func noundef i32 @_Z3booii(i32 noundef %a, i32 noundef %b) #1 { | ||
| entry: | ||
| %retval = alloca i32, align 4 | ||
| %a.addr = alloca i32, align 4 | ||
| %b.addr = alloca i32, align 4 | ||
| %retval.ascast = addrspacecast i32* %retval to i32 addrspace(4)* | ||
| %a.addr.ascast = addrspacecast i32* %a.addr to i32 addrspace(4)* | ||
| %b.addr.ascast = addrspacecast i32* %b.addr to i32 addrspace(4)* | ||
| store i32 %a, i32 addrspace(4)* %a.addr.ascast, align 4 | ||
| store i32 %b, i32 addrspace(4)* %b.addr.ascast, align 4 | ||
| %0 = load i32, i32 addrspace(4)* %a.addr.ascast, align 4 | ||
| %1 = load i32, i32 addrspace(4)* %b.addr.ascast, align 4 | ||
| %add = add nsw i32 %0, %1 | ||
| ret i32 %add | ||
| } | ||
|
|
||
| attributes #0 = { mustprogress nofree norecurse nosync nounwind willreturn memory(none) "sycl-module-id"="test3.cpp" "sycl-optlevel"="2" } | ||
| attributes #1 = { convergent mustprogress noinline norecurse nounwind optnone "sycl-module-id"="test2.cpp" "sycl-optlevel"="0" } | ||
|
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do we need an additional test with explicit
__attribute__((optnone))on the kernel/device function?There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
My changes do not interact with this attribute. The backend should be responsible to decide whether the attribute or the option takes precedence.
Thanks