1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
llvm-mirror/lib/Target/NVPTX/NVVMIntrRange.cpp
Reid Kleckner 74bbf4a42b [IR] Split out target specific intrinsic enums into separate headers
This has two main effects:
- Optimizes debug info size by saving 221.86 MB of obj file size in a
  Windows optimized+debug build of 'all'. This is 3.03% of 7,332.7MB of
  object file size.
- Incremental step towards decoupling target intrinsics.

The enums are still compact, so adding and removing a single
target-specific intrinsic will trigger a rebuild of all of LLVM.
Assigning distinct target id spaces is potential future work.

Part of PR34259

Reviewers: efriedma, echristo, MaskRay

Reviewed By: echristo, MaskRay

Differential Revision: https://reviews.llvm.org/D71320
2019-12-11 18:02:14 -08:00

154 lines
4.9 KiB
C++

//===- NVVMIntrRange.cpp - Set !range metadata for NVVM intrinsics --------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This pass adds appropriate !range metadata for calls to NVVM
// intrinsics that return a limited range of values.
//
//===----------------------------------------------------------------------===//
#include "NVPTX.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/IntrinsicsNVPTX.h"
#include "llvm/Support/CommandLine.h"
using namespace llvm;
#define DEBUG_TYPE "nvvm-intr-range"
namespace llvm { void initializeNVVMIntrRangePass(PassRegistry &); }
// Add !range metadata based on limits of given SM variant.
static cl::opt<unsigned> NVVMIntrRangeSM("nvvm-intr-range-sm", cl::init(20),
cl::Hidden, cl::desc("SM variant"));
namespace {
class NVVMIntrRange : public FunctionPass {
private:
struct {
unsigned x, y, z;
} MaxBlockSize, MaxGridSize;
public:
static char ID;
NVVMIntrRange() : NVVMIntrRange(NVVMIntrRangeSM) {}
NVVMIntrRange(unsigned int SmVersion) : FunctionPass(ID) {
MaxBlockSize.x = 1024;
MaxBlockSize.y = 1024;
MaxBlockSize.z = 64;
MaxGridSize.x = SmVersion >= 30 ? 0x7fffffff : 0xffff;
MaxGridSize.y = 0xffff;
MaxGridSize.z = 0xffff;
initializeNVVMIntrRangePass(*PassRegistry::getPassRegistry());
}
bool runOnFunction(Function &) override;
};
}
FunctionPass *llvm::createNVVMIntrRangePass(unsigned int SmVersion) {
return new NVVMIntrRange(SmVersion);
}
char NVVMIntrRange::ID = 0;
INITIALIZE_PASS(NVVMIntrRange, "nvvm-intr-range",
"Add !range metadata to NVVM intrinsics.", false, false)
// Adds the passed-in [Low,High) range information as metadata to the
// passed-in call instruction.
static bool addRangeMetadata(uint64_t Low, uint64_t High, CallInst *C) {
// This call already has range metadata, nothing to do.
if (C->getMetadata(LLVMContext::MD_range))
return false;
LLVMContext &Context = C->getParent()->getContext();
IntegerType *Int32Ty = Type::getInt32Ty(Context);
Metadata *LowAndHigh[] = {
ConstantAsMetadata::get(ConstantInt::get(Int32Ty, Low)),
ConstantAsMetadata::get(ConstantInt::get(Int32Ty, High))};
C->setMetadata(LLVMContext::MD_range, MDNode::get(Context, LowAndHigh));
return true;
}
bool NVVMIntrRange::runOnFunction(Function &F) {
// Go through the calls in this function.
bool Changed = false;
for (Instruction &I : instructions(F)) {
CallInst *Call = dyn_cast<CallInst>(&I);
if (!Call)
continue;
if (Function *Callee = Call->getCalledFunction()) {
switch (Callee->getIntrinsicID()) {
// Index within block
case Intrinsic::nvvm_read_ptx_sreg_tid_x:
Changed |= addRangeMetadata(0, MaxBlockSize.x, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_tid_y:
Changed |= addRangeMetadata(0, MaxBlockSize.y, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_tid_z:
Changed |= addRangeMetadata(0, MaxBlockSize.z, Call);
break;
// Block size
case Intrinsic::nvvm_read_ptx_sreg_ntid_x:
Changed |= addRangeMetadata(1, MaxBlockSize.x+1, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_ntid_y:
Changed |= addRangeMetadata(1, MaxBlockSize.y+1, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_ntid_z:
Changed |= addRangeMetadata(1, MaxBlockSize.z+1, Call);
break;
// Index within grid
case Intrinsic::nvvm_read_ptx_sreg_ctaid_x:
Changed |= addRangeMetadata(0, MaxGridSize.x, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_ctaid_y:
Changed |= addRangeMetadata(0, MaxGridSize.y, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_ctaid_z:
Changed |= addRangeMetadata(0, MaxGridSize.z, Call);
break;
// Grid size
case Intrinsic::nvvm_read_ptx_sreg_nctaid_x:
Changed |= addRangeMetadata(1, MaxGridSize.x+1, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_nctaid_y:
Changed |= addRangeMetadata(1, MaxGridSize.y+1, Call);
break;
case Intrinsic::nvvm_read_ptx_sreg_nctaid_z:
Changed |= addRangeMetadata(1, MaxGridSize.z+1, Call);
break;
// warp size is constant 32.
case Intrinsic::nvvm_read_ptx_sreg_warpsize:
Changed |= addRangeMetadata(32, 32+1, Call);
break;
// Lane ID is [0..warpsize)
case Intrinsic::nvvm_read_ptx_sreg_laneid:
Changed |= addRangeMetadata(0, 32, Call);
break;
default:
break;
}
}
}
return Changed;
}