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

[hsmhsm]

Summary

Since now, 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.

[arsenm]

llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp

120

Having "Update" in a comment doesn't make sense. Just explain the current situation

[hsmhsm]

Address the review comments by Matt.

[JonChesterfield]

Looks good to me. This will presumably increase the uses of the lower module lds pass. Maybe prudent to run it through the gerrit CI infra before landing?

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

196–199

Enable reads better than disable, thanks

[hsmhsm]

The https://reviews.llvm.org/D91516 also includes changes in this current patch, hence this patch is no longer required. All the review discussions and comments can be taken care within https://reviews.llvm.org/D91516 itself.

llvm/lib/Target/AMDGPU/AMDGPUAlwaysInlinePass.cpp

static bool alwaysInlineImpl(Module &M, bool GlobalOpt) {
   // is something of a workaround because we don't have a way of supporting LDS
   // objects defined in functions. LDS is always allocated by a kernel, and it
   // is difficult to manage LDS usage if a function may be used by multiple
   // kernels.
   //
   // OpenCL doesn't allow declaring LDS in non-kernels, so in practice this
   // should only appear when IPO passes manages to move LDs defined in a kernel
   // into a single user function.
+  //
+  // Update: Since now 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.
 
+  if (!AMDGPUTargetMachine::EnableLowerModuleLDS) {
     for (GlobalVariable &GV : M.globals()) {
       // TODO: Region address
       unsigned AS = GV.getAddressSpace();
       if (AS != AMDGPUAS::LOCAL_ADDRESS && AS != AMDGPUAS::REGION_ADDRESS)
         continue;
 
       recursivelyVisitUsers(GV, FuncsToAlwaysInline);
     }
+  }
 
   if (!AMDGPUTargetMachine::EnableFunctionCalls || StressCalls) {
     auto IncompatAttr
       = StressCalls ? Attribute::AlwaysInline : Attribute::NoInline;
 
     for (Function &F : M) {
       if (!F.isDeclaration() && !F.use_empty() &&
           !F.hasFnAttribute(IncompatAttr)) {

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.h

protected:
 
   StringRef getGPUName(const Function &F) const;
   StringRef getFeatureString(const Function &F) const;
 
 public:
   static bool EnableLateStructurizeCFG;
   static bool EnableFunctionCalls;
   static bool EnableFixedFunctionABI;
+  static bool EnableLowerModuleLDS;
 
   AMDGPUTargetMachine(const Target &T, const Triple &TT, StringRef CPU,
                       StringRef FS, TargetOptions Options,
                       Optional<Reloc::Model> RM, Optional<CodeModel::Model> CM,
                       CodeGenOpt::Level OL);
   ~AMDGPUTargetMachine() override;
 
   const TargetSubtargetInfo *getSubtargetImpl() const;

llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

static cl::opt<bool> EnableScalarIRPasses(
   cl::init(true),
   cl::Hidden);
 
 static cl::opt<bool> EnableStructurizerWorkarounds(
     "amdgpu-enable-structurizer-workarounds",
     cl::desc("Enable workarounds for the StructurizeCFG pass"), cl::init(true),
     cl::Hidden);
 
-static cl::opt<bool>
-    DisableLowerModuleLDS("amdgpu-disable-lower-module-lds", cl::Hidden,
-                          cl::desc("Disable lower module lds pass"),
-                          cl::init(false));
+static cl::opt<bool, true> EnableLowerModuleLDS(
+    "amdgpu-enable-lower-module-lds", cl::desc("Enable lower module lds pass"),
+    cl::location(AMDGPUTargetMachine::EnableLowerModuleLDS), cl::init(true),
+    cl::Hidden);
 
 extern "C" LLVM_EXTERNAL_VISIBILITY void LLVMInitializeAMDGPUTarget() {
   // Register the target
   RegisterTargetMachine<R600TargetMachine> X(getTheAMDGPUTarget());
   RegisterTargetMachine<GCNTargetMachine> Y(getTheGCNTarget());
 
   PassRegistry *PR = PassRegistry::getPassRegistry();
   initializeR600ClauseMergePassPass(*PR);
AMDGPUTargetMachine::AMDGPUTargetMachine(const Target &T, const Triple &TT,
   if (TT.getOS() == Triple::AMDHSA &&
       EnableAMDGPUFixedFunctionABIOpt.getNumOccurrences() == 0)
     EnableFixedFunctionABI = true;
 }
 
 bool AMDGPUTargetMachine::EnableLateStructurizeCFG = false;
 bool AMDGPUTargetMachine::EnableFunctionCalls = false;
 bool AMDGPUTargetMachine::EnableFixedFunctionABI = false;
+bool AMDGPUTargetMachine::EnableLowerModuleLDS = false;
 
 AMDGPUTargetMachine::~AMDGPUTargetMachine() = default;
 
 StringRef AMDGPUTargetMachine::getGPUName(const Function &F) const {
   Attribute GPUAttr = F.getFnAttribute("target-cpu");
   return GPUAttr.isValid() ? GPUAttr.getValueAsString() : getTargetCPU();
 }
 
void AMDGPUPassConfig::addIRPasses() {
   // Handle uses of OpenCL image2d_t, image3d_t and sampler_t arguments.
   if (TM.getTargetTriple().getArch() == Triple::r600)
     addPass(createR600OpenCLImageTypeLoweringPass());
 
   // Replace OpenCL enqueued block function pointers with global variables.
   addPass(createAMDGPUOpenCLEnqueuedBlockLoweringPass());
 
   // Can increase LDS used by kernel so runs before PromoteAlloca
-  if (!DisableLowerModuleLDS)
+  if (EnableLowerModuleLDS)
     addPass(createAMDGPULowerModuleLDSPass());
 
   if (TM.getOptLevel() > CodeGenOpt::None) {
     addPass(createInferAddressSpacesPass());
     addPass(createAMDGPUPromoteAlloca());
 
     if (EnableSROA)
       addPass(createSROAPass());

llvm/test/CodeGen/AMDGPU/GlobalISel/lds-global-non-entry-func.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -amdgpu-disable-lower-module-lds=true -o - %s 2> %t | FileCheck --check-prefix=GFX8 %s
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -amdgpu-enable-lower-module-lds=false -o - %s 2> %t | FileCheck --check-prefix=GFX8 %s
 ; RUN: FileCheck -check-prefix=ERR %s < %t
 
-; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-disable-lower-module-lds=true -o - %s 2> %t | FileCheck --check-prefix=GFX9 %s
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-enable-lower-module-lds=false -o - %s 2> %t | FileCheck --check-prefix=GFX9 %s
 ; RUN: FileCheck -check-prefix=ERR %s < %t
 
 @lds = internal addrspace(3) global float undef, align 4
 
 ; ERR: warning: <unknown>:0:0: in function func_use_lds_global void (): local memory global used by non-kernel function
 define void @func_use_lds_global() {
 ; GFX8-LABEL: func_use_lds_global:
 ; GFX8:       ; %bb.0:

llvm/test/CodeGen/AMDGPU/addrspacecast-initializer-unsupported.ll

-; RUN: not --crash llc -march=amdgcn -verify-machineinstrs -amdgpu-disable-lower-module-lds=true < %s 2>&1 | FileCheck -check-prefix=ERROR %s
+; RUN: not --crash llc -march=amdgcn -verify-machineinstrs -amdgpu-enable-lower-module-lds=false < %s 2>&1 | FileCheck -check-prefix=ERROR %s
 
 ; ERROR: LLVM ERROR: Unsupported expression in static initializer: addrspacecast ([256 x i32] addrspace(3)* @lds.arr to [256 x i32] addrspace(4)*)
 
 @lds.arr = unnamed_addr addrspace(3) global [256 x i32] undef, align 4
 
 @gv_flatptr_from_lds = unnamed_addr addrspace(2) global i32 addrspace(4)* getelementptr ([256 x i32], [256 x i32] addrspace(4)* addrspacecast ([256 x i32] addrspace(3)* @lds.arr to [256 x i32] addrspace(4)*), i64 0, i64 8), align 4

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

-; 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-stress-function-calls < %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-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 -amdgpu-enable-lower-module-lds=false < %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
 
 ; GCN-NOT: load_lds_simple
 
 define internal i32 @load_lds_simple() {
   %load = load i32, i32 addrspace(3)* @lds0, align 4
   ret i32 %load

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

-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-always-inline %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 -amdgpu-stress-function-calls -amdgpu-always-inline %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-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 -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 -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 -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"
 
 @lds0 = addrspace(3) global i32 undef, align 4
 @lds1 = addrspace(3) global [512 x i32] undef, align 4
 @nested.lds.address = addrspace(1) global i32 addrspace(3)* @lds0, align 4
 @gds0 = addrspace(2) global i32 undef, align 4
 

llvm/test/CodeGen/AMDGPU/lds-global-non-entry-func.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -o - -amdgpu-disable-lower-module-lds=true %s 2> %t | FileCheck -check-prefixes=GCN,GFX8 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -o - -amdgpu-enable-lower-module-lds=false %s 2> %t | FileCheck -check-prefixes=GCN,GFX8 %s
 ; RUN: FileCheck -check-prefix=ERR %s < %t
 
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - -amdgpu-disable-lower-module-lds=true %s 2> %t | FileCheck -check-prefixes=GCN,GFX9 %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -o - -amdgpu-enable-lower-module-lds=false %s 2> %t | FileCheck -check-prefixes=GCN,GFX9 %s
 ; RUN: FileCheck -check-prefix=ERR %s < %t
 
 @lds = internal addrspace(3) global float undef, align 4
 
 ; ERR: warning: <unknown>:0:0: in function func_use_lds_global void (): local memory global used by non-kernel function
 define void @func_use_lds_global() {
 ; GFX8-LABEL: func_use_lds_global:
 ; GFX8:       ; %bb.0:

llvm/test/CodeGen/AMDGPU/promote-alloca-to-lds-constantexpr-use.ll

 ; RUN: opt -S -disable-promote-alloca-to-vector -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-promote-alloca < %s | FileCheck -check-prefix=IR %s
-; RUN: llc -disable-promote-alloca-to-vector -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-disable-lower-module-lds=true < %s | FileCheck -check-prefix=ASM %s
+; RUN: llc -disable-promote-alloca-to-vector -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-enable-lower-module-lds=false < %s | FileCheck -check-prefix=ASM %s
 
 target datalayout = "A5"
 
 @all_lds = internal unnamed_addr addrspace(3) global [16384 x i32] undef, align 4
 @some_lds = internal unnamed_addr addrspace(3) global [32 x i32] undef, align 4
 
 @initializer_user_some = addrspace(1) global i32 ptrtoint ([32 x i32] addrspace(3)* @some_lds to i32), align 4
 @initializer_user_all = addrspace(1) global i32 ptrtoint ([16384 x i32] addrspace(3)* @all_lds to i32), align 4