AMDGPU: Separate R600 and GCN TableGen files
Summary:
We now have two sets of generated TableGen files, one for R600 and one
for GCN, so each sub-target now has its own tables of instructions,
registers, ISel patterns, etc. This should help reduce compile time
since each sub-target now only has to consider information that
is specific to itself. This will also help prevent the R600
sub-target from slowing down new features for GCN, like disassembler
support, GlobalISel, etc.
Reviewers: arsenm, nhaehnle, jvesely
Reviewed By: arsenm
Subscribers: MatzeB, kzhuravl, wdng, mgorny, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits
Differential Revision: https://reviews.llvm.org/D46365
llvm-svn: 335942
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
index 2f83e60..ffe3483 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
@@ -152,7 +152,7 @@
IsAMDGCN = TT.getArch() == Triple::amdgcn;
IsAMDHSA = TT.getOS() == Triple::AMDHSA;
- const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>(F);
+ const AMDGPUCommonSubtarget &ST = AMDGPUCommonSubtarget::get(*TM, F);
if (!ST.isPromoteAllocaEnabled())
return false;
@@ -174,8 +174,8 @@
std::pair<Value *, Value *>
AMDGPUPromoteAlloca::getLocalSizeYZ(IRBuilder<> &Builder) {
- const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>(
- *Builder.GetInsertBlock()->getParent());
+ const Function &F = *Builder.GetInsertBlock()->getParent();
+ const AMDGPUCommonSubtarget &ST = AMDGPUCommonSubtarget::get(*TM, F);
if (!IsAMDHSA) {
Function *LocalSizeYFn
@@ -261,8 +261,8 @@
}
Value *AMDGPUPromoteAlloca::getWorkitemID(IRBuilder<> &Builder, unsigned N) {
- const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>(
- *Builder.GetInsertBlock()->getParent());
+ const AMDGPUCommonSubtarget &ST =
+ AMDGPUCommonSubtarget::get(*TM, *Builder.GetInsertBlock()->getParent());
Intrinsic::ID IntrID = Intrinsic::ID::not_intrinsic;
switch (N) {
@@ -602,7 +602,7 @@
bool AMDGPUPromoteAlloca::hasSufficientLocalMem(const Function &F) {
FunctionType *FTy = F.getFunctionType();
- const AMDGPUSubtarget &ST = TM->getSubtarget<AMDGPUSubtarget>(F);
+ const AMDGPUCommonSubtarget &ST = AMDGPUCommonSubtarget::get(*TM, F);
// If the function has any arguments in the local address space, then it's
// possible these arguments require the entire local memory space, so
@@ -729,8 +729,7 @@
if (!SufficientLDS)
return false;
- const AMDGPUSubtarget &ST =
- TM->getSubtarget<AMDGPUSubtarget>(ContainingFunction);
+ const AMDGPUCommonSubtarget &ST = AMDGPUCommonSubtarget::get(*TM, ContainingFunction);
unsigned WorkGroupSize = ST.getFlatWorkGroupSizes(ContainingFunction).second;
const DataLayout &DL = Mod->getDataLayout();