AMDGPU: Enable function calls by default

[arsenm]

Summary

The inline-calls test is only sort of testing what it's intended.
Ideally we would stop running any form of inliner in the backend
passes, but that's antoher step.

Fixes some crashes on illegal call situations which are unfortunately
still valid IR.

[arsenm]

This actually breaks the option completely

[arsenm]

Split bug fix to separate patch

[msearles]

LGTM; 1 minor nit (typo in comment); no need to re-review

lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

430

Nit: typo in comment 'ssupported'

[arsenm]

r355051

lib/Target/AMDGPU/AMDGPUTargetMachine.cpp

 
 // Option to run late CFG structurizer
 static cl::opt<bool, true> LateCFGStructurize(
   "amdgpu-late-structurize",
   cl::desc("Enable late CFG structurization"),
   cl::location(AMDGPUTargetMachine::EnableLateStructurizeCFG),
   cl::Hidden);
 
-static cl::opt<bool, true> EnableAMDGPUFunctionCalls(
+static cl::opt<bool, true> EnableAMDGPUFunctionCallsOpt(
   "amdgpu-function-calls",
   cl::desc("Enable AMDGPU function call support"),
   cl::location(AMDGPUTargetMachine::EnableFunctionCalls),
-  cl::init(false),
+  cl::init(true),
   cl::Hidden);
 
 // Enable lib calls simplifications
 static cl::opt<bool> EnableLibCallSimplify(
   "amdgpu-simplify-libcall",
   cl::desc("Enable amdgpu library simplifications"),
   cl::init(true),
   cl::Hidden);
static bool mustPreserveGV(const GlobalValue &GV) {
   return !GV.use_empty();
 }
 
 void AMDGPUTargetMachine::adjustPassManager(PassManagerBuilder &Builder) {
   Builder.DivergentTarget = true;
 
   bool EnableOpt = getOptLevel() > CodeGenOpt::None;
   bool Internalize = InternalizeSymbols;
-  bool EarlyInline = EarlyInlineAll && EnableOpt && !EnableAMDGPUFunctionCalls;
+  bool EarlyInline = EarlyInlineAll && EnableOpt && !EnableFunctionCalls;
   bool AMDGPUAA = EnableAMDGPUAliasAnalysis && EnableOpt;
   bool LibCallSimplify = EnableLibCallSimplify && EnableOpt;
 
-  if (EnableAMDGPUFunctionCalls) {
+  if (EnableFunctionCalls) {
     delete Builder.Inliner;
     Builder.Inliner = createAMDGPUFunctionInliningPass();
   }
 
   Builder.addExtension(
     PassManagerBuilder::EP_ModuleOptimizerEarly,
     [Internalize, EarlyInline, AMDGPUAA](const PassManagerBuilder &,
                                          legacy::PassManagerBase &PM) {

 R600TargetMachine::R600TargetMachine(const Target &T, const Triple &TT,
                                      StringRef CPU, StringRef FS,
                                      TargetOptions Options,
                                      Optional<Reloc::Model> RM,
                                      Optional<CodeModel::Model> CM,
                                      CodeGenOpt::Level OL, bool JIT)
     : AMDGPUTargetMachine(T, TT, CPU, FS, Options, RM, CM, OL) {
   setRequiresStructuredCFG(true);
+
+  // Override the default since calls aren't ssupported for r600.
+  if (EnableFunctionCalls &&
+      EnableAMDGPUFunctionCallsOpt.getNumOccurrences() == 0)
+    EnableFunctionCalls = false;
 }
 
 const R600Subtarget *R600TargetMachine::getSubtargetImpl(
   const Function &F) const {
   StringRef GPU = getGPUName(F);
   StringRef FS = getFeatureString(F);
 
   SmallString<128> SubtargetKey(GPU);

test/CodeGen/AMDGPU/amdgpu-inline.ll

-; RUN: opt -mtriple=amdgcn--amdhsa -data-layout=A5 -O3 -S -amdgpu-function-calls -inline-threshold=1 < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-INL1 %s
-; RUN: opt -mtriple=amdgcn--amdhsa -data-layout=A5 -O3 -S -amdgpu-function-calls < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-INLDEF %s
+; RUN: opt -mtriple=amdgcn--amdhsa -data-layout=A5 -O3 -S -inline-threshold=1 < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-INL1 %s
+; RUN: opt -mtriple=amdgcn--amdhsa -data-layout=A5 -O3 -S < %s | FileCheck -check-prefix=GCN -check-prefix=GCN-INLDEF %s
 
 define coldcc float @foo(float %x, float %y) {
 entry:
   %cmp = fcmp ogt float %x, 0.000000e+00
   %div = fdiv float %y, %x
   %mul = fmul float %x, %y
   %cond = select i1 %cmp, float %div, float %mul
   ret float %cond

test/CodeGen/AMDGPU/call-graph-register-usage.ll

 ; GCN: ; NumVgprs: 33
 define void @indirect_use_10_vgpr() #0 {
   call void @use_10_vgpr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}indirect_2_level_use_10_vgpr:
 ; GCN: is_dynamic_callstack = 0
-; GCN: ; NumVgprs: 10
+; GCN: ; NumVgprs: 33
 define amdgpu_kernel void @indirect_2_level_use_10_vgpr() #0 {
   call void @indirect_use_10_vgpr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}use_40_vgpr:
 ; GCN: ; NumVgprs: 40
 define void @use_40_vgpr() #1 {

 ; GCN: is_dynamic_callstack = 1
 ; GCN: workitem_private_segment_byte_size = 2064
 define amdgpu_kernel void @usage_direct_recursion(i32 %n) #0 {
   call void @direct_recursion_use_stack(i32 %n)
   ret void
 }
 
 
-attributes #0 = { nounwind norecurse }
+attributes #0 = { nounwind noinline norecurse }
 attributes #1 = { nounwind noinline norecurse }
 attributes #2 = { nounwind noinline }

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

-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-function-calls -amdgpu-always-inline %s | FileCheck -check-prefixes=CALLS-ENABLED,ALL %s
-; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-function-calls -amdgpu-stress-function-calls -amdgpu-always-inline %s | FileCheck -check-prefixes=STRESS-CALLS,ALL %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-always-inline %s | FileCheck -check-prefixes=CALLS-ENABLED,ALL %s
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -amdgpu-stress-function-calls -amdgpu-always-inline %s | FileCheck -check-prefixes=STRESS-CALLS,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
 

test/CodeGen/AMDGPU/inline-calls.ll

 ; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck  %s
 ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck  %s
 ; RUN: llc -march=r600 -mcpu=redwood -verify-machineinstrs < %s | FileCheck %s
 
-; CHECK-NOT: {{^}}func:
+; ALL-NOT: {{^}}func:
 define internal i32 @func(i32 %a) {
 entry:
   %tmp0 = add i32 %a, 1
   ret i32 %tmp0
 }
 
-; CHECK: {{^}}kernel:
-; CHECK-NOT: call
+; ALL: {{^}}kernel:
+; GCN-NOT: s_swappc_b64
 define amdgpu_kernel void @kernel(i32 addrspace(1)* %out) {
 entry:
   %tmp0 = call i32 @func(i32 1)
   store i32 %tmp0, i32 addrspace(1)* %out
   ret void
 }
 
 ; CHECK-NOT: func_alias
+; ALL-NOT: func_alias
 @func_alias = alias i32 (i32), i32 (i32)* @func
 
-; CHECK: {{^}}kernel3:
-; CHECK-NOT: call
+; ALL: {{^}}kernel3:
+; GCN-NOT: s_swappc_b64
 define amdgpu_kernel void @kernel3(i32 addrspace(1)* %out) {
 entry:
   %tmp0 = call i32 @func_alias(i32 1)
   store i32 %tmp0, i32 addrspace(1)* %out
   ret void
 }