shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[AMDGPU] Add an option to completely disable kernel argument preload (#153975)

Browse Source 
The existing `amdgpu-kernarg-preload-count` can't be used as a switch to
turn it off if it is set to 0. This PR adds an extra option to turn it
off.

Fixes SWDEV-550147.
This commit is contained in:
Shilei Tian 2025-08-18 09:44:20 -04:00 committed by GitHub
parent f38c83c582
commit e37eff5dcd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 37 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/AMDGPU/AMDGPUPreloadKernelArguments.cpp
View File

@ -37,6 +37,11 @@ static cl::opt<unsigned> KernargPreloadCount(
"amdgpu-kernarg-preload-count", "amdgpu-kernarg-preload-count",
cl::desc("How many kernel arguments to preload onto SGPRs"), cl::init(0)); cl::desc("How many kernel arguments to preload onto SGPRs"), cl::init(0));
static cl::opt<bool>
EnableKernargPreload("amdgpu-kernarg-preload",
cl::desc("Enable preload kernel arguments to SGPRs"),
cl::init(true));
namespace { namespace {
class AMDGPUPreloadKernelArgumentsLegacy : public ModulePass { class AMDGPUPreloadKernelArgumentsLegacy : public ModulePass {
@ -275,6 +280,9 @@ AMDGPUPreloadKernelArgumentsLegacy::AMDGPUPreloadKernelArgumentsLegacy(
: ModulePass(ID), TM(TM) {} : ModulePass(ID), TM(TM) {}
static bool markKernelArgsAsInreg(Module &M, const TargetMachine &TM) { static bool markKernelArgsAsInreg(Module &M, const TargetMachine &TM) {
if (!EnableKernargPreload)
return false;
SmallVector<Function *, 4> FunctionsToErase; SmallVector<Function *, 4> FunctionsToErase;
bool Changed = false; bool Changed = false;
for (auto &F : M) { for (auto &F : M) {

29
llvm/test/CodeGen/AMDGPU/disable-preload-kernargs.ll Normal file
View File

@ -0,0 +1,29 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -passes=amdgpu-preload-kernel-arguments -amdgpu-kernarg-preload=0 %s -o - | FileCheck -check-prefix=NO-PRELOAD %s
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -passes=amdgpu-preload-kernel-arguments %s -o - | FileCheck -check-prefix=DEFAULT-PRELOAD %s
@g1 = protected addrspace(1) externally_initialized global i16 0, align 2
define amdgpu_kernel void @test_kernel_with_zero_kernel_arg() {
; NO-PRELOAD-LABEL: define amdgpu_kernel void @test_kernel_with_zero_kernel_arg(
; NO-PRELOAD-SAME: ) #[[ATTR0:[0-9]+]] {
; NO-PRELOAD-NEXT: [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; NO-PRELOAD-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 12
; NO-PRELOAD-NEXT: [[GROUP_SIZE_X:%.*]] = load i16, ptr addrspace(4) [[GEP]], align 2
; NO-PRELOAD-NEXT: store i16 [[GROUP_SIZE_X]], ptr addrspace(1) @g1, align 2
; NO-PRELOAD-NEXT: ret void
;
; DEFAULT-PRELOAD-LABEL: define amdgpu_kernel void @test_kernel_with_zero_kernel_arg(
; DEFAULT-PRELOAD-SAME: i32 inreg "amdgpu-hidden-argument" [[_HIDDEN_BLOCK_COUNT_X:%.*]], i32 inreg "amdgpu-hidden-argument" [[_HIDDEN_BLOCK_COUNT_Y:%.*]], i32 inreg "amdgpu-hidden-argument" [[_HIDDEN_BLOCK_COUNT_Z:%.*]], i16 inreg "amdgpu-hidden-argument" [[_HIDDEN_GROUP_SIZE_X:%.*]]) #[[ATTR0:[0-9]+]] {
; DEFAULT-PRELOAD-NEXT: [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
; DEFAULT-PRELOAD-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 12
; DEFAULT-PRELOAD-NEXT: [[GROUP_SIZE_X:%.*]] = load i16, ptr addrspace(4) [[GEP]], align 2
; DEFAULT-PRELOAD-NEXT: store i16 [[_HIDDEN_GROUP_SIZE_X]], ptr addrspace(1) @g1, align 2
; DEFAULT-PRELOAD-NEXT: ret void
;
%implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
%gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 12
%group_size_x = load i16, ptr addrspace(4) %gep
store i16 %group_size_x, ptr addrspace(1) @g1
ret void
}