llvm-project/llvm/lib/Analysis/CostModel.cpp

112 lines
3.8 KiB
C++
Raw Normal View History

//===- CostModel.cpp ------ Cost Model Analysis ---------------------------===//
//
// 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 file defines the cost model analysis. It provides a very basic cost
// estimation for LLVM-IR. This analysis uses the services of the codegen
// to approximate the cost of any IR instruction when lowered to machine
// instructions. The cost results are unit-less and the cost number represents
// the throughput of the machine assuming that all loads hit the cache, all
// branches are predicted, etc. The cost numbers can be added in order to
// compare two or more transformation alternatives.
//
//===----------------------------------------------------------------------===//
Costmodel: Add support for horizontal vector reductions Upcoming SLP vectorization improvements will want to be able to estimate costs of horizontal reductions. Add infrastructure to support this. We model reductions as a series of (shufflevector,add) tuples ultimately followed by an extractelement. For example, for an add-reduction of <4 x float> we could generate the following sequence: (v0, v1, v2, v3) \ \ / / \ \ / + + (v0+v2, v1+v3, undef, undef) \ / ((v0+v2) + (v1+v3), undef, undef) %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7 %r = extractelement <4 x float> %bin.rdx8, i32 0 This commit adds a cost model interface "getReductionCost(Opcode, Ty, Pairwise)" that will allow clients to ask for the cost of such a reduction (as backends might generate more efficient code than the cost of the individual instructions summed up). This interface is excercised by the CostModel analysis pass which looks for reduction patterns like the one above - starting at extractelements - and if it sees a matching sequence will call the cost model interface. We will also support a second form of pairwise reduction that is well supported on common architectures (haddps, vpadd, faddp). (v0, v1, v2, v3) \ / \ / (v0+v1, v2+v3, undef, undef) \ / ((v0+v1)+(v2+v3), undef, undef, undef) %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 %r = extractelement <4 x float> %bin.rdx.1, i32 0 llvm-svn: 190876
2013-09-18 02:06:50 +08:00
#include "llvm/ADT/STLExtras.h"
#include "llvm/Analysis/Passes.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/IR/Function.h"
#include "llvm/Pass.h"
Costmodel: Add support for horizontal vector reductions Upcoming SLP vectorization improvements will want to be able to estimate costs of horizontal reductions. Add infrastructure to support this. We model reductions as a series of (shufflevector,add) tuples ultimately followed by an extractelement. For example, for an add-reduction of <4 x float> we could generate the following sequence: (v0, v1, v2, v3) \ \ / / \ \ / + + (v0+v2, v1+v3, undef, undef) \ / ((v0+v2) + (v1+v3), undef, undef) %rdx.shuf = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 2, i32 3, i32 undef, i32 undef> %bin.rdx = fadd <4 x float> %rdx, %rdx.shuf %rdx.shuf7 = shufflevector <4 x float> %bin.rdx, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> %bin.rdx8 = fadd <4 x float> %bin.rdx, %rdx.shuf7 %r = extractelement <4 x float> %bin.rdx8, i32 0 This commit adds a cost model interface "getReductionCost(Opcode, Ty, Pairwise)" that will allow clients to ask for the cost of such a reduction (as backends might generate more efficient code than the cost of the individual instructions summed up). This interface is excercised by the CostModel analysis pass which looks for reduction patterns like the one above - starting at extractelements - and if it sees a matching sequence will call the cost model interface. We will also support a second form of pairwise reduction that is well supported on common architectures (haddps, vpadd, faddp). (v0, v1, v2, v3) \ / \ / (v0+v1, v2+v3, undef, undef) \ / ((v0+v1)+(v2+v3), undef, undef, undef) %rdx.shuf.0.0 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 0, i32 2 , i32 undef, i32 undef> %rdx.shuf.0.1 = shufflevector <4 x float> %rdx, <4 x float> undef, <4 x i32> <i32 1, i32 3, i32 undef, i32 undef> %bin.rdx.0 = fadd <4 x float> %rdx.shuf.0.0, %rdx.shuf.0.1 %rdx.shuf.1.0 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> %rdx.shuf.1.1 = shufflevector <4 x float> %bin.rdx.0, <4 x float> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> %bin.rdx.1 = fadd <4 x float> %rdx.shuf.1.0, %rdx.shuf.1.1 %r = extractelement <4 x float> %bin.rdx.1, i32 0 llvm-svn: 190876
2013-09-18 02:06:50 +08:00
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
static cl::opt<TargetTransformInfo::TargetCostKind> CostKind(
"cost-kind", cl::desc("Target cost kind"),
cl::init(TargetTransformInfo::TCK_RecipThroughput),
cl::values(clEnumValN(TargetTransformInfo::TCK_RecipThroughput,
"throughput", "Reciprocal throughput"),
clEnumValN(TargetTransformInfo::TCK_Latency,
"latency", "Instruction latency"),
clEnumValN(TargetTransformInfo::TCK_CodeSize,
"code-size", "Code size")));
#define CM_NAME "cost-model"
#define DEBUG_TYPE CM_NAME
namespace {
class CostModelAnalysis : public FunctionPass {
public:
static char ID; // Class identification, replacement for typeinfo
CostModelAnalysis() : FunctionPass(ID), F(nullptr), TTI(nullptr) {
initializeCostModelAnalysisPass(
*PassRegistry::getPassRegistry());
}
/// Returns the expected cost of the instruction.
/// Returns -1 if the cost is unknown.
/// Note, this method does not cache the cost calculation and it
/// can be expensive in some cases.
unsigned getInstructionCost(const Instruction *I) const {
return TTI->getInstructionCost(I, TargetTransformInfo::TCK_RecipThroughput);
}
private:
void getAnalysisUsage(AnalysisUsage &AU) const override;
bool runOnFunction(Function &F) override;
void print(raw_ostream &OS, const Module*) const override;
/// The function that we analyze.
Function *F;
/// Target information.
const TargetTransformInfo *TTI;
};
} // End of anonymous namespace
// Register this pass.
char CostModelAnalysis::ID = 0;
static const char cm_name[] = "Cost Model Analysis";
INITIALIZE_PASS_BEGIN(CostModelAnalysis, CM_NAME, cm_name, false, true)
INITIALIZE_PASS_END (CostModelAnalysis, CM_NAME, cm_name, false, true)
FunctionPass *llvm::createCostModelAnalysisPass() {
return new CostModelAnalysis();
}
void
CostModelAnalysis::getAnalysisUsage(AnalysisUsage &AU) const {
AU.setPreservesAll();
}
bool
CostModelAnalysis::runOnFunction(Function &F) {
this->F = &F;
[PM] Change the core design of the TTI analysis to use a polymorphic type erased interface and a single analysis pass rather than an extremely complex analysis group. The end result is that the TTI analysis can contain a type erased implementation that supports the polymorphic TTI interface. We can build one from a target-specific implementation or from a dummy one in the IR. I've also factored all of the code into "mix-in"-able base classes, including CRTP base classes to facilitate calling back up to the most specialized form when delegating horizontally across the surface. These aren't as clean as I would like and I'm planning to work on cleaning some of this up, but I wanted to start by putting into the right form. There are a number of reasons for this change, and this particular design. The first and foremost reason is that an analysis group is complete overkill, and the chaining delegation strategy was so opaque, confusing, and high overhead that TTI was suffering greatly for it. Several of the TTI functions had failed to be implemented in all places because of the chaining-based delegation making there be no checking of this. A few other functions were implemented with incorrect delegation. The message to me was very clear working on this -- the delegation and analysis group structure was too confusing to be useful here. The other reason of course is that this is *much* more natural fit for the new pass manager. This will lay the ground work for a type-erased per-function info object that can look up the correct subtarget and even cache it. Yet another benefit is that this will significantly simplify the interaction of the pass managers and the TargetMachine. See the future work below. The downside of this change is that it is very, very verbose. I'm going to work to improve that, but it is somewhat an implementation necessity in C++ to do type erasure. =/ I discussed this design really extensively with Eric and Hal prior to going down this path, and afterward showed them the result. No one was really thrilled with it, but there doesn't seem to be a substantially better alternative. Using a base class and virtual method dispatch would make the code much shorter, but as discussed in the update to the programmer's manual and elsewhere, a polymorphic interface feels like the more principled approach even if this is perhaps the least compelling example of it. ;] Ultimately, there is still a lot more to be done here, but this was the huge chunk that I couldn't really split things out of because this was the interface change to TTI. I've tried to minimize all the other parts of this. The follow up work should include at least: 1) Improving the TargetMachine interface by having it directly return a TTI object. Because we have a non-pass object with value semantics and an internal type erasure mechanism, we can narrow the interface of the TargetMachine to *just* do what we need: build and return a TTI object that we can then insert into the pass pipeline. 2) Make the TTI object be fully specialized for a particular function. This will include splitting off a minimal form of it which is sufficient for the inliner and the old pass manager. 3) Add a new pass manager analysis which produces TTI objects from the target machine for each function. This may actually be done as part of #2 in order to use the new analysis to implement #2. 4) Work on narrowing the API between TTI and the targets so that it is easier to understand and less verbose to type erase. 5) Work on narrowing the API between TTI and its clients so that it is easier to understand and less verbose to forward. 6) Try to improve the CRTP-based delegation. I feel like this code is just a bit messy and exacerbating the complexity of implementing the TTI in each target. Many thanks to Eric and Hal for their help here. I ended up blocked on this somewhat more abruptly than I expected, and so I appreciate getting it sorted out very quickly. Differential Revision: http://reviews.llvm.org/D7293 llvm-svn: 227669
2015-01-31 11:43:40 +08:00
auto *TTIWP = getAnalysisIfAvailable<TargetTransformInfoWrapperPass>();
TTI = TTIWP ? &TTIWP->getTTI(F) : nullptr;
return false;
}
void CostModelAnalysis::print(raw_ostream &OS, const Module*) const {
if (!F)
return;
for (BasicBlock &B : *F) {
for (Instruction &Inst : B) {
unsigned Cost = TTI->getInstructionCost(&Inst, CostKind);
if (Cost != (unsigned)-1)
OS << "Cost Model: Found an estimated cost of " << Cost;
else
OS << "Cost Model: Unknown cost";
OS << " for instruction: " << Inst << "\n";
}
}
}