16a0629e7c
This patch improves `computeKnownFPClass` by using context-sensitive
information from `DomConditionCache`.
The motivation of this patch is to optimize the following case found in
[fmt/format.h](e17bc67547/include/fmt/format.h (L3555-L3566)):
```
define float @test(float %x, i1 %cond) {
%i32 = bitcast float %x to i32
%cmp = icmp slt i32 %i32, 0
br i1 %cmp, label %if.then1, label %if.else
if.then1:
%fneg = fneg float %x
br label %if.end
if.else:
br i1 %cond, label %if.then2, label %if.end
if.then2:
br label %if.end
if.end:
%value = phi float [ %fneg, %if.then1 ], [ %x, %if.then2 ], [ %x, %if.else ]
%ret = call float @llvm.fabs.f32(float %value)
ret float %ret
}
```
We can prove the sign bit of %value is always zero. Then the fabs can be
eliminated.
This pattern also exists in cpython/duckdb/oiio/openexr.
Compile-time impact:
https://llvm-compile-time-tracker.com/compare.php?from=f82e0809ba12170e2f648f8a1ac01e78ef06c958&to=041218bf5491996edd828cc15b3aec5a59ddc636&stat=instructions:u
|stage1-O3|stage1-ReleaseThinLTO|stage1-ReleaseLTO-g|stage1-O0-g|stage2-O3|stage2-O0-g|stage2-clang|
|--|--|--|--|--|--|--|
|-0.00%|+0.01%|+0.00%|-0.03%|+0.00%|+0.00%|+0.02%|
94 lines
3.5 KiB
C++
94 lines
3.5 KiB
C++
//===- DomConditionCache.cpp ----------------------------------------------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "llvm/Analysis/DomConditionCache.h"
|
|
#include "llvm/IR/PatternMatch.h"
|
|
|
|
using namespace llvm;
|
|
using namespace llvm::PatternMatch;
|
|
|
|
// TODO: This code is very similar to findAffectedValues() in
|
|
// AssumptionCache, but currently specialized to just the patterns that
|
|
// computeKnownBits() supports, and without the notion of result elem indices
|
|
// that are AC specific. Deduplicate this code once we have a clearer picture
|
|
// of how much they can be shared.
|
|
static void findAffectedValues(Value *Cond,
|
|
SmallVectorImpl<Value *> &Affected) {
|
|
auto AddAffected = [&Affected](Value *V) {
|
|
if (isa<Argument>(V) || isa<GlobalValue>(V)) {
|
|
Affected.push_back(V);
|
|
} else if (auto *I = dyn_cast<Instruction>(V)) {
|
|
Affected.push_back(I);
|
|
|
|
// Peek through unary operators to find the source of the condition.
|
|
Value *Op;
|
|
if (match(I, m_PtrToInt(m_Value(Op)))) {
|
|
if (isa<Instruction>(Op) || isa<Argument>(Op))
|
|
Affected.push_back(Op);
|
|
}
|
|
}
|
|
};
|
|
|
|
bool TopLevelIsAnd = match(Cond, m_LogicalAnd());
|
|
SmallVector<Value *, 8> Worklist;
|
|
SmallPtrSet<Value *, 8> Visited;
|
|
Worklist.push_back(Cond);
|
|
while (!Worklist.empty()) {
|
|
Value *V = Worklist.pop_back_val();
|
|
if (!Visited.insert(V).second)
|
|
continue;
|
|
|
|
CmpInst::Predicate Pred;
|
|
Value *A, *B;
|
|
// Only recurse into and/or if it matches the top-level and/or type.
|
|
if (TopLevelIsAnd ? match(V, m_LogicalAnd(m_Value(A), m_Value(B)))
|
|
: match(V, m_LogicalOr(m_Value(A), m_Value(B)))) {
|
|
Worklist.push_back(A);
|
|
Worklist.push_back(B);
|
|
} else if (match(V, m_ICmp(Pred, m_Value(A), m_Constant()))) {
|
|
AddAffected(A);
|
|
|
|
if (ICmpInst::isEquality(Pred)) {
|
|
Value *X;
|
|
// (X & C) or (X | C) or (X ^ C).
|
|
// (X << C) or (X >>_s C) or (X >>_u C).
|
|
if (match(A, m_BitwiseLogic(m_Value(X), m_ConstantInt())) ||
|
|
match(A, m_Shift(m_Value(X), m_ConstantInt())))
|
|
AddAffected(X);
|
|
} else {
|
|
Value *X;
|
|
// Handle (A + C1) u< C2, which is the canonical form of
|
|
// A > C3 && A < C4.
|
|
if (match(A, m_Add(m_Value(X), m_ConstantInt())))
|
|
AddAffected(X);
|
|
// Handle icmp slt/sgt (bitcast X to int), 0/-1, which is supported by
|
|
// computeKnownFPClass().
|
|
if ((Pred == ICmpInst::ICMP_SLT || Pred == ICmpInst::ICMP_SGT) &&
|
|
match(A, m_ElementWiseBitCast(m_Value(X))))
|
|
Affected.push_back(X);
|
|
}
|
|
} else if (match(Cond, m_CombineOr(m_FCmp(Pred, m_Value(A), m_Constant()),
|
|
m_Intrinsic<Intrinsic::is_fpclass>(
|
|
m_Value(A), m_Constant())))) {
|
|
// Handle patterns that computeKnownFPClass() support.
|
|
AddAffected(A);
|
|
}
|
|
}
|
|
}
|
|
|
|
void DomConditionCache::registerBranch(BranchInst *BI) {
|
|
assert(BI->isConditional() && "Must be conditional branch");
|
|
SmallVector<Value *, 16> Affected;
|
|
findAffectedValues(BI->getCondition(), Affected);
|
|
for (Value *V : Affected) {
|
|
auto &AV = AffectedValues[V];
|
|
if (!is_contained(AV, BI))
|
|
AV.push_back(BI);
|
|
}
|
|
}
|