AMDGPU: Remove AMDGPUFixFunctionBitcasts pass

[arsenm]

Summary

This was a workaround for not supporting indirect calls when
instcombine didn't eliminate constant expression casts of the callee
at -O0. Indirect calls are supposed to work now, so drop the hack.

[JonChesterfield]

Nice, thanks!

[arsenm]

2b4876157562bc76e86f193d371348993905bc61

llvm/lib/Target/AMDGPU/AMDGPU.h

 FunctionPass *createAMDGPUAtomicOptimizerPass();
 void initializeAMDGPUAtomicOptimizerPass(PassRegistry &);
 extern char &AMDGPUAtomicOptimizerID;
 
 ModulePass *createAMDGPULowerIntrinsicsPass();
 void initializeAMDGPULowerIntrinsicsPass(PassRegistry &);
 extern char &AMDGPULowerIntrinsicsID;
 
-ModulePass *createAMDGPUFixFunctionBitcastsPass();
-void initializeAMDGPUFixFunctionBitcastsPass(PassRegistry &);
-extern char &AMDGPUFixFunctionBitcastsID;
-
 ModulePass *createAMDGPUCtorDtorLoweringPass();
 void initializeAMDGPUCtorDtorLoweringPass(PassRegistry &);
 extern char &AMDGPUCtorDtorLoweringID;
 
 FunctionPass *createAMDGPULowerKernelArgumentsPass();
 void initializeAMDGPULowerKernelArgumentsPass(PassRegistry &);
 extern char &AMDGPULowerKernelArgumentsID;
 

llvm/lib/Target/AMDGPU/AMDGPUFixFunctionBitcasts.cpp

-//===-- AMDGPUFixFunctionBitcasts.cpp - Fix function bitcasts -------------===//
-//
-// 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
-//
-//===----------------------------------------------------------------------===//
-///
-/// \file
-/// Promote indirect (bitcast) calls to direct calls when they are statically
-/// known to be direct. Required when InstCombine is not run (e.g. at OptNone)
-/// because AMDGPU does not support indirect calls.
-///
-//===----------------------------------------------------------------------===//
-
-#include "AMDGPU.h"
-#include "llvm/IR/InstVisitor.h"
-#include "llvm/Pass.h"
-#include "llvm/Transforms/Utils/CallPromotionUtils.h"
-
-using namespace llvm;
-
-#define DEBUG_TYPE "amdgpu-fix-function-bitcasts"
-
-namespace {
-class AMDGPUFixFunctionBitcasts final
-    : public ModulePass,
-      public InstVisitor<AMDGPUFixFunctionBitcasts> {
-
-  bool runOnModule(Module &M) override;
-
-  bool Modified;
-
-public:
-  void visitCallBase(CallBase &CB) {
-    if (CB.getCalledFunction())
-      return;
-    auto *Callee =
-        dyn_cast<Function>(CB.getCalledOperand()->stripPointerCasts());
-    if (Callee && isLegalToPromote(CB, Callee)) {
-      promoteCall(CB, Callee);
-      Modified = true;
-    }
-  }
-
-  static char ID;
-  AMDGPUFixFunctionBitcasts() : ModulePass(ID) {}
-};
-} // End anonymous namespace
-
-char AMDGPUFixFunctionBitcasts::ID = 0;
-char &llvm::AMDGPUFixFunctionBitcastsID = AMDGPUFixFunctionBitcasts::ID;
-INITIALIZE_PASS(AMDGPUFixFunctionBitcasts, DEBUG_TYPE,
-                "Fix function bitcasts for AMDGPU", false, false)
-
-ModulePass *llvm::createAMDGPUFixFunctionBitcastsPass() {
-  return new AMDGPUFixFunctionBitcasts();
-}
-
-bool AMDGPUFixFunctionBitcasts::runOnModule(Module &M) {
-  Modified = false;
-  visit(M);
-  return Modified;
-}

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   initializeSIFixSGPRCopiesPass(*PR);
   initializeSIFixVGPRCopiesPass(*PR);
   initializeSIFoldOperandsPass(*PR);
   initializeSIPeepholeSDWAPass(*PR);
   initializeSIShrinkInstructionsPass(*PR);
   initializeSIOptimizeExecMaskingPreRAPass(*PR);
   initializeSIOptimizeVGPRLiveRangePass(*PR);
   initializeSILoadStoreOptimizerPass(*PR);
-  initializeAMDGPUFixFunctionBitcastsPass(*PR);
   initializeAMDGPUCtorDtorLoweringPass(*PR);
   initializeAMDGPUAlwaysInlinePass(*PR);
   initializeAMDGPUAttributorPass(*PR);
   initializeAMDGPUAnnotateKernelFeaturesPass(*PR);
   initializeAMDGPUAnnotateUniformValuesPass(*PR);
   initializeAMDGPUArgumentUsageInfoPass(*PR);
   initializeAMDGPUAtomicOptimizerPass(*PR);
   initializeAMDGPULowerKernelArgumentsPass(*PR);
void AMDGPUPassConfig::addIRPasses() {
   // There is no reason to run these.
   disablePass(&StackMapLivenessID);
   disablePass(&FuncletLayoutID);
   disablePass(&PatchableFunctionID);
 
   addPass(createAMDGPUPrintfRuntimeBinding());
   addPass(createAMDGPUCtorDtorLoweringPass());
 
-  // This must occur before inlining, as the inliner will not look through
-  // bitcast calls.
-  addPass(createAMDGPUFixFunctionBitcastsPass());
-
   // A call to propagate attributes pass in the backend in case opt was not run.
   addPass(createAMDGPUPropagateAttributesEarlyPass(&TM));
 
   addPass(createAMDGPULowerIntrinsicsPass());
 
   // Function calls are not supported, so make sure we inline everything.
   addPass(createAMDGPUAlwaysInlinePass());
   addPass(createAlwaysInlinerLegacyPass());

llvm/lib/Target/AMDGPU/CMakeLists.txt

add_llvm_target(AMDGPUCodeGen
   AMDGPUAsmPrinter.cpp
   AMDGPUAtomicOptimizer.cpp
   AMDGPUAttributor.cpp
   AMDGPUCallLowering.cpp
   AMDGPUCodeGenPrepare.cpp
   AMDGPUCombinerHelper.cpp
   AMDGPUCtorDtorLowering.cpp
   AMDGPUExportClustering.cpp
-  AMDGPUFixFunctionBitcasts.cpp
   AMDGPUFrameLowering.cpp
   AMDGPUGlobalISelUtils.cpp
   AMDGPUHSAMetadataStreamer.cpp
   AMDGPUInstCombineIntrinsic.cpp
   AMDGPUInstrInfo.cpp
   AMDGPUInstructionSelector.cpp
   AMDGPUISelDAGToDAG.cpp
   AMDGPUISelLowering.cpp

llvm/test/CodeGen/AMDGPU/call-constexpr.ll

 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-fix-function-bitcasts < %s | FileCheck -check-prefix=OPT %s
 
 ; GCN-LABEL: {{^}}test_bitcast_return_type_noinline:
 ; GCN: s_getpc_b64
 ; GCN: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, ret_i32_noinline@rel32@lo+4
 ; GCN: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, ret_i32_noinline@rel32@hi+12
 ; GCN: s_swappc_b64
-; OPT-LABEL: @test_bitcast_return_type_noinline(
-; OPT: %val = call i32 @ret_i32_noinline()
-; OPT: bitcast i32 %val to float
 define amdgpu_kernel void @test_bitcast_return_type_noinline() #0 {
   %val = call float bitcast (i32()* @ret_i32_noinline to float()*)()
   %op = fadd float %val, 1.0
   store volatile float %op, float addrspace(1)* undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_bitcast_return_type_alwaysinline:
-; GCN-NOT: s_getpc_b64
-; GCN-NOT: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, ret_i32_alwaysinline@rel32@lo+4
-; GCN-NOT: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, ret_i32_alwaysinline@rel32@hi+12
-; GCN-NOT: s_swappc_b64
-; OPT-LABEL: @test_bitcast_return_type_alwaysinline(
-; OPT: %val = call i32 @ret_i32_alwaysinline()
-; OPT: bitcast i32 %val to float
+; GCN: s_swappc_b64
 define amdgpu_kernel void @test_bitcast_return_type_alwaysinline() #0 {
   %val = call float bitcast (i32()* @ret_i32_alwaysinline to float()*)()
   %op = fadd float %val, 1.0
   store volatile float %op, float addrspace(1)* undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_bitcast_argument_type:
 ; GCN: s_getpc_b64
 ; GCN: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, ident_i32@rel32@lo+4
 ; GCN: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, ident_i32@rel32@hi+12
 ; GCN: s_swappc_b64
-; OPT-LABEL: @test_bitcast_argument_type(
-; OPT: %1 = bitcast float 2.000000e+00 to i32
-; OPT: %val = call i32 @ident_i32(i32 %1)
-; OPT-NOT: bitcast i32 %val to float
 define amdgpu_kernel void @test_bitcast_argument_type() #0 {
   %val = call i32 bitcast (i32(i32)* @ident_i32 to i32(float)*)(float 2.0)
   %op = add i32 %val, 1
   store volatile i32 %op, i32 addrspace(1)* undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_bitcast_argument_and_return_types:
 ; GCN: s_getpc_b64
 ; GCN: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, ident_i32@rel32@lo+4
 ; GCN: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, ident_i32@rel32@hi+12
 ; GCN: s_swappc_b64
-; OPT-LABEL: @test_bitcast_argument_and_return_types(
-; OPT: %1 = bitcast float 2.000000e+00 to i32
-; OPT: %val = call i32 @ident_i32(i32 %1)
-; OPT: bitcast i32 %val to float
 define amdgpu_kernel void @test_bitcast_argument_and_return_types() #0 {
   %val = call float bitcast (i32(i32)* @ident_i32 to float(float)*)(float 2.0)
   %op = fadd float %val, 1.0
   store volatile float %op, float addrspace(1)* undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}use_workitem_id_x:

 ; GCN-LABEL: {{^}}test_bitcast_use_workitem_id_x:
 ; GCN: v_mov_b32_e32 v31, v0
 ; GCN: s_getpc_b64
 ; GCN: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, use_workitem_id_x@rel32@lo+4
 ; GCN: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, use_workitem_id_x@rel32@hi+12
 ; GCN: v_mov_b32_e32 v0, 9
 ; GCN: s_swappc_b64
 ; GCN: v_add_f32_e32
-; OPT-LABEL: @use_workitem_id_x(
-; OPT: %val = call i32 @use_workitem_id_x(i32 9)
-; OPT: bitcast i32 %val to float
 define amdgpu_kernel void @test_bitcast_use_workitem_id_x() #0 {
   %val = call float bitcast (i32(i32)* @use_workitem_id_x to float(i32)*)(i32 9)
   %op = fadd float %val, 1.0
   store volatile float %op, float addrspace(1)* undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_invoke:
 ; GCN: s_getpc_b64
 ; GCN: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, ident_i32@rel32@lo+4
 ; GCN: s_addc_u32 s{{[0-9]+}}, s{{[0-9]+}}, ident_i32@rel32@hi+12
 ; GCN: s_swappc_b64
-; OPT-LABEL: @test_invoke(
-; OPT: %1 = bitcast float 2.000000e+00 to i32
-; OPT: %val = invoke i32 @ident_i32(i32 %1)
-; OPT-NEXT: to label %continue.split unwind label %broken
-; OPT-LABEL: continue.split:
-; OPT: bitcast i32 %val to float
 @_ZTIi = external global i8*
 declare i32 @__gxx_personality_v0(...)
 define amdgpu_kernel void @test_invoke() #0 personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
   %val = invoke float bitcast (i32(i32)* @ident_i32 to float(float)*)(float 2.0)
           to label %continue unwind label %broken
 
 broken:
   landingpad { i8*, i32 } catch i8** @_ZTIi