mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-17 18:31:04 +00:00
9cd9e4bb2c
Summary: This patch adds a threshold that controls the number of bonus instructions allowed for folding branches with common destination. The original code allows at most one bonus instruction. With this patch, users can customize the threshold to allow multiple bonus instructions. The default threshold is still 1, so that the code behaves the same as before when users do not specify this threshold. The motivation of this change is that tuning this threshold significantly (up to 25%) improves the performance of some CUDA programs in our internal code base. In general, branch instructions are very expensive for GPU programs. Therefore, it is sometimes worth trading more arithmetic computation for a more straightened control flow. Here's a reduced example: __global__ void foo(int a, int b, int c, int d, int e, int n, const int *input, int *output) { int sum = 0; for (int i = 0; i < n; ++i) sum += (((i ^ a) > b) && (((i | c ) ^ d) > e)) ? 0 : input[i]; *output = sum; } The select statement in the loop body translates to two branch instructions "if ((i ^ a) > b)" and "if (((i | c) ^ d) > e)" which share a common destination. With the default threshold, SimplifyCFG is unable to fold them, because computing the condition of the second branch "(i | c) ^ d > e" requires two bonus instructions. With the threshold increased, SimplifyCFG can fold the two branches so that the loop body contains only one branch, making the code conceptually look like: sum += (((i ^ a) > b) & (((i | c ) ^ d) > e)) ? 0 : input[i]; Increasing the threshold significantly improves the performance of this particular example. In the configuration where both conditions are guaranteed to be true, increasing the threshold from 1 to 2 improves the performance by 18.24%. Even in the configuration where the first condition is false and the second condition is true, which favors shortcuts, increasing the threshold from 1 to 2 still improves the performance by 4.35%. We are still looking for a good threshold and maybe a better cost model than just counting the number of bonus instructions. However, according to the above numbers, we think it is at least worth adding a threshold to enable more experiments and tuning. Let me know what you think. Thanks! Test Plan: Added one test case to check the threshold is in effect Reviewers: nadav, eliben, meheff, resistor, hfinkel Reviewed By: hfinkel Subscribers: hfinkel, llvm-commits Differential Revision: http://reviews.llvm.org/D5529 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218711 91177308-0d34-0410-b5e6-96231b3b80d8
409 lines
14 KiB
C++
409 lines
14 KiB
C++
//===-- Scalar.h - Scalar Transformations -----------------------*- C++ -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This header file defines prototypes for accessor functions that expose passes
|
|
// in the Scalar transformations library.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_TRANSFORMS_SCALAR_H
|
|
#define LLVM_TRANSFORMS_SCALAR_H
|
|
|
|
#include "llvm/ADT/StringRef.h"
|
|
|
|
namespace llvm {
|
|
|
|
class BasicBlockPass;
|
|
class FunctionPass;
|
|
class Pass;
|
|
class GetElementPtrInst;
|
|
class PassInfo;
|
|
class TerminatorInst;
|
|
class TargetLowering;
|
|
class TargetMachine;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// ConstantPropagation - A worklist driven constant propagation pass
|
|
//
|
|
FunctionPass *createConstantPropagationPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// AlignmentFromAssumptions - Use assume intrinsics to set load/store
|
|
// alignments.
|
|
//
|
|
FunctionPass *createAlignmentFromAssumptionsPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// SCCP - Sparse conditional constant propagation.
|
|
//
|
|
FunctionPass *createSCCPPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// DeadInstElimination - This pass quickly removes trivially dead instructions
|
|
// without modifying the CFG of the function. It is a BasicBlockPass, so it
|
|
// runs efficiently when queued next to other BasicBlockPass's.
|
|
//
|
|
Pass *createDeadInstEliminationPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// DeadCodeElimination - This pass is more powerful than DeadInstElimination,
|
|
// because it is worklist driven that can potentially revisit instructions when
|
|
// their other instructions become dead, to eliminate chains of dead
|
|
// computations.
|
|
//
|
|
FunctionPass *createDeadCodeEliminationPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// DeadStoreElimination - This pass deletes stores that are post-dominated by
|
|
// must-aliased stores and are not loaded used between the stores.
|
|
//
|
|
FunctionPass *createDeadStoreEliminationPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// AggressiveDCE - This pass uses the SSA based Aggressive DCE algorithm. This
|
|
// algorithm assumes instructions are dead until proven otherwise, which makes
|
|
// it more successful are removing non-obviously dead instructions.
|
|
//
|
|
FunctionPass *createAggressiveDCEPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// SROA - Replace aggregates or pieces of aggregates with scalar SSA values.
|
|
//
|
|
FunctionPass *createSROAPass(bool RequiresDomTree = true);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// ScalarReplAggregates - Break up alloca's of aggregates into multiple allocas
|
|
// if possible.
|
|
//
|
|
FunctionPass *createScalarReplAggregatesPass(signed Threshold = -1,
|
|
bool UseDomTree = true,
|
|
signed StructMemberThreshold = -1,
|
|
signed ArrayElementThreshold = -1,
|
|
signed ScalarLoadThreshold = -1);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// InductionVariableSimplify - Transform induction variables in a program to all
|
|
// use a single canonical induction variable per loop.
|
|
//
|
|
Pass *createIndVarSimplifyPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// InstructionCombining - Combine instructions to form fewer, simple
|
|
// instructions. This pass does not modify the CFG, and has a tendency to make
|
|
// instructions dead, so a subsequent DCE pass is useful.
|
|
//
|
|
// This pass combines things like:
|
|
// %Y = add int 1, %X
|
|
// %Z = add int 1, %Y
|
|
// into:
|
|
// %Z = add int 2, %X
|
|
//
|
|
FunctionPass *createInstructionCombiningPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LICM - This pass is a loop invariant code motion and memory promotion pass.
|
|
//
|
|
Pass *createLICMPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopStrengthReduce - This pass is strength reduces GEP instructions that use
|
|
// a loop's canonical induction variable as one of their indices.
|
|
//
|
|
Pass *createLoopStrengthReducePass();
|
|
|
|
Pass *createGlobalMergePass(const TargetMachine *TM = nullptr);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopUnswitch - This pass is a simple loop unswitching pass.
|
|
//
|
|
Pass *createLoopUnswitchPass(bool OptimizeForSize = false);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopInstSimplify - This pass simplifies instructions in a loop's body.
|
|
//
|
|
Pass *createLoopInstSimplifyPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopUnroll - This pass is a simple loop unrolling pass.
|
|
//
|
|
Pass *createLoopUnrollPass(int Threshold = -1, int Count = -1,
|
|
int AllowPartial = -1, int Runtime = -1);
|
|
// Create an unrolling pass for full unrolling only.
|
|
Pass *createSimpleLoopUnrollPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopReroll - This pass is a simple loop rerolling pass.
|
|
//
|
|
Pass *createLoopRerollPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopRotate - This pass is a simple loop rotating pass.
|
|
//
|
|
Pass *createLoopRotatePass(int MaxHeaderSize = -1);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopIdiom - This pass recognizes and replaces idioms in loops.
|
|
//
|
|
Pass *createLoopIdiomPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// PromoteMemoryToRegister - This pass is used to promote memory references to
|
|
// be register references. A simple example of the transformation performed by
|
|
// this pass is:
|
|
//
|
|
// FROM CODE TO CODE
|
|
// %X = alloca i32, i32 1 ret i32 42
|
|
// store i32 42, i32 *%X
|
|
// %Y = load i32* %X
|
|
// ret i32 %Y
|
|
//
|
|
FunctionPass *createPromoteMemoryToRegisterPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// DemoteRegisterToMemoryPass - This pass is used to demote registers to memory
|
|
// references. In basically undoes the PromoteMemoryToRegister pass to make cfg
|
|
// hacking easier.
|
|
//
|
|
FunctionPass *createDemoteRegisterToMemoryPass();
|
|
extern char &DemoteRegisterToMemoryID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Reassociate - This pass reassociates commutative expressions in an order that
|
|
// is designed to promote better constant propagation, GCSE, LICM, PRE...
|
|
//
|
|
// For example: 4 + (x + 5) -> x + (4 + 5)
|
|
//
|
|
FunctionPass *createReassociatePass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// JumpThreading - Thread control through mult-pred/multi-succ blocks where some
|
|
// preds always go to some succ. Thresholds other than minus one override the
|
|
// internal BB duplication default threshold.
|
|
//
|
|
FunctionPass *createJumpThreadingPass(int Threshold = -1);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// CFGSimplification - Merge basic blocks, eliminate unreachable blocks,
|
|
// simplify terminator instructions, etc...
|
|
//
|
|
FunctionPass *createCFGSimplificationPass(int Threshold = -1);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// FlattenCFG - flatten CFG, reduce number of conditional branches by using
|
|
// parallel-and and parallel-or mode, etc...
|
|
//
|
|
FunctionPass *createFlattenCFGPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// CFG Structurization - Remove irreducible control flow
|
|
//
|
|
Pass *createStructurizeCFGPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// BreakCriticalEdges - Break all of the critical edges in the CFG by inserting
|
|
// a dummy basic block. This pass may be "required" by passes that cannot deal
|
|
// with critical edges. For this usage, a pass must call:
|
|
//
|
|
// AU.addRequiredID(BreakCriticalEdgesID);
|
|
//
|
|
// This pass obviously invalidates the CFG, but can update forward dominator
|
|
// (set, immediate dominators, tree, and frontier) information.
|
|
//
|
|
FunctionPass *createBreakCriticalEdgesPass();
|
|
extern char &BreakCriticalEdgesID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopSimplify - Insert Pre-header blocks into the CFG for every function in
|
|
// the module. This pass updates dominator information, loop information, and
|
|
// does not add critical edges to the CFG.
|
|
//
|
|
// AU.addRequiredID(LoopSimplifyID);
|
|
//
|
|
Pass *createLoopSimplifyPass();
|
|
extern char &LoopSimplifyID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// TailCallElimination - This pass eliminates call instructions to the current
|
|
// function which occur immediately before return instructions.
|
|
//
|
|
FunctionPass *createTailCallEliminationPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LowerSwitch - This pass converts SwitchInst instructions into a sequence of
|
|
// chained binary branch instructions.
|
|
//
|
|
FunctionPass *createLowerSwitchPass();
|
|
extern char &LowerSwitchID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LowerInvoke - This pass removes invoke instructions, converting them to call
|
|
// instructions.
|
|
//
|
|
FunctionPass *createLowerInvokePass();
|
|
extern char &LowerInvokePassID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LCSSA - This pass inserts phi nodes at loop boundaries to simplify other loop
|
|
// optimizations.
|
|
//
|
|
Pass *createLCSSAPass();
|
|
extern char &LCSSAID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// EarlyCSE - This pass performs a simple and fast CSE pass over the dominator
|
|
// tree.
|
|
//
|
|
FunctionPass *createEarlyCSEPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// MergedLoadStoreMotion - This pass merges loads and stores in diamonds. Loads
|
|
// are hoisted into the header, while stores sink into the footer.
|
|
//
|
|
FunctionPass *createMergedLoadStoreMotionPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// GVN - This pass performs global value numbering and redundant load
|
|
// elimination cotemporaneously.
|
|
//
|
|
FunctionPass *createGVNPass(bool NoLoads = false);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// MemCpyOpt - This pass performs optimizations related to eliminating memcpy
|
|
// calls and/or combining multiple stores into memset's.
|
|
//
|
|
FunctionPass *createMemCpyOptPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoopDeletion - This pass performs DCE of non-infinite loops that it
|
|
// can prove are dead.
|
|
//
|
|
Pass *createLoopDeletionPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// ConstantHoisting - This pass prepares a function for expensive constants.
|
|
//
|
|
FunctionPass *createConstantHoistingPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// InstructionNamer - Give any unnamed non-void instructions "tmp" names.
|
|
//
|
|
FunctionPass *createInstructionNamerPass();
|
|
extern char &InstructionNamerID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Sink - Code Sinking
|
|
//
|
|
FunctionPass *createSinkingPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LowerAtomic - Lower atomic intrinsics to non-atomic form
|
|
//
|
|
Pass *createLowerAtomicPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// ValuePropagation - Propagate CFG-derived value information
|
|
//
|
|
Pass *createCorrelatedValuePropagationPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// InstructionSimplifier - Remove redundant instructions.
|
|
//
|
|
FunctionPass *createInstructionSimplifierPass();
|
|
extern char &InstructionSimplifierID;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LowerExpectIntrinsics - Removes llvm.expect intrinsics and creates
|
|
// "block_weights" metadata.
|
|
FunctionPass *createLowerExpectIntrinsicPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// PartiallyInlineLibCalls - Tries to inline the fast path of library
|
|
// calls such as sqrt.
|
|
//
|
|
FunctionPass *createPartiallyInlineLibCallsPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// SampleProfilePass - Loads sample profile data from disk and generates
|
|
// IR metadata to reflect the profile.
|
|
FunctionPass *createSampleProfileLoaderPass();
|
|
FunctionPass *createSampleProfileLoaderPass(StringRef Name);
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// ScalarizerPass - Converts vector operations into scalar operations
|
|
//
|
|
FunctionPass *createScalarizerPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// AddDiscriminators - Add DWARF path discriminators to the IR.
|
|
FunctionPass *createAddDiscriminatorsPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// SeparateConstOffsetFromGEP - Split GEPs for better CSE
|
|
//
|
|
FunctionPass *createSeparateConstOffsetFromGEPPass();
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// LoadCombine - Combine loads into bigger loads.
|
|
//
|
|
BasicBlockPass *createLoadCombinePass();
|
|
|
|
} // End llvm namespace
|
|
|
|
#endif
|