-
Notifications
You must be signed in to change notification settings - Fork 10.8k
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.
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
[NewPM][AMDGPU] Add AMDGPUPassRegistry.def #86095
Merged
Merged
Conversation
This file contains 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
@llvm/pr-subscribers-backend-amdgpu Author: None (paperchalice) ChangesMove the pass registry to a separate file, prepare for porting dag-isel. Full diff: https://github.com/llvm/llvm-project/pull/86095.diff 2 Files Affected:
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
new file mode 100644
index 00000000000000..90f36fadf35903
--- /dev/null
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPassRegistry.def
@@ -0,0 +1,73 @@
+//===- AMDGPUPassRegistry.def - Registry of AMDGPU passes -------*- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// This file is used as the registry of passes that are part of the
+// AMDGPU backend.
+//
+//===----------------------------------------------------------------------===//
+
+// NOTE: NO INCLUDE GUARD DESIRED!
+
+#ifndef MODULE_PASS
+#define MODULE_PASS(NAME, CREATE_PASS)
+#endif
+MODULE_PASS("amdgpu-always-inline", AMDGPUAlwaysInlinePass())
+MODULE_PASS("amdgpu-attributor", AMDGPUAttributorPass(*this))
+MODULE_PASS("amdgpu-lower-buffer-fat-pointers",
+ AMDGPULowerBufferFatPointersPass(*this))
+MODULE_PASS("amdgpu-lower-ctor-dtor", AMDGPUCtorDtorLoweringPass())
+MODULE_PASS("amdgpu-lower-module-lds", AMDGPULowerModuleLDSPass(*this))
+MODULE_PASS("amdgpu-printf-runtime-binding", AMDGPUPrintfRuntimeBindingPass())
+MODULE_PASS("amdgpu-unify-metadata", AMDGPUUnifyMetadataPass())
+#undef MODULE_PASS
+
+#ifndef FUNCTION_PASS
+#define FUNCTION_PASS(NAME, CREATE_PASS)
+#endif
+FUNCTION_PASS("amdgpu-codegenprepare", AMDGPUCodeGenPreparePass(*this))
+FUNCTION_PASS("amdgpu-image-intrinsic-opt",
+ AMDGPUImageIntrinsicOptimizerPass(*this))
+FUNCTION_PASS("amdgpu-lower-kernel-arguments",
+ AMDGPULowerKernelArgumentsPass(*this))
+FUNCTION_PASS("amdgpu-lower-kernel-attributes",
+ AMDGPULowerKernelAttributesPass())
+FUNCTION_PASS("amdgpu-simplifylib", AMDGPUSimplifyLibCallsPass())
+FUNCTION_PASS("amdgpu-promote-alloca", AMDGPUPromoteAllocaPass(*this))
+FUNCTION_PASS("amdgpu-promote-alloca-to-vector",
+ AMDGPUPromoteAllocaToVectorPass(*this))
+FUNCTION_PASS("amdgpu-promote-kernel-arguments",
+ AMDGPUPromoteKernelArgumentsPass())
+FUNCTION_PASS("amdgpu-rewrite-undef-for-phi", AMDGPURewriteUndefForPHIPass())
+FUNCTION_PASS("amdgpu-unify-divergent-exit-nodes",
+ AMDGPUUnifyDivergentExitNodesPass())
+FUNCTION_PASS("amdgpu-usenative", AMDGPUUseNativeCallsPass())
+#undef FUNCTION_PASS
+
+#ifndef FUNCTION_ANALYSIS
+#define FUNCTION_ANALYSIS(NAME, CREATE_PASS)
+#endif
+
+#ifndef FUNCTION_ALIAS_ANALYSIS
+#define FUNCTION_ALIAS_ANALYSIS(NAME, CREATE_PASS) \
+ FUNCTION_ANALYSIS(NAME, CREATE_PASS)
+#endif
+FUNCTION_ALIAS_ANALYSIS("amdgpu-aa", AMDGPUAA())
+#undef FUNCTION_ALIAS_ANALYSIS
+#undef FUNCTION_ANALYSIS
+
+#ifndef FUNCTION_PASS_WITH_PARAMS
+#define FUNCTION_PASS_WITH_PARAMS(NAME, CLASS, CREATE_PASS, PARSER, PARAMS)
+#endif
+FUNCTION_PASS_WITH_PARAMS(
+ "amdgpu-atomic-optimizer",
+ "AMDGPUAtomicOptimizerPass",
+ [=](ScanOptions Strategy) {
+ return AMDGPUAtomicOptimizerPass(*this, Strategy);
+ },
+ parseAMDGPUAtomicOptimizerStrategy, "strategy=dpp|iterative|none")
+#undef FUNCTION_PASS_WITH_PARAMS
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 2b457fe519d96c..98323d0d28a2e4 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -631,107 +631,26 @@ void AMDGPUTargetMachine::registerDefaultAliasAnalyses(AAManager &AAM) {
AAM.registerFunctionAnalysis<AMDGPUAA>();
}
+static Expected<ScanOptions>
+parseAMDGPUAtomicOptimizerStrategy(StringRef Params) {
+ if (Params.consume_front("strategy=")) {
+ if (Params == "dpp")
+ return ScanOptions::DPP;
+ if (Params == "iterative")
+ return ScanOptions::Iterative;
+ if (Params == "none")
+ return ScanOptions::None;
+ return make_error<StringError>("invalid parameter",
+ inconvertibleErrorCode());
+ }
+ return ScanOptions::Iterative;
+}
+
void AMDGPUTargetMachine::registerPassBuilderCallbacks(
PassBuilder &PB, bool PopulateClassToPassNames) {
- PB.registerPipelineParsingCallback(
- [this](StringRef PassName, ModulePassManager &PM,
- ArrayRef<PassBuilder::PipelineElement>) {
- if (PassName == "amdgpu-attributor") {
- PM.addPass(AMDGPUAttributorPass(*this));
- return true;
- }
- if (PassName == "amdgpu-unify-metadata") {
- PM.addPass(AMDGPUUnifyMetadataPass());
- return true;
- }
- if (PassName == "amdgpu-printf-runtime-binding") {
- PM.addPass(AMDGPUPrintfRuntimeBindingPass());
- return true;
- }
- if (PassName == "amdgpu-always-inline") {
- PM.addPass(AMDGPUAlwaysInlinePass());
- return true;
- }
- if (PassName == "amdgpu-lower-module-lds") {
- PM.addPass(AMDGPULowerModuleLDSPass(*this));
- return true;
- }
- if (PassName == "amdgpu-lower-buffer-fat-pointers") {
- PM.addPass(AMDGPULowerBufferFatPointersPass(*this));
- return true;
- }
- if (PassName == "amdgpu-lower-ctor-dtor") {
- PM.addPass(AMDGPUCtorDtorLoweringPass());
- return true;
- }
- return false;
- });
- PB.registerPipelineParsingCallback(
- [this](StringRef PassName, FunctionPassManager &PM,
- ArrayRef<PassBuilder::PipelineElement>) {
- if (PassName == "amdgpu-simplifylib") {
- PM.addPass(AMDGPUSimplifyLibCallsPass());
- return true;
- }
- if (PassName == "amdgpu-image-intrinsic-opt") {
- PM.addPass(AMDGPUImageIntrinsicOptimizerPass(*this));
- return true;
- }
- if (PassName == "amdgpu-usenative") {
- PM.addPass(AMDGPUUseNativeCallsPass());
- return true;
- }
- if (PassName == "amdgpu-promote-alloca") {
- PM.addPass(AMDGPUPromoteAllocaPass(*this));
- return true;
- }
- if (PassName == "amdgpu-promote-alloca-to-vector") {
- PM.addPass(AMDGPUPromoteAllocaToVectorPass(*this));
- return true;
- }
- if (PassName == "amdgpu-lower-kernel-attributes") {
- PM.addPass(AMDGPULowerKernelAttributesPass());
- return true;
- }
- if (PassName == "amdgpu-promote-kernel-arguments") {
- PM.addPass(AMDGPUPromoteKernelArgumentsPass());
- return true;
- }
- if (PassName == "amdgpu-unify-divergent-exit-nodes") {
- PM.addPass(AMDGPUUnifyDivergentExitNodesPass());
- return true;
- }
- if (PassName == "amdgpu-atomic-optimizer") {
- PM.addPass(
- AMDGPUAtomicOptimizerPass(*this, AMDGPUAtomicOptimizerStrategy));
- return true;
- }
- if (PassName == "amdgpu-codegenprepare") {
- PM.addPass(AMDGPUCodeGenPreparePass(*this));
- return true;
- }
- if (PassName == "amdgpu-lower-kernel-arguments") {
- PM.addPass(AMDGPULowerKernelArgumentsPass(*this));
- return true;
- }
- if (PassName == "amdgpu-rewrite-undef-for-phi") {
- PM.addPass(AMDGPURewriteUndefForPHIPass());
- return true;
- }
- return false;
- });
-
- PB.registerAnalysisRegistrationCallback([](FunctionAnalysisManager &FAM) {
- FAM.registerPass([&] { return AMDGPUAA(); });
- });
- PB.registerParseAACallback([](StringRef AAName, AAManager &AAM) {
- if (AAName == "amdgpu-aa") {
- AAM.registerFunctionAnalysis<AMDGPUAA>();
- return true;
- }
- return false;
- });
+#define GET_PASS_REGISTRY "AMDGPUPassRegistry.def"
+#include "llvm/Passes/TargetPassRegistry.inc"
PB.registerPipelineStartEPCallback(
[](ModulePassManager &PM, OptimizationLevel Level) {
|
paperchalice
force-pushed
the
amdgpu-registry
branch
from
March 21, 2024 07:24
cb1df90
to
bc2a45c
Compare
arsenm
approved these changes
Mar 21, 2024
Comment on lines
637
to
642
if (Params == "dpp") | ||
return ScanOptions::DPP; | ||
if (Params == "iterative") | ||
return ScanOptions::Iterative; | ||
if (Params == "none") | ||
return ScanOptions::None; |
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.
Could turn this into StringSwitch
paperchalice
force-pushed
the
amdgpu-registry
branch
from
March 21, 2024 09:55
bc2a45c
to
87d7c67
Compare
paperchalice
force-pushed
the
amdgpu-registry
branch
from
March 21, 2024 10:51
87d7c67
to
c969c16
Compare
aeubanks
approved these changes
Mar 21, 2024
chencha3
pushed a commit
to chencha3/llvm-project
that referenced
this pull request
Mar 23, 2024
Move the pass registry to a separate file, prepare for porting dag-isel.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Move the pass registry to a separate file, prepare for porting dag-isel.