maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/bolt/lib/Passes/FrameOptimizer.cpp

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

358 lines
13 KiB
C++
Raw Normal View History

[BOLT][NFC] Fix file-description comments Summary: Fix comments at the start of source files. (cherry picked from FBD33274597)
2021-12-22 02:21:41 +08:00
//===- bolt/Passes/FrameOptimizer.cpp -------------------------------------===//
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
//
[BOLT] Update license headers Summary: Update license and fix headers for some files. (cherry picked from FBD28112041)
2021-03-16 09:04:18 +08:00
// 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
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
//
//===----------------------------------------------------------------------===//
//
[BOLT][NFC] Fix file-description comments Summary: Fix comments at the start of source files. (cherry picked from FBD33274597)
2021-12-22 02:21:41 +08:00
// This file implements the FrameOptimizerPass class.
//
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
//===----------------------------------------------------------------------===//
Rebase: [NFC] Refactor sources to be buildable in shared mode Summary: Moves source files into separate components, and make explicit component dependency on each other, so LLVM build system knows how to build BOLT in BUILD_SHARED_LIBS=ON. Please use the -c merge.renamelimit=230 git option when rebasing your work on top of this change. To achieve this, we create a new library to hold core IR files (most classes beginning with Binary in their names), a new library to hold Utils, some command line options shared across both RewriteInstance and core IR files, a new library called Rewrite to hold most classes concerned with running top-level functions coordinating the binary rewriting process, and a new library called Profile to hold classes dealing with profile reading and writing. To remove the dependency from BinaryContext into X86-specific classes, we do some refactoring on the BinaryContext constructor to receive a reference to the specific backend directly from RewriteInstance. Then, the dependency on X86 or AArch64-specific classes is transfered to the Rewrite library. We can't have the Core library depend on targets because targets depend on Core (which would create a cycle). Files implementing the entry point of a tool are transferred to the tools/ folder. All header files are transferred to the include/ folder. The src/ folder was renamed to lib/. (cherry picked from FBD32746834)
2021-10-09 02:47:10 +08:00
#include "bolt/Passes/FrameOptimizer.h"
#include "bolt/Core/ParallelUtilities.h"
#include "bolt/Passes/BinaryFunctionCallGraph.h"
#include "bolt/Passes/DataflowInfoManager.h"
#include "bolt/Passes/ShrinkWrapping.h"
#include "bolt/Passes/StackAvailableExpressions.h"
#include "bolt/Passes/StackReachingUses.h"
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
#include "llvm/Support/Timer.h"
Rebase: [BOLT][NFC] Remove unneeded includes with include-what-you-use Summary: Ran iwyu multiple times, manually picked header remove lines. Reached fixed point wrt removal: iwyu doesn't automatically remove any more headers or forward declarations. (cherry picked from FBD29569221)
2021-05-01 04:54:02 +08:00
#include <deque>
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
#include <unordered_map>
#define DEBUG_TYPE "fop"
using namespace llvm;
namespace opts {
extern cl::opt<unsigned> Verbosity;
[BOLT] Only print stats when requested Summary: Make LLVM timers only output numbers when the -time-opts option is used. (cherry picked from FBD5212221)
2017-06-09 04:46:17 +08:00
extern cl::opt<bool> TimeOpts;
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
extern cl::OptionCategory BoltOptCategory;
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
using namespace bolt;
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
cl::opt<FrameOptimizationType>
FrameOptimization("frame-opt",
cl::init(FOP_NONE),
cl::desc("optimize stack frame accesses"),
cl::values(
clEnumValN(FOP_NONE, "none", "do not perform frame optimization"),
clEnumValN(FOP_HOT, "hot", "perform FOP on hot functions"),
[BOLT rebase] Rebase fixes on top of LLVM Feb2018 Summary: This commit includes all code necessary to make BOLT working again after the rebase. This includes a redesign of the EHFrame work, cherry-pick of the 3dnow disassembly work, compilation error fixes, and port of the debug_info work. The macroop fusion feature is not ported yet. The rebased version has minor changes to the "executed instructions" dynostats counter because REP prefixes are considered a part of the instruction it applies to. Also, some X86 instructions had the "mayLoad" tablegen property removed, which BOLT uses to identify and account for loads, thus reducing the total number of loads reported by dynostats. This was observed in X86::MOVDQUmr. TRAP instructions are not terminators anymore, changing our CFG. This commit adds compensation to preserve this old behavior and minimize tests changes. debug_info sections are now slightly larger. The discriminator field in the line table is slightly different due to a change upstream. New profiles generated with the other bolt are incompatible with this version because of different hash values calculated for functions, so they will be considered 100% stale. This commit changes the corresponding test to XFAIL so it can be updated. The hash function changes because it relies on raw opcode values, which change according to the opcodes described in the X86 tablegen files. When processing HHVM, bolt was observed to be using about 800MB more memory in the rebased version and being about 5% slower. (cherry picked from FBD7078072)
2018-02-07 07:00:23 +08:00
clEnumValN(FOP_ALL, "all", "perform FOP on all functions")),
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
cl::ZeroOrMore,
cl::cat(BoltOptCategory));
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
[bolt] Remove unneeded cl::ZeroOrMore for cl::opt options
2022-06-06 04:29:49 +08:00
cl::opt<bool> RemoveStores(
"frame-opt-rm-stores", cl::init(FOP_NONE),
cl::desc("apply additional analysis to remove stores (experimental)"),
cl::cat(BoltOptCategory));
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
} // namespace opts
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
namespace llvm {
namespace bolt {
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
Split FrameAnalysis and improve LivenessAnalysis Summary: Split FrameAnalysis into FrameAnalysis and RegAnalysis, since some optimizations only require register information about functions, not frame information. Refactor callgraph walking code into the CallGraphWalker class, allowing any analysis that depend on the call graph to easily traverse it via a visitor pattern. Also fix LivenessAnalysis, which was broken because it was not considering registers read into callees and incorporating this into caller. (cherry picked from FBD5177901)
2017-06-03 07:57:22 +08:00
void FrameOptimizerPass::removeUnnecessaryLoads(const RegAnalysis &RA,
const FrameAnalysis &FA,
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
BinaryFunction &BF) {
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
StackAvailableExpressions SAE(RA, FA, BF);
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
SAE.run();
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Performing unnecessary loads removal\n");
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
std::deque<std::pair<BinaryBasicBlock *, MCInst *>> ToErase;
bool Changed = false;
const auto ExprEnd = SAE.expr_end();
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
MCPlusBuilder *MIB = BF.getBinaryContext().MIB.get();
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
for (BinaryBasicBlock &BB : BF) {
[BOLT][NFC] Reformat with clang-format Summary: Selectively apply clang-format to BOLT code base. (cherry picked from FBD33119052)
2021-12-15 08:52:51 +08:00
LLVM_DEBUG(dbgs() << "\tNow at BB " << BB.getName() << "\n");
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
const MCInst *Prev = nullptr;
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
for (MCInst &Inst : BB) {
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG({
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
dbgs() << "\t\tNow at ";
Inst.dump();
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
for (auto I = Prev ? SAE.expr_begin(*Prev) : SAE.expr_begin(BB);
I != ExprEnd; ++I) {
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
dbgs() << "\t\t\tReached by: ";
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
(*I)->dump();
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
});
// if Inst is a load from stack and the current available expressions show
// this value is available in a register or immediate, replace this load
// with move from register or from immediate.
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
ErrorOr<const FrameIndexEntry &> FIEX = FA.getFIEFor(Inst);
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
if (!FIEX) {
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
Prev = &Inst;
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
continue;
}
// FIXME: Change to remove IsSimple == 0. We're being conservative here,
// but once replaceMemOperandWithReg is ready, we should feed it with all
// sorts of complex instructions.
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
if (FIEX->IsLoad == false || FIEX->IsSimple == false ||
FIEX->StackOffset >= 0) {
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
Prev = &Inst;
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
continue;
}
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
for (auto I = Prev ? SAE.expr_begin(*Prev) : SAE.expr_begin(BB);
I != ExprEnd; ++I) {
const MCInst *AvailableInst = *I;
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
ErrorOr<const FrameIndexEntry &> FIEY = FA.getFIEFor(*AvailableInst);
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
if (!FIEY)
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
continue;
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
assert(FIEY->IsStore && FIEY->IsSimple);
if (FIEX->StackOffset != FIEY->StackOffset || FIEX->Size != FIEY->Size)
continue;
// TODO: Change push/pops to stack adjustment instruction
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
if (MIB->isPop(Inst))
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
continue;
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
++NumRedundantLoads;
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
Changed = true;
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Redundant load instruction: ");
LLVM_DEBUG(Inst.dump());
LLVM_DEBUG(dbgs() << "Related store instruction: ");
LLVM_DEBUG(AvailableInst->dump());
LLVM_DEBUG(dbgs() << "@BB: " << BB.getName() << "\n");
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
// Replace load
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
if (FIEY->IsStoreFromReg) {
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
if (!MIB->replaceMemOperandWithReg(Inst, FIEY->RegOrImm)) {
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "FAILED to change operand to a reg\n");
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
break;
}
++NumLoadsChangedToReg;
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
MIB->removeAnnotation(Inst, "FrameAccessEntry");
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Changed operand to a reg\n");
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
if (MIB->isRedundantMove(Inst)) {
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
++NumLoadsDeleted;
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Created a redundant move\n");
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
// Delete it!
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
ToErase.push_front(std::make_pair(&BB, &Inst));
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
} else {
char Buf[8] = {0, 0, 0, 0, 0, 0, 0, 0};
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
support::ulittle64_t::ref(Buf + 0) = FIEY->RegOrImm;
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Changing operand to an imm... ");
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
if (!MIB->replaceMemOperandWithImm(Inst, StringRef(Buf, 8), 0)) {
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "FAILED\n");
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
} else {
++NumLoadsChangedToImm;
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
MIB->removeAnnotation(Inst, "FrameAccessEntry");
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Ok\n");
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
}
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Changed to: ");
LLVM_DEBUG(Inst.dump());
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
break;
}
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
Prev = &Inst;
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
}
[BOLT][NFC] Fix braces usage in Passes Summary: Refactor bolt/*/Passes to follow the braces rule for if/else/loop from [LLVM Coding Standards](https://llvm.org/docs/CodingStandards.html). (cherry picked from FBD33344642)
2021-12-29 08:36:17 +08:00
if (Changed)
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "FOP modified \"" << BF.getPrintName() << "\"\n");
[BOLT][NFC] Fix braces usage in Passes Summary: Refactor bolt/*/Passes to follow the braces rule for if/else/loop from [LLVM Coding Standards](https://llvm.org/docs/CodingStandards.html). (cherry picked from FBD33344642)
2021-12-29 08:36:17 +08:00
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
// TODO: Implement an interface of eraseInstruction that works out the
// complete list of elements to remove.
[BOLT][NFC] Fix braces usage in Passes Summary: Refactor bolt/*/Passes to follow the braces rule for if/else/loop from [LLVM Coding Standards](https://llvm.org/docs/CodingStandards.html). (cherry picked from FBD33344642)
2021-12-29 08:36:17 +08:00
for (std::pair<BinaryBasicBlock *, MCInst *> I : ToErase)
[BOLT] New inliner implementation Summary: Addresses correctness issues related to inlining. Inlining heuristics are not part of this diff. (cherry picked from FBD13796888)
2019-02-01 03:23:02 +08:00
I.first->eraseInstruction(I.first->findInstruction(I.second));
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
void FrameOptimizerPass::removeUnusedStores(const FrameAnalysis &FA,
BinaryFunction &BF) {
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
StackReachingUses SRU(FA, BF);
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
SRU.run();
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Performing unused stores removal\n");
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
std::vector<std::pair<BinaryBasicBlock *, MCInst *>> ToErase;
bool Changed = false;
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
for (BinaryBasicBlock &BB : BF) {
[BOLT][NFC] Reformat with clang-format Summary: Selectively apply clang-format to BOLT code base. (cherry picked from FBD33119052)
2021-12-15 08:52:51 +08:00
LLVM_DEBUG(dbgs() << "\tNow at BB " << BB.getName() << "\n");
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
const MCInst *Prev = nullptr;
for (auto I = BB.rbegin(), E = BB.rend(); I != E; ++I) {
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
MCInst &Inst = *I;
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG({
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
dbgs() << "\t\tNow at ";
Inst.dump();
for (auto I = Prev ? SRU.expr_begin(*Prev) : SRU.expr_begin(BB);
I != SRU.expr_end(); ++I) {
dbgs() << "\t\t\tReached by: ";
(*I)->dump();
}
});
Rebase: [BOLT][NFC] Expand auto types Summary: Expanded auto types across BOLT semi-automatically with the aid of clangd LSP (cherry picked from FBD33289309)
2021-04-08 15:19:26 +08:00
ErrorOr<const FrameIndexEntry &> FIEX = FA.getFIEFor(Inst);
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
if (!FIEX) {
Prev = &Inst;
continue;
}
if (FIEX->IsLoad || !FIEX->IsSimple || FIEX->StackOffset >= 0) {
Prev = &Inst;
continue;
}
if (SRU.isStoreUsed(*FIEX,
Prev ? SRU.expr_begin(*Prev) : SRU.expr_begin(BB))) {
Prev = &Inst;
continue;
}
// TODO: Change push/pops to stack adjustment instruction
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
if (BF.getBinaryContext().MIB->isPush(Inst))
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
continue;
++NumRedundantStores;
Changed = true;
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "Unused store instruction: ");
LLVM_DEBUG(Inst.dump());
LLVM_DEBUG(dbgs() << "@BB: " << BB.getName() << "\n");
LLVM_DEBUG(dbgs() << "FIE offset = " << FIEX->StackOffset
[BOLT][NFC] Reformat with clang-format Summary: Selectively apply clang-format to BOLT code base. (cherry picked from FBD33119052)
2021-12-15 08:52:51 +08:00
<< " size = " << (int)FIEX->Size << "\n");
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
// Delete it!
[BOLT][NFC] Avoid unnecessary copies with push_back Summary: Small refactoring inspired by clang-tidy modernize-use-emplace (cherry picked from FBD28307493)
2021-05-08 09:43:25 +08:00
ToErase.emplace_back(&BB, &Inst);
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
Prev = &Inst;
}
}
[BOLT][NFC] Fix braces usage in Passes Summary: Refactor bolt/*/Passes to follow the braces rule for if/else/loop from [LLVM Coding Standards](https://llvm.org/docs/CodingStandards.html). (cherry picked from FBD33344642)
2021-12-29 08:36:17 +08:00
for (std::pair<BinaryBasicBlock *, MCInst *> I : ToErase)
[BOLT] New inliner implementation Summary: Addresses correctness issues related to inlining. Inlining heuristics are not part of this diff. (cherry picked from FBD13796888)
2019-02-01 03:23:02 +08:00
I.first->eraseInstruction(I.first->findInstruction(I.second));
[BOLT][NFC] Fix braces usage in Passes Summary: Refactor bolt/*/Passes to follow the braces rule for if/else/loop from [LLVM Coding Standards](https://llvm.org/docs/CodingStandards.html). (cherry picked from FBD33344642)
2021-12-29 08:36:17 +08:00
if (Changed)
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(dbgs() << "FOP modified \"" << BF.getPrintName() << "\"\n");
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
}
[BOLT] Move BinaryFunctions into a BinaryContext and more Summary: A long due refactoring that makes interfaces cleaner and less awkward. Mainly makes the future work way easier. (cherry picked from FBD14766284)
2019-04-04 06:52:01 +08:00
void FrameOptimizerPass::runOnFunctions(BinaryContext &BC) {
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
if (opts::FrameOptimization == FOP_NONE)
return;
run SPT in parallel, and split annotation allocator Summary: This diff includes two main changes: 1) When creating an annotation, a dedicated annotation allocator can be used, instead of the default allocator. This allows some annotation to be deallocated right after the end of their usage completely. Furthermore, having the ability to use dedicated allocators allows running SPT in parallel where each task uses a different allocator. 2) SPT is parallelized. (cherry picked from FBD15913492)
2019-06-15 10:56:11 +08:00
std::unique_ptr<BinaryFunctionCallGraph> CG;
std::unique_ptr<FrameAnalysis> FA;
std::unique_ptr<RegAnalysis> RA;
{
NamedRegionTimer T1("callgraph", "create call graph", "FOP",
"FOP breakdown", opts::TimeOpts);
CG = std::make_unique<BinaryFunctionCallGraph>(buildCallGraph(BC));
}
{
NamedRegionTimer T1("frameanalysis", "frame analysis", "FOP",
"FOP breakdown", opts::TimeOpts);
FA = std::make_unique<FrameAnalysis>(BC, *CG);
}
{
[BOLT][NFC] Reformat with clang-format Summary: Selectively apply clang-format to BOLT code base. (cherry picked from FBD33119052)
2021-12-15 08:52:51 +08:00
NamedRegionTimer T1("reganalysis", "reg analysis", "FOP", "FOP breakdown",
opts::TimeOpts);
run SPT in parallel, and split annotation allocator Summary: This diff includes two main changes: 1) When creating an annotation, a dedicated annotation allocator can be used, instead of the default allocator. This allows some annotation to be deallocated right after the end of their usage completely. Furthermore, having the ability to use dedicated allocators allows running SPT in parallel where each task uses a different allocator. 2) SPT is parallelized. (cherry picked from FBD15913492)
2019-06-15 10:56:11 +08:00
RA = std::make_unique<RegAnalysis>(BC, &BC.getBinaryFunctions(), CG.get());
}
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
// Perform caller-saved register optimizations, then callee-saved register
// optimizations (shrink wrapping)
[BOLT] Move BinaryFunctions into a BinaryContext and more Summary: A long due refactoring that makes interfaces cleaner and less awkward. Mainly makes the future work way easier. (cherry picked from FBD14766284)
2019-04-04 06:52:01 +08:00
for (auto &I : BC.getBinaryFunctions()) {
run SPT in parallel, and split annotation allocator Summary: This diff includes two main changes: 1) When creating an annotation, a dedicated annotation allocator can be used, instead of the default allocator. This allows some annotation to be deallocated right after the end of their usage completely. Furthermore, having the ability to use dedicated allocators allows running SPT in parallel where each task uses a different allocator. 2) SPT is parallelized. (cherry picked from FBD15913492)
2019-06-15 10:56:11 +08:00
if (!FA->hasFrameInfo(I.second))
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
continue;
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
// Restrict pass execution if user asked to only run on hot functions
if (opts::FrameOptimization == FOP_HOT) {
if (I.second.getKnownExecutionCount() < BC.getHotThreshold())
continue;
Rebase: Merge BOLT codebase in monorepo Summary: This commit is the first step in rebasing all of BOLT history in the LLVM monorepo. It also solves trivial build issues by updating BOLT codebase to use current LLVM. There is still work left in rebasing some BOLT features and in making sure everything is working as intended. History has been rewritten to put BOLT in the /bolt folder, as opposed to /tools/llvm-bolt. (cherry picked from FBD33289252)
2020-12-02 08:29:39 +08:00
LLVM_DEBUG(
dbgs() << "Considering " << I.second.getPrintName()
<< " for frame optimizations because its execution count ( "
<< I.second.getKnownExecutionCount()
<< " ) exceeds our hotness threshold ( "
<< BC.getHotThreshold() << " )\n");
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
}
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
{
[BOLT rebase] Rebase fixes on top of LLVM Feb2018 Summary: This commit includes all code necessary to make BOLT working again after the rebase. This includes a redesign of the EHFrame work, cherry-pick of the 3dnow disassembly work, compilation error fixes, and port of the debug_info work. The macroop fusion feature is not ported yet. The rebased version has minor changes to the "executed instructions" dynostats counter because REP prefixes are considered a part of the instruction it applies to. Also, some X86 instructions had the "mayLoad" tablegen property removed, which BOLT uses to identify and account for loads, thus reducing the total number of loads reported by dynostats. This was observed in X86::MOVDQUmr. TRAP instructions are not terminators anymore, changing our CFG. This commit adds compensation to preserve this old behavior and minimize tests changes. debug_info sections are now slightly larger. The discriminator field in the line table is slightly different due to a change upstream. New profiles generated with the other bolt are incompatible with this version because of different hash values calculated for functions, so they will be considered 100% stale. This commit changes the corresponding test to XFAIL so it can be updated. The hash function changes because it relies on raw opcode values, which change according to the opcodes described in the X86 tablegen files. When processing HHVM, bolt was observed to be using about 800MB more memory in the rebased version and being about 5% slower. (cherry picked from FBD7078072)
2018-02-07 07:00:23 +08:00
NamedRegionTimer T1("removeloads", "remove loads", "FOP", "FOP breakdown",
opts::TimeOpts);
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
removeUnnecessaryLoads(*RA, *FA, I.second);
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
[BOLT] Fix shrink-wrapping bugs Summary: Make shrink-wrapping more stable. Changes: * Correctly detect landing pads at the dominance frontier, bailing on such cases because we are not prepared to split LPs that are target of a critical edge. * Disable FOP's store removal by default - this is experimental and shouldn t go to prod because removing a store that we failed to detect it's actually necessary is disastrous. This pass currently doesn't have a great impact on the number of stores reduced, so it is not a problem. Most stores reduced are due shrink wrapping anyway. * Fix stack access identification - correctly estimate memory length of weird instructions, bail if we don't know. * Make rules for shrink-wrapping more strict: cancel shrink wrapping on a number of cases when we are not 100% sure that we are dealing with a regular callee-saved register. * Add basic block folding to SW. Sometimes when splitting critical edges we create a lot of redundant BBs with the same instructions, same successor but different predecessor. Fold all identical BBs created by splitting critical edges. * Change defaults: now the threshold used to determine when to perform SW is more conservative, to be sure we are moving a spill to a colder area. This effort, along with BB folding, helps us to avoid hurting icache performance by indiscriminately increasing code size. (cherry picked from FBD5315086)
2017-06-23 07:34:01 +08:00
if (opts::RemoveStores) {
[BOLT rebase] Rebase fixes on top of LLVM Feb2018 Summary: This commit includes all code necessary to make BOLT working again after the rebase. This includes a redesign of the EHFrame work, cherry-pick of the 3dnow disassembly work, compilation error fixes, and port of the debug_info work. The macroop fusion feature is not ported yet. The rebased version has minor changes to the "executed instructions" dynostats counter because REP prefixes are considered a part of the instruction it applies to. Also, some X86 instructions had the "mayLoad" tablegen property removed, which BOLT uses to identify and account for loads, thus reducing the total number of loads reported by dynostats. This was observed in X86::MOVDQUmr. TRAP instructions are not terminators anymore, changing our CFG. This commit adds compensation to preserve this old behavior and minimize tests changes. debug_info sections are now slightly larger. The discriminator field in the line table is slightly different due to a change upstream. New profiles generated with the other bolt are incompatible with this version because of different hash values calculated for functions, so they will be considered 100% stale. This commit changes the corresponding test to XFAIL so it can be updated. The hash function changes because it relies on raw opcode values, which change according to the opcodes described in the X86 tablegen files. When processing HHVM, bolt was observed to be using about 800MB more memory in the rebased version and being about 5% slower. (cherry picked from FBD7078072)
2018-02-07 07:00:23 +08:00
NamedRegionTimer T1("removestores", "remove stores", "FOP",
"FOP breakdown", opts::TimeOpts);
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
removeUnusedStores(*FA, I.second);
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
}
// Don't even start shrink wrapping if no profiling info is available
if (I.second.getKnownExecutionCount() == 0)
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
continue;
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
}
{
NamedRegionTimer T1("shrinkwrapping", "shrink wrapping", "FOP",
"FOP breakdown", opts::TimeOpts);
performShrinkWrapping(*RA, *FA, BC);
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
outs() << "BOLT-INFO: FOP optimized " << NumRedundantLoads
<< " redundant load(s) and " << NumRedundantStores
<< " unused store(s)\n";
Cover RSP-indexed accesses in frame optimization Summary: Add a new dataflow analysis to recover the value of RSP at a given point of the program. This value is expressed as an offset from the CFA. Use this information to detect redundant load in memory accesses performed via RSP as well, not only RBP as done previously. Bail when RSP value (as an offset of the CFA) can't be reliably determined with a simple dataflow analysis. (cherry picked from FBD4372261)
2016-12-29 09:09:52 +08:00
outs() << "BOLT-INFO: FOP changed " << NumLoadsChangedToReg
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
<< " load(s) to use a register instead of a stack access, and "
<< NumLoadsChangedToImm << " to use an immediate.\n"
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
<< "BOLT-INFO: FOP deleted " << NumLoadsDeleted << " load(s) and "
<< NumRedundantStores << " store(s).\n";
run SPT in parallel, and split annotation allocator Summary: This diff includes two main changes: 1) When creating an annotation, a dedicated annotation allocator can be used, instead of the default allocator. This allows some annotation to be deallocated right after the end of their usage completely. Furthermore, having the ability to use dedicated allocators allows running SPT in parallel where each task uses a different allocator. 2) SPT is parallelized. (cherry picked from FBD15913492)
2019-06-15 10:56:11 +08:00
FA->printStats();
[BOLT] Add shrink wrapping pass Summary: Add an implementation for shrink wrapping, a frame optimization that moves callee-saved register spills from hot prologues to cold successors. (cherry picked from FBD4983706)
2017-05-02 07:52:54 +08:00
ShrinkWrapping::printStats();
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
}
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
void FrameOptimizerPass::performShrinkWrapping(const RegAnalysis &RA,
const FrameAnalysis &FA,
BinaryContext &BC) {
// Initialize necessary annotations to allow safe parallel accesses to
// annotation index in MIB
BC.MIB->getOrCreateAnnotationIndex(CalleeSavedAnalysis::getSaveTagName());
BC.MIB->getOrCreateAnnotationIndex(CalleeSavedAnalysis::getRestoreTagName());
BC.MIB->getOrCreateAnnotationIndex(StackLayoutModifier::getTodoTagName());
BC.MIB->getOrCreateAnnotationIndex(StackLayoutModifier::getSlotTagName());
BC.MIB->getOrCreateAnnotationIndex(
StackLayoutModifier::getOffsetCFIRegTagName());
BC.MIB->getOrCreateAnnotationIndex("ReachingDefs");
BC.MIB->getOrCreateAnnotationIndex("ReachingUses");
BC.MIB->getOrCreateAnnotationIndex("LivenessAnalysis");
BC.MIB->getOrCreateAnnotationIndex("StackReachingUses");
BC.MIB->getOrCreateAnnotationIndex("PostDominatorAnalysis");
BC.MIB->getOrCreateAnnotationIndex("DominatorAnalysis");
BC.MIB->getOrCreateAnnotationIndex("StackPointerTracking");
BC.MIB->getOrCreateAnnotationIndex("StackPointerTrackingForInternalCalls");
BC.MIB->getOrCreateAnnotationIndex("StackAvailableExpressions");
BC.MIB->getOrCreateAnnotationIndex("StackAllocationAnalysis");
BC.MIB->getOrCreateAnnotationIndex("ShrinkWrap-Todo");
BC.MIB->getOrCreateAnnotationIndex("PredictiveStackPointerTracking");
BC.MIB->getOrCreateAnnotationIndex("ReachingInsnsBackward");
BC.MIB->getOrCreateAnnotationIndex("ReachingInsns");
BC.MIB->getOrCreateAnnotationIndex("AccessesDeletedPos");
BC.MIB->getOrCreateAnnotationIndex("DeleteMe");
ParallelUtilities::PredicateTy SkipPredicate = [&](const BinaryFunction &BF) {
if (!FA.hasFrameInfo(BF))
return true;
if (opts::FrameOptimization == FOP_HOT &&
(BF.getKnownExecutionCount() < BC.getHotThreshold()))
return true;
if (BF.getKnownExecutionCount() == 0)
return true;
return false;
};
ParallelUtilities::WorkFuncWithAllocTy WorkFunction =
[&](BinaryFunction &BF, MCPlusBuilder::AllocatorIdTy AllocatorId) {
[BOLT][NFC] Do not pass BinaryContext alongside BinaryFunction Summary: BinaryContext is available via BinaryFunction::getBinaryContext(), hence there's no reason to pass both as arguments to a function. In a similar fashion, BinaryBasicBlock has an access to BinaryFunction via getFunction(). Eliminate unneeded arguments. (cherry picked from FBD31921680)
2021-10-26 15:06:34 +08:00
DataflowInfoManager Info(BF, &RA, &FA, AllocatorId);
ShrinkWrapping SW(FA, BF, Info, AllocatorId);
Run shrink wrapping in parallel Summary: Shrink wrapping is an expensive part of frame optimizations if performed on all functions. This diff makes it run in parallel, reducing wall time. (cherry picked from FBD16092651)
2019-07-03 01:48:43 +08:00
if (SW.perform()) {
std::lock_guard<std::mutex> Lock(FuncsChangedMutex);
FuncsChanged.insert(&BF);
}
};
ParallelUtilities::runOnEachFunctionWithUniqueAllocId(
BC, ParallelUtilities::SchedulingPolicy::SP_INST_QUADRATIC, WorkFunction,
SkipPredicate, "shrink-wrapping");
}
Add a frame optimization pass Summary: This is a first attempt to perform data flow analyses on bolt and try to rebuild the stack frame for functions. The goal of the frame optimization pass is to detect instructions that are accessing stack and, if loading values, evaluate whether this load is redundant and we can substitute the memory operation for a register load or immediate load. To find opportunities, this pass also builds a map of clobbered registers by function, so we use this in our analysis at call sites. If a call site is found out to not clobber a caller-saved register but the caller is spilling it anyway to the stack (to comply with the ABI), we should detect these cases and remove this unnecessary move. (cherry picked from FBD4337238)
2016-12-06 03:47:08 +08:00
} // namespace bolt
} // namespace llvm