maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AMDGPU] Disable forceful inline of non-kernel functions which use LDS. 

Now since LDS uses within non-kernel functions are being handled in the
pass - LowerModuleLDS, we *NO* need to *forcefully* inline non-kernel
functions just because they use LDS. Do forceful inlining only when the
pass - LowerModuleLDS is not enabled. It is enabled by default.

Reviewed By: JonChesterfield

Differential Revision: https://reviews.llvm.org/D100481
This commit is contained in:
hsmahesha 2021-04-15 09:12:46 +05:30
parent 90ae4d9030
commit 4973b0c4e7
5 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -120,10 +120,10 @@ static bool alwaysInlineImpl(Module &M, bool GlobalOpt) {
for (GlobalVariable &GV : M.globals()) { for (GlobalVariable &GV : M.globals()) {
// TODO: Region address // TODO: Region address
unsigned AS = GV.getAddressSpace(); unsigned AS = GV.getAddressSpace();
if (AS != AMDGPUAS::LOCAL_ADDRESS && AS != AMDGPUAS::REGION_ADDRESS) if ((AS == AMDGPUAS::REGION_ADDRESS) ||
continue; (AS == AMDGPUAS::LOCAL_ADDRESS &&
!AMDGPUTargetMachine::EnableLowerModuleLDS))
recursivelyVisitUsers(GV, FuncsToAlwaysInline); recursivelyVisitUsers(GV, FuncsToAlwaysInline);
} }
if (!AMDGPUTargetMachine::EnableFunctionCalls || StressCalls) { if (!AMDGPUTargetMachine::EnableFunctionCalls || StressCalls) {

9
llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
View File

@ -193,10 +193,10 @@ static cl::opt<bool> EnableStructurizerWorkarounds(
cl::desc("Enable workarounds for the StructurizeCFG pass"), cl::init(true), cl::desc("Enable workarounds for the StructurizeCFG pass"), cl::init(true),
cl::Hidden); cl::Hidden);
static cl::opt<bool> static cl::opt<bool, true> EnableLowerModuleLDS(
EnableLowerModuleLDS("amdgpu-enable-lower-module-lds", cl::Hidden, "amdgpu-enable-lower-module-lds", cl::desc("Enable lower module lds pass"),
cl::desc("Enable lower module lds pass"), cl::location(AMDGPUTargetMachine::EnableLowerModuleLDS), cl::init(true),
cl::init(true)); cl::Hidden);
extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() { extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
// Register the target // Register the target
@ -393,6 +393,7 @@ AMDGPUTargetMachine::AMDGPUTargetMachine(const Target &T, const Triple &TT,
bool AMDGPUTargetMachine::EnableLateStructurizeCFG = false; bool AMDGPUTargetMachine::EnableLateStructurizeCFG = false;
bool AMDGPUTargetMachine::EnableFunctionCalls = false; bool AMDGPUTargetMachine::EnableFunctionCalls = false;
bool AMDGPUTargetMachine::EnableFixedFunctionABI = false; bool AMDGPUTargetMachine::EnableFixedFunctionABI = false;
bool AMDGPUTargetMachine::EnableLowerModuleLDS = true;
AMDGPUTargetMachine::~AMDGPUTargetMachine() = default; AMDGPUTargetMachine::~AMDGPUTargetMachine() = default;

1
llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h
View File

@ -35,6 +35,7 @@ public:
static bool EnableLateStructurizeCFG; static bool EnableLateStructurizeCFG;
static bool EnableFunctionCalls; static bool EnableFunctionCalls;
static bool EnableFixedFunctionABI; static bool EnableFixedFunctionABI;
static bool EnableLowerModuleLDS;
AMDGPUTargetMachine(const Target &T, const Triple &TT, StringRef CPU, AMDGPUTargetMachine(const Target &T, const Triple &TT, StringRef CPU,
StringRef FS, TargetOptions Options, StringRef FS, TargetOptions Options,

6
llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address-codegen.ll
View File

@ -1,6 +1,6 @@
; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-function-calls -amdgpu-stress-function-calls < %s | FileCheck -check-prefix=GCN %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-function-calls -amdgpu-stress-function-calls -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls < %s | FileCheck -check-prefix=GCN %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=GCN %s ; RUN: llc -mtriple=amdgcn-amd-amdhsa -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=GCN %s
@lds0 = addrspace(3) global i32 undef, align 4 @lds0 = addrspace(3) global i32 undef, align 4

8
llvm/test/CodeGen/AMDGPU/force-alwaysinline-lds-global-address.ll
View File

@ -1,7 +1,7 @@
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s ; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s ; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s ; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -passes=amdgpu-always-inline %s | FileCheck --check-prefix=ALL %s ; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -passes=amdgpu-always-inline -amdgpu-enable-lower-module-lds=false %s | FileCheck --check-prefix=ALL %s
target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5" target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"