https://github.com/arsenm updated
https://github.com/llvm/llvm-project/pull/102867
>From 12b9f7af4cb81d0dfc6c59d9472acb0d73c8d209 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <matthew.arsena...@amd.com>
Date: Mon, 12 Aug 2024 13:09:55 +0400
Subject: [PATCH] AMDGPU/NewPM: Fill out passes in addCodeGenPrepare
AMDGPUAnnotateKernelFeatures hasn't been ported yet, but it
should be soon removable.
---
.../lib/Target/AMDGPU/AMDGPUTargetMachine.cpp | 27 +++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
index 23a7a5e590071..40201d8eaa1f2 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -1773,8 +1773,35 @@ AMDGPUCodeGenPassBuilder::AMDGPUCodeGenPassBuilder(
}
void AMDGPUCodeGenPassBuilder::addCodeGenPrepare(AddIRPass &addPass) const {
+ // AMDGPUAnnotateKernelFeaturesPass is missing here, but it will hopefully be
+ // deleted soon.
+
+ if (EnableLowerKernelArguments)
+ addPass(AMDGPULowerKernelArgumentsPass(TM));
+
+ // This lowering has been placed after codegenprepare to take advantage of
+ // address mode matching (which is why it isn't put with the LDS lowerings).
+ // It could be placed anywhere before uniformity annotations (an analysis
+ // that it changes by splitting up fat pointers into their components)
+ // but has been put before switch lowering and CFG flattening so that those
+ // passes can run on the more optimized control flow this pass creates in
+ // many cases.
+ //
+ // FIXME: This should ideally be put after the LoadStoreVectorizer.
+ // However, due to some annoying facts about ResourceUsageAnalysis,
+ // (especially as exercised in the resource-usage-dead-function test),
+ // we need all the function passes codegenprepare all the way through
+ // said resource usage analysis to run on the call graph produced
+ // before codegenprepare runs (because codegenprepare will knock some
+ // nodes out of the graph, which leads to function-level passes not
+ // being run on them, which causes crashes in the resource usage analysis).
+ addPass(AMDGPULowerBufferFatPointersPass(TM));
+
Base::addCodeGenPrepare(addPass);
+ if (isPassEnabled(EnableLoadStoreVectorizer))
+ addPass(LoadStoreVectorizerPass());
+
// LowerSwitch pass may introduce unreachable blocks that can cause
unexpected
// behavior for subsequent passes. Placing it here seems better that these
// blocks would get cleaned up by UnreachableBlockElim inserted next in the
_______________________________________________
llvm-branch-commits mailing list
llvm-branch-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
