2021-01-06 20:43:28 +01:00
|
|
|
; RUN: opt -O0 -mtriple=amdgcn--amdhsa -disable-output -disable-verify -debug-pass=Structure -enable-new-pm=0 %s 2>&1 | FileCheck -check-prefix=GCN-O0 %s
|
|
|
|
|
; RUN: opt -O1 -mtriple=amdgcn--amdhsa -disable-output -disable-verify -debug-pass=Structure -enable-new-pm=0 %s 2>&1 | FileCheck -check-prefix=GCN-O1 %s
|
|
|
|
|
; RUN: opt -O2 -mtriple=amdgcn--amdhsa -disable-output -disable-verify -debug-pass=Structure -enable-new-pm=0 %s 2>&1 | FileCheck -check-prefix=GCN-O2 %s
|
|
|
|
|
; RUN: opt -O3 -mtriple=amdgcn--amdhsa -disable-output -disable-verify -debug-pass=Structure -enable-new-pm=0 %s 2>&1 | FileCheck -check-prefix=GCN-O3 %s
|
2020-05-21 20:58:35 +02:00
|
|
|
|
|
|
|
|
; REQUIRES: asserts
|
|
|
|
|
|
|
|
|
|
; GCN-O0: Pass Arguments:
|
|
|
|
|
; GCN-O0-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O0-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O0-NEXT: Early propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O0-NEXT: Replace builtin math calls with that native versions.
|
|
|
|
|
|
|
|
|
|
; GCN-O0-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O0-NEXT: Target Library Information
|
|
|
|
|
; GCN-O0-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O0-NEXT: Target Pass Configuration
|
|
|
|
|
; GCN-O0-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O0-NEXT: Profile summary info
|
|
|
|
|
; GCN-O0-NEXT: ModulePass Manager
|
2020-11-16 10:49:04 +01:00
|
|
|
; GCN-O0-NEXT: Annotation2Metadata
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O0-NEXT: Force set function attributes
|
|
|
|
|
; GCN-O0-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O0-NEXT: Call Graph SCC Pass Manager
|
2021-01-06 06:11:21 +01:00
|
|
|
; GCN-O0-NEXT: Function Integration/Inlining
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O0-NEXT: A No-Op Barrier Pass
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; GCN-O1: Pass Arguments:
|
|
|
|
|
; GCN-O1-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O1-NEXT: AMDGPU Address space based Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: External Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O1-NEXT: Target Library Information
|
|
|
|
|
; GCN-O1-NEXT: Type-Based Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: Scoped NoAlias Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Early propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O1-NEXT: Replace builtin math calls with that native versions.
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Simplify well-known AMD library calls
|
2021-04-12 20:51:51 +02:00
|
|
|
; GCN-O1-NEXT: Lower 'expect' Intrinsics
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: SROA
|
|
|
|
|
; GCN-O1-NEXT: Early CSE
|
|
|
|
|
|
|
|
|
|
; GCN-O1-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O1-NEXT: Target Library Information
|
|
|
|
|
; GCN-O1-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O1-NEXT: Target Pass Configuration
|
|
|
|
|
; GCN-O1-NEXT: Type-Based Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: Scoped NoAlias Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: AMDGPU Address space based Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: External Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O1-NEXT: Profile summary info
|
|
|
|
|
; GCN-O1-NEXT: ModulePass Manager
|
2020-11-16 10:49:04 +01:00
|
|
|
; GCN-O1-NEXT: Annotation2Metadata
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Force set function attributes
|
|
|
|
|
; GCN-O1-NEXT: Infer set function attributes
|
|
|
|
|
; GCN-O1-NEXT: Unify multiple OpenCL metadata due to linking
|
|
|
|
|
; GCN-O1-NEXT: AMDGPU Printf lowering
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Late propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O1-NEXT: Interprocedural Sparse Conditional Constant Propagation
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Called Value Propagation
|
|
|
|
|
; GCN-O1-NEXT: Global Variable Optimizer
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Promote Memory to Register
|
|
|
|
|
; GCN-O1-NEXT: Dead Argument Elimination
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O1-NEXT: Globals Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: Call Graph SCC Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Remove unused exception handling info
|
2021-01-06 06:11:21 +01:00
|
|
|
; GCN-O1-NEXT: Function Integration/Inlining
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Deduce function attributes
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Infer address spaces
|
|
|
|
|
; GCN-O1-NEXT: AMDGPU Kernel Attributes
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
2020-05-21 01:24:06 +02:00
|
|
|
; GCN-O1-NEXT: AMDGPU Promote Alloca to vector
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: SROA
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Memory SSA
|
|
|
|
|
; GCN-O1-NEXT: Early CSE w/ MemorySSA
|
|
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Conditionally eliminate dead library calls
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: PGOMemOPSize
|
|
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: Reassociate expressions
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
[PassManager] Run additional LICM before LoopRotate
Loop rotation often has to perform code duplication
from header into preheader, which introduces PHI nodes.
>>! In D99204, @thopre wrote:
>
> With loop peeling, it is important that unnecessary PHIs be avoided or
> it will leads to spurious peeling. One source of such PHIs is loop
> rotation which creates PHIs for invariant loads. Those PHIs are
> particularly problematic since loop peeling is now run as part of simple
> loop unrolling before GVN is run, and are thus a source of spurious
> peeling.
>
> Note that while some of the load can be hoisted and eventually
> eliminated by instruction combine, this is not always possible due to
> alignment issue. In particular, the motivating example [1] was a load
> inside a class instance which cannot be hoisted because the `this'
> pointer has an alignment of 1.
>
> [1] http://lists.llvm.org/pipermail/llvm-dev/attachments/20210312/4ce73c47/attachment.cpp
Now, we could enhance LoopRotate to avoid duplicating code when not needed,
but instead hoist loop-invariant code, but isn't that a code duplication? (*sic*)
We have LICM, and in fact we already run it right after LoopRotation.
We could try to move it to before LoopRotation,
that is basically free from compile-time perspective:
https://llvm-compile-time-tracker.com/compare.php?from=6c93eb4477d88af046b915bc955c03693b2cbb58&to=a4bee6d07732b1184c436da489040b912f0dc271&stat=instructions
But, looking at stats, i think it isn't great that we would no longer do LICM after LoopRotation, in particular:
| statistic name | LoopRotate-LICM | LICM-LoopRotate | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9015799 | -131 | 0.00% | 0.00% |
| indvars.NumElimCmp | 3536 | 3544 | 8 | 0.23% | 0.23% |
| indvars.NumElimExt | 36725 | 36580 | -145 | -0.39% | 0.39% |
| indvars.NumElimIV | 1197 | 1187 | -10 | -0.84% | 0.84% |
| indvars.NumElimIdentity | 143 | 136 | -7 | -4.90% | 4.90% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29890 | 48 | 0.16% | 0.16% |
| indvars.NumReplaced | 2293 | 2227 | -66 | -2.88% | 2.88% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26329 | -109 | -0.41% | 0.41% |
| instcount.TotalBlocks | 1178338 | 1173840 | -4498 | -0.38% | 0.38% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9896139 | -9303 | -0.09% | 0.09% |
| lcssa.NumLCSSA | 425871 | 423961 | -1910 | -0.45% | 0.45% |
| licm.NumHoisted | 378357 | 378753 | 396 | 0.10% | 0.10% |
| licm.NumMovedCalls | 2193 | 2208 | 15 | 0.68% | 0.68% |
| licm.NumMovedLoads | 35899 | 31821 | -4078 | -11.36% | 11.36% |
| licm.NumPromoted | 11178 | 11154 | -24 | -0.21% | 0.21% |
| licm.NumSunk | 13359 | 13587 | 228 | 1.71% | 1.71% |
| loop-delete.NumDeleted | 8547 | 8402 | -145 | -1.70% | 1.70% |
| loop-instsimplify.NumSimplified | 12876 | 11890 | -986 | -7.66% | 7.66% |
| loop-peel.NumPeeled | 1008 | 925 | -83 | -8.23% | 8.23% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42003 | -12 | -0.03% | 0.03% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 242 | 2 | 0.83% | 0.83% |
| loop-simplifycfg.NumLoopExitsDeleted | 497 | 20 | -477 | -95.98% | 95.98% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 336 | -282 | -45.63% | 45.63% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11032 | 4 | 0.04% | 0.04% |
| loop-unroll.NumUnrolled | 12608 | 12529 | -79 | -0.63% | 0.63% |
| mem2reg.NumDeadAlloca | 10222 | 10221 | -1 | -0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192110 | 192106 | -4 | 0.00% | 0.00% |
| mem2reg.NumSingleStore | 637650 | 637643 | -7 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 814 | 812 | -2 | -0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282934 | -174 | -0.06% | 0.06% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106718 | 6 | 0.01% | 0.01% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
... but that actually regresses LICM (-12% `licm.NumMovedLoads`),
loop-simplifycfg (`NumLoopExitsDeleted`, `NumTerminatorsFolded`),
simple-loop-unswitch (`NumTrivial`).
What if we instead have LICM both before and after LoopRotate?
| statistic name | LoopRotate-LICM | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9014474 | -1456 | -0.02% | 0.02% |
| indvars.NumElimCmp | 3536 | 3546 | 10 | 0.28% | 0.28% |
| indvars.NumElimExt | 36725 | 36681 | -44 | -0.12% | 0.12% |
| indvars.NumElimIV | 1197 | 1185 | -12 | -1.00% | 1.00% |
| indvars.NumElimIdentity | 143 | 146 | 3 | 2.10% | 2.10% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29899 | 57 | 0.19% | 0.19% |
| indvars.NumReplaced | 2293 | 2299 | 6 | 0.26% | 0.26% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26404 | -34 | -0.13% | 0.13% |
| instcount.TotalBlocks | 1178338 | 1173652 | -4686 | -0.40% | 0.40% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9895452 | -9990 | -0.10% | 0.10% |
| lcssa.NumLCSSA | 425871 | 425373 | -498 | -0.12% | 0.12% |
| licm.NumHoisted | 378357 | 383352 | 4995 | 1.32% | 1.32% |
| licm.NumMovedCalls | 2193 | 2204 | 11 | 0.50% | 0.50% |
| licm.NumMovedLoads | 35899 | 35755 | -144 | -0.40% | 0.40% |
| licm.NumPromoted | 11178 | 11163 | -15 | -0.13% | 0.13% |
| licm.NumSunk | 13359 | 14321 | 962 | 7.20% | 7.20% |
| loop-delete.NumDeleted | 8547 | 8538 | -9 | -0.11% | 0.11% |
| loop-instsimplify.NumSimplified | 12876 | 12041 | -835 | -6.48% | 6.48% |
| loop-peel.NumPeeled | 1008 | 924 | -84 | -8.33% | 8.33% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42005 | -10 | -0.02% | 0.02% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 241 | 1 | 0.42% | 0.42% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 619 | 1 | 0.16% | 0.16% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11029 | 1 | 0.01% | 0.01% |
| loop-unroll.NumUnrolled | 12608 | 12525 | -83 | -0.66% | 0.66% |
| mem2reg.NumPHIInsert | 192110 | 192073 | -37 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637650 | 637652 | 2 | 0.00% | 0.00% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282998 | -110 | -0.04% | 0.04% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106691 | -21 | -0.02% | 0.02% |
| simple-loop-unswitch.NumBranches | 5178 | 5185 | 7 | 0.14% | 0.14% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 925 | 11 | 1.20% | 1.20% |
| simple-loop-unswitch.NumTrivial | 183 | 179 | -4 | -2.19% | 2.19% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
I.e. we end up with less instructions, less peeling, more LICM activity,
also note how none of those 4 regressions are here. Namely:
| statistic name | LICM-LoopRotate | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015799 | 9014474 | -1325 | -0.01% | 0.01% |
| indvars.NumElimCmp | 3544 | 3546 | 2 | 0.06% | 0.06% |
| indvars.NumElimExt | 36580 | 36681 | 101 | 0.28% | 0.28% |
| indvars.NumElimIV | 1187 | 1185 | -2 | -0.17% | 0.17% |
| indvars.NumElimIdentity | 136 | 146 | 10 | 7.35% | 7.35% |
| indvars.NumLFTR | 29890 | 29899 | 9 | 0.03% | 0.03% |
| indvars.NumReplaced | 2227 | 2299 | 72 | 3.23% | 3.23% |
| indvars.NumWidened | 26329 | 26404 | 75 | 0.28% | 0.28% |
| instcount.TotalBlocks | 1173840 | 1173652 | -188 | -0.02% | 0.02% |
| instcount.TotalInsts | 9896139 | 9895452 | -687 | -0.01% | 0.01% |
| lcssa.NumLCSSA | 423961 | 425373 | 1412 | 0.33% | 0.33% |
| licm.NumHoisted | 378753 | 383352 | 4599 | 1.21% | 1.21% |
| licm.NumMovedCalls | 2208 | 2204 | -4 | -0.18% | 0.18% |
| licm.NumMovedLoads | 31821 | 35755 | 3934 | 12.36% | 12.36% |
| licm.NumPromoted | 11154 | 11163 | 9 | 0.08% | 0.08% |
| licm.NumSunk | 13587 | 14321 | 734 | 5.40% | 5.40% |
| loop-delete.NumDeleted | 8402 | 8538 | 136 | 1.62% | 1.62% |
| loop-instsimplify.NumSimplified | 11890 | 12041 | 151 | 1.27% | 1.27% |
| loop-peel.NumPeeled | 925 | 924 | -1 | -0.11% | 0.11% |
| loop-rotate.NumRotated | 42003 | 42005 | 2 | 0.00% | 0.00% |
| loop-simplifycfg.NumLoopBlocksDeleted | 242 | 241 | -1 | -0.41% | 0.41% |
| loop-simplifycfg.NumLoopExitsDeleted | 20 | 497 | 477 | 2385.00% | 2385.00% |
| loop-simplifycfg.NumTerminatorsFolded | 336 | 619 | 283 | 84.23% | 84.23% |
| loop-unroll.NumCompletelyUnrolled | 11032 | 11029 | -3 | -0.03% | 0.03% |
| loop-unroll.NumUnrolled | 12529 | 12525 | -4 | -0.03% | 0.03% |
| mem2reg.NumDeadAlloca | 10221 | 10222 | 1 | 0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192106 | 192073 | -33 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637643 | 637652 | 9 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 812 | 814 | 2 | 0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 282934 | 282998 | 64 | 0.02% | 0.02% |
| scalar-evolution.NumTripCountsNotComputed | 106718 | 106691 | -27 | -0.03% | 0.03% |
| simple-loop-unswitch.NumBranches | 4752 | 5185 | 433 | 9.11% | 9.11% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 503 | 925 | 422 | 83.90% | 83.90% |
| simple-loop-unswitch.NumSwitches | 18 | 20 | 2 | 11.11% | 11.11% |
| simple-loop-unswitch.NumTrivial | 95 | 179 | 84 | 88.42% | 88.42% |
{F15983613} {F15983615} {F15983616}
(this is vanilla llvm testsuite + rawspeed + darktable)
As an example of the code where early LICM only is bad, see:
https://godbolt.org/z/GzEbacs4K
This does have an observable compile-time regression of +~0.5% geomean
https://llvm-compile-time-tracker.com/compare.php?from=7c5222e4d1a3a14f029e5f614c9aefd0fa505f1e&to=5d81826c3411982ca26e46b9d0aff34c80577664&stat=instructions
but i think that's basically nothing, and there's potential that it might
be avoidable in the future by fixing clang to produce alignment information
on function arguments, thus making the second run unneeded.
Differential Revision: https://reviews.llvm.org/D99249
2021-04-02 09:40:12 +02:00
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Memory SSA
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
[PassManager] Run additional LICM before LoopRotate
Loop rotation often has to perform code duplication
from header into preheader, which introduces PHI nodes.
>>! In D99204, @thopre wrote:
>
> With loop peeling, it is important that unnecessary PHIs be avoided or
> it will leads to spurious peeling. One source of such PHIs is loop
> rotation which creates PHIs for invariant loads. Those PHIs are
> particularly problematic since loop peeling is now run as part of simple
> loop unrolling before GVN is run, and are thus a source of spurious
> peeling.
>
> Note that while some of the load can be hoisted and eventually
> eliminated by instruction combine, this is not always possible due to
> alignment issue. In particular, the motivating example [1] was a load
> inside a class instance which cannot be hoisted because the `this'
> pointer has an alignment of 1.
>
> [1] http://lists.llvm.org/pipermail/llvm-dev/attachments/20210312/4ce73c47/attachment.cpp
Now, we could enhance LoopRotate to avoid duplicating code when not needed,
but instead hoist loop-invariant code, but isn't that a code duplication? (*sic*)
We have LICM, and in fact we already run it right after LoopRotation.
We could try to move it to before LoopRotation,
that is basically free from compile-time perspective:
https://llvm-compile-time-tracker.com/compare.php?from=6c93eb4477d88af046b915bc955c03693b2cbb58&to=a4bee6d07732b1184c436da489040b912f0dc271&stat=instructions
But, looking at stats, i think it isn't great that we would no longer do LICM after LoopRotation, in particular:
| statistic name | LoopRotate-LICM | LICM-LoopRotate | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9015799 | -131 | 0.00% | 0.00% |
| indvars.NumElimCmp | 3536 | 3544 | 8 | 0.23% | 0.23% |
| indvars.NumElimExt | 36725 | 36580 | -145 | -0.39% | 0.39% |
| indvars.NumElimIV | 1197 | 1187 | -10 | -0.84% | 0.84% |
| indvars.NumElimIdentity | 143 | 136 | -7 | -4.90% | 4.90% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29890 | 48 | 0.16% | 0.16% |
| indvars.NumReplaced | 2293 | 2227 | -66 | -2.88% | 2.88% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26329 | -109 | -0.41% | 0.41% |
| instcount.TotalBlocks | 1178338 | 1173840 | -4498 | -0.38% | 0.38% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9896139 | -9303 | -0.09% | 0.09% |
| lcssa.NumLCSSA | 425871 | 423961 | -1910 | -0.45% | 0.45% |
| licm.NumHoisted | 378357 | 378753 | 396 | 0.10% | 0.10% |
| licm.NumMovedCalls | 2193 | 2208 | 15 | 0.68% | 0.68% |
| licm.NumMovedLoads | 35899 | 31821 | -4078 | -11.36% | 11.36% |
| licm.NumPromoted | 11178 | 11154 | -24 | -0.21% | 0.21% |
| licm.NumSunk | 13359 | 13587 | 228 | 1.71% | 1.71% |
| loop-delete.NumDeleted | 8547 | 8402 | -145 | -1.70% | 1.70% |
| loop-instsimplify.NumSimplified | 12876 | 11890 | -986 | -7.66% | 7.66% |
| loop-peel.NumPeeled | 1008 | 925 | -83 | -8.23% | 8.23% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42003 | -12 | -0.03% | 0.03% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 242 | 2 | 0.83% | 0.83% |
| loop-simplifycfg.NumLoopExitsDeleted | 497 | 20 | -477 | -95.98% | 95.98% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 336 | -282 | -45.63% | 45.63% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11032 | 4 | 0.04% | 0.04% |
| loop-unroll.NumUnrolled | 12608 | 12529 | -79 | -0.63% | 0.63% |
| mem2reg.NumDeadAlloca | 10222 | 10221 | -1 | -0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192110 | 192106 | -4 | 0.00% | 0.00% |
| mem2reg.NumSingleStore | 637650 | 637643 | -7 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 814 | 812 | -2 | -0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282934 | -174 | -0.06% | 0.06% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106718 | 6 | 0.01% | 0.01% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
... but that actually regresses LICM (-12% `licm.NumMovedLoads`),
loop-simplifycfg (`NumLoopExitsDeleted`, `NumTerminatorsFolded`),
simple-loop-unswitch (`NumTrivial`).
What if we instead have LICM both before and after LoopRotate?
| statistic name | LoopRotate-LICM | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9014474 | -1456 | -0.02% | 0.02% |
| indvars.NumElimCmp | 3536 | 3546 | 10 | 0.28% | 0.28% |
| indvars.NumElimExt | 36725 | 36681 | -44 | -0.12% | 0.12% |
| indvars.NumElimIV | 1197 | 1185 | -12 | -1.00% | 1.00% |
| indvars.NumElimIdentity | 143 | 146 | 3 | 2.10% | 2.10% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29899 | 57 | 0.19% | 0.19% |
| indvars.NumReplaced | 2293 | 2299 | 6 | 0.26% | 0.26% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26404 | -34 | -0.13% | 0.13% |
| instcount.TotalBlocks | 1178338 | 1173652 | -4686 | -0.40% | 0.40% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9895452 | -9990 | -0.10% | 0.10% |
| lcssa.NumLCSSA | 425871 | 425373 | -498 | -0.12% | 0.12% |
| licm.NumHoisted | 378357 | 383352 | 4995 | 1.32% | 1.32% |
| licm.NumMovedCalls | 2193 | 2204 | 11 | 0.50% | 0.50% |
| licm.NumMovedLoads | 35899 | 35755 | -144 | -0.40% | 0.40% |
| licm.NumPromoted | 11178 | 11163 | -15 | -0.13% | 0.13% |
| licm.NumSunk | 13359 | 14321 | 962 | 7.20% | 7.20% |
| loop-delete.NumDeleted | 8547 | 8538 | -9 | -0.11% | 0.11% |
| loop-instsimplify.NumSimplified | 12876 | 12041 | -835 | -6.48% | 6.48% |
| loop-peel.NumPeeled | 1008 | 924 | -84 | -8.33% | 8.33% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42005 | -10 | -0.02% | 0.02% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 241 | 1 | 0.42% | 0.42% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 619 | 1 | 0.16% | 0.16% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11029 | 1 | 0.01% | 0.01% |
| loop-unroll.NumUnrolled | 12608 | 12525 | -83 | -0.66% | 0.66% |
| mem2reg.NumPHIInsert | 192110 | 192073 | -37 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637650 | 637652 | 2 | 0.00% | 0.00% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282998 | -110 | -0.04% | 0.04% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106691 | -21 | -0.02% | 0.02% |
| simple-loop-unswitch.NumBranches | 5178 | 5185 | 7 | 0.14% | 0.14% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 925 | 11 | 1.20% | 1.20% |
| simple-loop-unswitch.NumTrivial | 183 | 179 | -4 | -2.19% | 2.19% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
I.e. we end up with less instructions, less peeling, more LICM activity,
also note how none of those 4 regressions are here. Namely:
| statistic name | LICM-LoopRotate | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015799 | 9014474 | -1325 | -0.01% | 0.01% |
| indvars.NumElimCmp | 3544 | 3546 | 2 | 0.06% | 0.06% |
| indvars.NumElimExt | 36580 | 36681 | 101 | 0.28% | 0.28% |
| indvars.NumElimIV | 1187 | 1185 | -2 | -0.17% | 0.17% |
| indvars.NumElimIdentity | 136 | 146 | 10 | 7.35% | 7.35% |
| indvars.NumLFTR | 29890 | 29899 | 9 | 0.03% | 0.03% |
| indvars.NumReplaced | 2227 | 2299 | 72 | 3.23% | 3.23% |
| indvars.NumWidened | 26329 | 26404 | 75 | 0.28% | 0.28% |
| instcount.TotalBlocks | 1173840 | 1173652 | -188 | -0.02% | 0.02% |
| instcount.TotalInsts | 9896139 | 9895452 | -687 | -0.01% | 0.01% |
| lcssa.NumLCSSA | 423961 | 425373 | 1412 | 0.33% | 0.33% |
| licm.NumHoisted | 378753 | 383352 | 4599 | 1.21% | 1.21% |
| licm.NumMovedCalls | 2208 | 2204 | -4 | -0.18% | 0.18% |
| licm.NumMovedLoads | 31821 | 35755 | 3934 | 12.36% | 12.36% |
| licm.NumPromoted | 11154 | 11163 | 9 | 0.08% | 0.08% |
| licm.NumSunk | 13587 | 14321 | 734 | 5.40% | 5.40% |
| loop-delete.NumDeleted | 8402 | 8538 | 136 | 1.62% | 1.62% |
| loop-instsimplify.NumSimplified | 11890 | 12041 | 151 | 1.27% | 1.27% |
| loop-peel.NumPeeled | 925 | 924 | -1 | -0.11% | 0.11% |
| loop-rotate.NumRotated | 42003 | 42005 | 2 | 0.00% | 0.00% |
| loop-simplifycfg.NumLoopBlocksDeleted | 242 | 241 | -1 | -0.41% | 0.41% |
| loop-simplifycfg.NumLoopExitsDeleted | 20 | 497 | 477 | 2385.00% | 2385.00% |
| loop-simplifycfg.NumTerminatorsFolded | 336 | 619 | 283 | 84.23% | 84.23% |
| loop-unroll.NumCompletelyUnrolled | 11032 | 11029 | -3 | -0.03% | 0.03% |
| loop-unroll.NumUnrolled | 12529 | 12525 | -4 | -0.03% | 0.03% |
| mem2reg.NumDeadAlloca | 10221 | 10222 | 1 | 0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192106 | 192073 | -33 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637643 | 637652 | 9 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 812 | 814 | 2 | 0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 282934 | 282998 | 64 | 0.02% | 0.02% |
| scalar-evolution.NumTripCountsNotComputed | 106718 | 106691 | -27 | -0.03% | 0.03% |
| simple-loop-unswitch.NumBranches | 4752 | 5185 | 433 | 9.11% | 9.11% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 503 | 925 | 422 | 83.90% | 83.90% |
| simple-loop-unswitch.NumSwitches | 18 | 20 | 2 | 11.11% | 11.11% |
| simple-loop-unswitch.NumTrivial | 95 | 179 | 84 | 88.42% | 88.42% |
{F15983613} {F15983615} {F15983616}
(this is vanilla llvm testsuite + rawspeed + darktable)
As an example of the code where early LICM only is bad, see:
https://godbolt.org/z/GzEbacs4K
This does have an observable compile-time regression of +~0.5% geomean
https://llvm-compile-time-tracker.com/compare.php?from=7c5222e4d1a3a14f029e5f614c9aefd0fa505f1e&to=5d81826c3411982ca26e46b9d0aff34c80577664&stat=instructions
but i think that's basically nothing, and there's potential that it might
be avoidable in the future by fixing clang to produce alignment information
on function arguments, thus making the second run unneeded.
Differential Revision: https://reviews.llvm.org/D99249
2021-04-02 09:40:12 +02:00
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Loop Invariant Code Motion
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Rotate Loops
|
|
|
|
|
; GCN-O1-NEXT: Loop Invariant Code Motion
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Legacy Divergence Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Unswitch loops
|
|
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Recognize loop idioms
|
[PassManager] Run Induction Variable Simplification pass *after* Recognize loop idioms pass, not before
Currently, `-indvars` runs first, and then immediately after `-loop-idiom` does.
I'm not really sure if `-loop-idiom` requires `-indvars` to run beforehand,
but i'm *very* sure that `-indvars` requires `-loop-idiom` to run afterwards,
as it can be seen in the phase-ordering test.
LoopIdiom runs on two types of loops: countable ones, and uncountable ones.
For uncountable ones, IndVars obviously didn't make any change to them,
since they are uncountable, so for them the order should be irrelevant.
For countable ones, well, they should have been countable before IndVars
for IndVars to make any change to them, and since SCEV is used on them,
it shouldn't matter if IndVars have already canonicalized them.
So i don't really see why we'd want the current ordering.
Should this cause issues, it will give us a reproducer test case
that shows flaws in this logic, and we then could adjust accordingly.
While this is quite likely beneficial in-the-wild already,
it's a required part for the full motivational pattern
behind `left-shift-until-bittest` loop idiom (D91038).
Reviewed By: dmgreen
Differential Revision: https://reviews.llvm.org/D91800
2020-11-25 17:17:25 +01:00
|
|
|
; GCN-O1-NEXT: Induction Variable Simplification
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Delete dead loops
|
|
|
|
|
; GCN-O1-NEXT: Unroll loops
|
[amdgpu] Run SROA after loop unrolling.
Summary: - There are promotable `alloca`s after loop unrolling.
Reviewers: rampitec, arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, nikic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D84252
2020-07-20 07:09:13 +02:00
|
|
|
; GCN-O1-NEXT: SROA
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Sparse Conditional Constant Propagation
|
|
|
|
|
; GCN-O1-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O1-NEXT: Bit-Tracking Dead Code Elimination
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Aggressive Dead Code Elimination
|
2021-01-10 10:52:01 +01:00
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Memory SSA
|
|
|
|
|
; GCN-O1-NEXT: MemCpy Optimization
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: A No-Op Barrier Pass
|
|
|
|
|
; GCN-O1-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O1-NEXT: Deduce function attributes in RPO
|
|
|
|
|
; GCN-O1-NEXT: Global Variable Optimizer
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Dead Global Elimination
|
|
|
|
|
; GCN-O1-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O1-NEXT: Globals Alias Analysis
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Float to int
|
|
|
|
|
; GCN-O1-NEXT: Lower constant intrinsics
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Rotate Loops
|
|
|
|
|
; GCN-O1-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Loop Distribution
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O1-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Inject TLI Mappings
|
|
|
|
|
; GCN-O1-NEXT: Loop Vectorization
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Load Elimination
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
2021-05-08 12:13:05 +02:00
|
|
|
; GCN-O1-NEXT: Optimize scalar/vector ops
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Unroll loops
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Memory SSA
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
2020-09-16 04:12:10 +02:00
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Loop Invariant Code Motion
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Warn about non-applied transformations
|
|
|
|
|
; GCN-O1-NEXT: Alignment from assumptions
|
|
|
|
|
; GCN-O1-NEXT: Strip Unused Function Prototypes
|
[LPM] Port CGProfilePass from NPM to LPM
Reviewers: hans, chandlerc!, asbirlea, nikic
Reviewed By: hans, nikic
Subscribers: steven_wu, dexonsmith, nikic, echristo, void, zhizhouy, cfe-commits, aeubanks, MaskRay, jvesely, nhaehnle, hiraditya, kerbowa, llvm-commits
Tags: #llvm, #clang
Differential Revision: https://reviews.llvm.org/D83013
2020-07-08 21:30:28 +02:00
|
|
|
; GCN-O1-NEXT: Call Graph Profile
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O1-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O1-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O1-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O1-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O1-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O1-NEXT: Loop Sink
|
|
|
|
|
; GCN-O1-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O1-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O1-NEXT: Remove redundant instructions
|
|
|
|
|
; GCN-O1-NEXT: Hoist/decompose integer division and remainder
|
|
|
|
|
; GCN-O1-NEXT: Simplify the CFG
|
2020-11-13 10:46:55 +01:00
|
|
|
; GCN-O1-NEXT: Annotation Remarks
|
2020-05-21 20:58:35 +02:00
|
|
|
|
|
|
|
|
; GCN-O1-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
|
|
|
|
|
; GCN-O1-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
|
|
|
|
|
; GCN-O1-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O1-NEXT: Target Library Information
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
|
|
|
|
|
; GCN-O1-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O1-NEXT: Target Library Information
|
|
|
|
|
; GCN-O1-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O1-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O1-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O1-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O1-NEXT: Block Frequency Analysis
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; GCN-O2: Pass Arguments:
|
|
|
|
|
; GCN-O2-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O2-NEXT: AMDGPU Address space based Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: External Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O2-NEXT: Target Library Information
|
|
|
|
|
; GCN-O2-NEXT: Type-Based Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: Scoped NoAlias Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Early propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O2-NEXT: Replace builtin math calls with that native versions.
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Simplify well-known AMD library calls
|
2021-04-12 20:51:51 +02:00
|
|
|
; GCN-O2-NEXT: Lower 'expect' Intrinsics
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: SROA
|
|
|
|
|
; GCN-O2-NEXT: Early CSE
|
|
|
|
|
|
|
|
|
|
; GCN-O2-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O2-NEXT: Target Library Information
|
|
|
|
|
; GCN-O2-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O2-NEXT: Target Pass Configuration
|
|
|
|
|
; GCN-O2-NEXT: Type-Based Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: Scoped NoAlias Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: AMDGPU Address space based Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: External Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O2-NEXT: Profile summary info
|
|
|
|
|
; GCN-O2-NEXT: ModulePass Manager
|
2020-11-16 10:49:04 +01:00
|
|
|
; GCN-O2-NEXT: Annotation2Metadata
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Force set function attributes
|
|
|
|
|
; GCN-O2-NEXT: Infer set function attributes
|
|
|
|
|
; GCN-O2-NEXT: Unify multiple OpenCL metadata due to linking
|
|
|
|
|
; GCN-O2-NEXT: AMDGPU Printf lowering
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Late propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O2-NEXT: Interprocedural Sparse Conditional Constant Propagation
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Called Value Propagation
|
|
|
|
|
; GCN-O2-NEXT: Global Variable Optimizer
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Promote Memory to Register
|
|
|
|
|
; GCN-O2-NEXT: Dead Argument Elimination
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O2-NEXT: Globals Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: Call Graph SCC Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Remove unused exception handling info
|
2021-01-06 06:11:21 +01:00
|
|
|
; GCN-O2-NEXT: Function Integration/Inlining
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: OpenMP specific optimizations
|
|
|
|
|
; GCN-O2-NEXT: Deduce function attributes
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Infer address spaces
|
|
|
|
|
; GCN-O2-NEXT: AMDGPU Kernel Attributes
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
2020-05-21 01:24:06 +02:00
|
|
|
; GCN-O2-NEXT: AMDGPU Promote Alloca to vector
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: SROA
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Memory SSA
|
|
|
|
|
; GCN-O2-NEXT: Early CSE w/ MemorySSA
|
|
|
|
|
; GCN-O2-NEXT: Speculatively execute instructions if target has divergent branches
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Lazy Value Information Analysis
|
|
|
|
|
; GCN-O2-NEXT: Jump Threading
|
|
|
|
|
; GCN-O2-NEXT: Value Propagation
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Conditionally eliminate dead library calls
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: PGOMemOPSize
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Tail Call Elimination
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: Reassociate expressions
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
[PassManager] Run additional LICM before LoopRotate
Loop rotation often has to perform code duplication
from header into preheader, which introduces PHI nodes.
>>! In D99204, @thopre wrote:
>
> With loop peeling, it is important that unnecessary PHIs be avoided or
> it will leads to spurious peeling. One source of such PHIs is loop
> rotation which creates PHIs for invariant loads. Those PHIs are
> particularly problematic since loop peeling is now run as part of simple
> loop unrolling before GVN is run, and are thus a source of spurious
> peeling.
>
> Note that while some of the load can be hoisted and eventually
> eliminated by instruction combine, this is not always possible due to
> alignment issue. In particular, the motivating example [1] was a load
> inside a class instance which cannot be hoisted because the `this'
> pointer has an alignment of 1.
>
> [1] http://lists.llvm.org/pipermail/llvm-dev/attachments/20210312/4ce73c47/attachment.cpp
Now, we could enhance LoopRotate to avoid duplicating code when not needed,
but instead hoist loop-invariant code, but isn't that a code duplication? (*sic*)
We have LICM, and in fact we already run it right after LoopRotation.
We could try to move it to before LoopRotation,
that is basically free from compile-time perspective:
https://llvm-compile-time-tracker.com/compare.php?from=6c93eb4477d88af046b915bc955c03693b2cbb58&to=a4bee6d07732b1184c436da489040b912f0dc271&stat=instructions
But, looking at stats, i think it isn't great that we would no longer do LICM after LoopRotation, in particular:
| statistic name | LoopRotate-LICM | LICM-LoopRotate | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9015799 | -131 | 0.00% | 0.00% |
| indvars.NumElimCmp | 3536 | 3544 | 8 | 0.23% | 0.23% |
| indvars.NumElimExt | 36725 | 36580 | -145 | -0.39% | 0.39% |
| indvars.NumElimIV | 1197 | 1187 | -10 | -0.84% | 0.84% |
| indvars.NumElimIdentity | 143 | 136 | -7 | -4.90% | 4.90% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29890 | 48 | 0.16% | 0.16% |
| indvars.NumReplaced | 2293 | 2227 | -66 | -2.88% | 2.88% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26329 | -109 | -0.41% | 0.41% |
| instcount.TotalBlocks | 1178338 | 1173840 | -4498 | -0.38% | 0.38% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9896139 | -9303 | -0.09% | 0.09% |
| lcssa.NumLCSSA | 425871 | 423961 | -1910 | -0.45% | 0.45% |
| licm.NumHoisted | 378357 | 378753 | 396 | 0.10% | 0.10% |
| licm.NumMovedCalls | 2193 | 2208 | 15 | 0.68% | 0.68% |
| licm.NumMovedLoads | 35899 | 31821 | -4078 | -11.36% | 11.36% |
| licm.NumPromoted | 11178 | 11154 | -24 | -0.21% | 0.21% |
| licm.NumSunk | 13359 | 13587 | 228 | 1.71% | 1.71% |
| loop-delete.NumDeleted | 8547 | 8402 | -145 | -1.70% | 1.70% |
| loop-instsimplify.NumSimplified | 12876 | 11890 | -986 | -7.66% | 7.66% |
| loop-peel.NumPeeled | 1008 | 925 | -83 | -8.23% | 8.23% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42003 | -12 | -0.03% | 0.03% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 242 | 2 | 0.83% | 0.83% |
| loop-simplifycfg.NumLoopExitsDeleted | 497 | 20 | -477 | -95.98% | 95.98% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 336 | -282 | -45.63% | 45.63% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11032 | 4 | 0.04% | 0.04% |
| loop-unroll.NumUnrolled | 12608 | 12529 | -79 | -0.63% | 0.63% |
| mem2reg.NumDeadAlloca | 10222 | 10221 | -1 | -0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192110 | 192106 | -4 | 0.00% | 0.00% |
| mem2reg.NumSingleStore | 637650 | 637643 | -7 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 814 | 812 | -2 | -0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282934 | -174 | -0.06% | 0.06% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106718 | 6 | 0.01% | 0.01% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
... but that actually regresses LICM (-12% `licm.NumMovedLoads`),
loop-simplifycfg (`NumLoopExitsDeleted`, `NumTerminatorsFolded`),
simple-loop-unswitch (`NumTrivial`).
What if we instead have LICM both before and after LoopRotate?
| statistic name | LoopRotate-LICM | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9014474 | -1456 | -0.02% | 0.02% |
| indvars.NumElimCmp | 3536 | 3546 | 10 | 0.28% | 0.28% |
| indvars.NumElimExt | 36725 | 36681 | -44 | -0.12% | 0.12% |
| indvars.NumElimIV | 1197 | 1185 | -12 | -1.00% | 1.00% |
| indvars.NumElimIdentity | 143 | 146 | 3 | 2.10% | 2.10% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29899 | 57 | 0.19% | 0.19% |
| indvars.NumReplaced | 2293 | 2299 | 6 | 0.26% | 0.26% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26404 | -34 | -0.13% | 0.13% |
| instcount.TotalBlocks | 1178338 | 1173652 | -4686 | -0.40% | 0.40% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9895452 | -9990 | -0.10% | 0.10% |
| lcssa.NumLCSSA | 425871 | 425373 | -498 | -0.12% | 0.12% |
| licm.NumHoisted | 378357 | 383352 | 4995 | 1.32% | 1.32% |
| licm.NumMovedCalls | 2193 | 2204 | 11 | 0.50% | 0.50% |
| licm.NumMovedLoads | 35899 | 35755 | -144 | -0.40% | 0.40% |
| licm.NumPromoted | 11178 | 11163 | -15 | -0.13% | 0.13% |
| licm.NumSunk | 13359 | 14321 | 962 | 7.20% | 7.20% |
| loop-delete.NumDeleted | 8547 | 8538 | -9 | -0.11% | 0.11% |
| loop-instsimplify.NumSimplified | 12876 | 12041 | -835 | -6.48% | 6.48% |
| loop-peel.NumPeeled | 1008 | 924 | -84 | -8.33% | 8.33% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42005 | -10 | -0.02% | 0.02% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 241 | 1 | 0.42% | 0.42% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 619 | 1 | 0.16% | 0.16% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11029 | 1 | 0.01% | 0.01% |
| loop-unroll.NumUnrolled | 12608 | 12525 | -83 | -0.66% | 0.66% |
| mem2reg.NumPHIInsert | 192110 | 192073 | -37 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637650 | 637652 | 2 | 0.00% | 0.00% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282998 | -110 | -0.04% | 0.04% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106691 | -21 | -0.02% | 0.02% |
| simple-loop-unswitch.NumBranches | 5178 | 5185 | 7 | 0.14% | 0.14% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 925 | 11 | 1.20% | 1.20% |
| simple-loop-unswitch.NumTrivial | 183 | 179 | -4 | -2.19% | 2.19% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
I.e. we end up with less instructions, less peeling, more LICM activity,
also note how none of those 4 regressions are here. Namely:
| statistic name | LICM-LoopRotate | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015799 | 9014474 | -1325 | -0.01% | 0.01% |
| indvars.NumElimCmp | 3544 | 3546 | 2 | 0.06% | 0.06% |
| indvars.NumElimExt | 36580 | 36681 | 101 | 0.28% | 0.28% |
| indvars.NumElimIV | 1187 | 1185 | -2 | -0.17% | 0.17% |
| indvars.NumElimIdentity | 136 | 146 | 10 | 7.35% | 7.35% |
| indvars.NumLFTR | 29890 | 29899 | 9 | 0.03% | 0.03% |
| indvars.NumReplaced | 2227 | 2299 | 72 | 3.23% | 3.23% |
| indvars.NumWidened | 26329 | 26404 | 75 | 0.28% | 0.28% |
| instcount.TotalBlocks | 1173840 | 1173652 | -188 | -0.02% | 0.02% |
| instcount.TotalInsts | 9896139 | 9895452 | -687 | -0.01% | 0.01% |
| lcssa.NumLCSSA | 423961 | 425373 | 1412 | 0.33% | 0.33% |
| licm.NumHoisted | 378753 | 383352 | 4599 | 1.21% | 1.21% |
| licm.NumMovedCalls | 2208 | 2204 | -4 | -0.18% | 0.18% |
| licm.NumMovedLoads | 31821 | 35755 | 3934 | 12.36% | 12.36% |
| licm.NumPromoted | 11154 | 11163 | 9 | 0.08% | 0.08% |
| licm.NumSunk | 13587 | 14321 | 734 | 5.40% | 5.40% |
| loop-delete.NumDeleted | 8402 | 8538 | 136 | 1.62% | 1.62% |
| loop-instsimplify.NumSimplified | 11890 | 12041 | 151 | 1.27% | 1.27% |
| loop-peel.NumPeeled | 925 | 924 | -1 | -0.11% | 0.11% |
| loop-rotate.NumRotated | 42003 | 42005 | 2 | 0.00% | 0.00% |
| loop-simplifycfg.NumLoopBlocksDeleted | 242 | 241 | -1 | -0.41% | 0.41% |
| loop-simplifycfg.NumLoopExitsDeleted | 20 | 497 | 477 | 2385.00% | 2385.00% |
| loop-simplifycfg.NumTerminatorsFolded | 336 | 619 | 283 | 84.23% | 84.23% |
| loop-unroll.NumCompletelyUnrolled | 11032 | 11029 | -3 | -0.03% | 0.03% |
| loop-unroll.NumUnrolled | 12529 | 12525 | -4 | -0.03% | 0.03% |
| mem2reg.NumDeadAlloca | 10221 | 10222 | 1 | 0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192106 | 192073 | -33 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637643 | 637652 | 9 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 812 | 814 | 2 | 0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 282934 | 282998 | 64 | 0.02% | 0.02% |
| scalar-evolution.NumTripCountsNotComputed | 106718 | 106691 | -27 | -0.03% | 0.03% |
| simple-loop-unswitch.NumBranches | 4752 | 5185 | 433 | 9.11% | 9.11% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 503 | 925 | 422 | 83.90% | 83.90% |
| simple-loop-unswitch.NumSwitches | 18 | 20 | 2 | 11.11% | 11.11% |
| simple-loop-unswitch.NumTrivial | 95 | 179 | 84 | 88.42% | 88.42% |
{F15983613} {F15983615} {F15983616}
(this is vanilla llvm testsuite + rawspeed + darktable)
As an example of the code where early LICM only is bad, see:
https://godbolt.org/z/GzEbacs4K
This does have an observable compile-time regression of +~0.5% geomean
https://llvm-compile-time-tracker.com/compare.php?from=7c5222e4d1a3a14f029e5f614c9aefd0fa505f1e&to=5d81826c3411982ca26e46b9d0aff34c80577664&stat=instructions
but i think that's basically nothing, and there's potential that it might
be avoidable in the future by fixing clang to produce alignment information
on function arguments, thus making the second run unneeded.
Differential Revision: https://reviews.llvm.org/D99249
2021-04-02 09:40:12 +02:00
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Memory SSA
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
[PassManager] Run additional LICM before LoopRotate
Loop rotation often has to perform code duplication
from header into preheader, which introduces PHI nodes.
>>! In D99204, @thopre wrote:
>
> With loop peeling, it is important that unnecessary PHIs be avoided or
> it will leads to spurious peeling. One source of such PHIs is loop
> rotation which creates PHIs for invariant loads. Those PHIs are
> particularly problematic since loop peeling is now run as part of simple
> loop unrolling before GVN is run, and are thus a source of spurious
> peeling.
>
> Note that while some of the load can be hoisted and eventually
> eliminated by instruction combine, this is not always possible due to
> alignment issue. In particular, the motivating example [1] was a load
> inside a class instance which cannot be hoisted because the `this'
> pointer has an alignment of 1.
>
> [1] http://lists.llvm.org/pipermail/llvm-dev/attachments/20210312/4ce73c47/attachment.cpp
Now, we could enhance LoopRotate to avoid duplicating code when not needed,
but instead hoist loop-invariant code, but isn't that a code duplication? (*sic*)
We have LICM, and in fact we already run it right after LoopRotation.
We could try to move it to before LoopRotation,
that is basically free from compile-time perspective:
https://llvm-compile-time-tracker.com/compare.php?from=6c93eb4477d88af046b915bc955c03693b2cbb58&to=a4bee6d07732b1184c436da489040b912f0dc271&stat=instructions
But, looking at stats, i think it isn't great that we would no longer do LICM after LoopRotation, in particular:
| statistic name | LoopRotate-LICM | LICM-LoopRotate | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9015799 | -131 | 0.00% | 0.00% |
| indvars.NumElimCmp | 3536 | 3544 | 8 | 0.23% | 0.23% |
| indvars.NumElimExt | 36725 | 36580 | -145 | -0.39% | 0.39% |
| indvars.NumElimIV | 1197 | 1187 | -10 | -0.84% | 0.84% |
| indvars.NumElimIdentity | 143 | 136 | -7 | -4.90% | 4.90% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29890 | 48 | 0.16% | 0.16% |
| indvars.NumReplaced | 2293 | 2227 | -66 | -2.88% | 2.88% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26329 | -109 | -0.41% | 0.41% |
| instcount.TotalBlocks | 1178338 | 1173840 | -4498 | -0.38% | 0.38% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9896139 | -9303 | -0.09% | 0.09% |
| lcssa.NumLCSSA | 425871 | 423961 | -1910 | -0.45% | 0.45% |
| licm.NumHoisted | 378357 | 378753 | 396 | 0.10% | 0.10% |
| licm.NumMovedCalls | 2193 | 2208 | 15 | 0.68% | 0.68% |
| licm.NumMovedLoads | 35899 | 31821 | -4078 | -11.36% | 11.36% |
| licm.NumPromoted | 11178 | 11154 | -24 | -0.21% | 0.21% |
| licm.NumSunk | 13359 | 13587 | 228 | 1.71% | 1.71% |
| loop-delete.NumDeleted | 8547 | 8402 | -145 | -1.70% | 1.70% |
| loop-instsimplify.NumSimplified | 12876 | 11890 | -986 | -7.66% | 7.66% |
| loop-peel.NumPeeled | 1008 | 925 | -83 | -8.23% | 8.23% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42003 | -12 | -0.03% | 0.03% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 242 | 2 | 0.83% | 0.83% |
| loop-simplifycfg.NumLoopExitsDeleted | 497 | 20 | -477 | -95.98% | 95.98% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 336 | -282 | -45.63% | 45.63% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11032 | 4 | 0.04% | 0.04% |
| loop-unroll.NumUnrolled | 12608 | 12529 | -79 | -0.63% | 0.63% |
| mem2reg.NumDeadAlloca | 10222 | 10221 | -1 | -0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192110 | 192106 | -4 | 0.00% | 0.00% |
| mem2reg.NumSingleStore | 637650 | 637643 | -7 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 814 | 812 | -2 | -0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282934 | -174 | -0.06% | 0.06% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106718 | 6 | 0.01% | 0.01% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
... but that actually regresses LICM (-12% `licm.NumMovedLoads`),
loop-simplifycfg (`NumLoopExitsDeleted`, `NumTerminatorsFolded`),
simple-loop-unswitch (`NumTrivial`).
What if we instead have LICM both before and after LoopRotate?
| statistic name | LoopRotate-LICM | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9014474 | -1456 | -0.02% | 0.02% |
| indvars.NumElimCmp | 3536 | 3546 | 10 | 0.28% | 0.28% |
| indvars.NumElimExt | 36725 | 36681 | -44 | -0.12% | 0.12% |
| indvars.NumElimIV | 1197 | 1185 | -12 | -1.00% | 1.00% |
| indvars.NumElimIdentity | 143 | 146 | 3 | 2.10% | 2.10% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29899 | 57 | 0.19% | 0.19% |
| indvars.NumReplaced | 2293 | 2299 | 6 | 0.26% | 0.26% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26404 | -34 | -0.13% | 0.13% |
| instcount.TotalBlocks | 1178338 | 1173652 | -4686 | -0.40% | 0.40% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9895452 | -9990 | -0.10% | 0.10% |
| lcssa.NumLCSSA | 425871 | 425373 | -498 | -0.12% | 0.12% |
| licm.NumHoisted | 378357 | 383352 | 4995 | 1.32% | 1.32% |
| licm.NumMovedCalls | 2193 | 2204 | 11 | 0.50% | 0.50% |
| licm.NumMovedLoads | 35899 | 35755 | -144 | -0.40% | 0.40% |
| licm.NumPromoted | 11178 | 11163 | -15 | -0.13% | 0.13% |
| licm.NumSunk | 13359 | 14321 | 962 | 7.20% | 7.20% |
| loop-delete.NumDeleted | 8547 | 8538 | -9 | -0.11% | 0.11% |
| loop-instsimplify.NumSimplified | 12876 | 12041 | -835 | -6.48% | 6.48% |
| loop-peel.NumPeeled | 1008 | 924 | -84 | -8.33% | 8.33% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42005 | -10 | -0.02% | 0.02% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 241 | 1 | 0.42% | 0.42% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 619 | 1 | 0.16% | 0.16% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11029 | 1 | 0.01% | 0.01% |
| loop-unroll.NumUnrolled | 12608 | 12525 | -83 | -0.66% | 0.66% |
| mem2reg.NumPHIInsert | 192110 | 192073 | -37 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637650 | 637652 | 2 | 0.00% | 0.00% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282998 | -110 | -0.04% | 0.04% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106691 | -21 | -0.02% | 0.02% |
| simple-loop-unswitch.NumBranches | 5178 | 5185 | 7 | 0.14% | 0.14% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 925 | 11 | 1.20% | 1.20% |
| simple-loop-unswitch.NumTrivial | 183 | 179 | -4 | -2.19% | 2.19% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
I.e. we end up with less instructions, less peeling, more LICM activity,
also note how none of those 4 regressions are here. Namely:
| statistic name | LICM-LoopRotate | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015799 | 9014474 | -1325 | -0.01% | 0.01% |
| indvars.NumElimCmp | 3544 | 3546 | 2 | 0.06% | 0.06% |
| indvars.NumElimExt | 36580 | 36681 | 101 | 0.28% | 0.28% |
| indvars.NumElimIV | 1187 | 1185 | -2 | -0.17% | 0.17% |
| indvars.NumElimIdentity | 136 | 146 | 10 | 7.35% | 7.35% |
| indvars.NumLFTR | 29890 | 29899 | 9 | 0.03% | 0.03% |
| indvars.NumReplaced | 2227 | 2299 | 72 | 3.23% | 3.23% |
| indvars.NumWidened | 26329 | 26404 | 75 | 0.28% | 0.28% |
| instcount.TotalBlocks | 1173840 | 1173652 | -188 | -0.02% | 0.02% |
| instcount.TotalInsts | 9896139 | 9895452 | -687 | -0.01% | 0.01% |
| lcssa.NumLCSSA | 423961 | 425373 | 1412 | 0.33% | 0.33% |
| licm.NumHoisted | 378753 | 383352 | 4599 | 1.21% | 1.21% |
| licm.NumMovedCalls | 2208 | 2204 | -4 | -0.18% | 0.18% |
| licm.NumMovedLoads | 31821 | 35755 | 3934 | 12.36% | 12.36% |
| licm.NumPromoted | 11154 | 11163 | 9 | 0.08% | 0.08% |
| licm.NumSunk | 13587 | 14321 | 734 | 5.40% | 5.40% |
| loop-delete.NumDeleted | 8402 | 8538 | 136 | 1.62% | 1.62% |
| loop-instsimplify.NumSimplified | 11890 | 12041 | 151 | 1.27% | 1.27% |
| loop-peel.NumPeeled | 925 | 924 | -1 | -0.11% | 0.11% |
| loop-rotate.NumRotated | 42003 | 42005 | 2 | 0.00% | 0.00% |
| loop-simplifycfg.NumLoopBlocksDeleted | 242 | 241 | -1 | -0.41% | 0.41% |
| loop-simplifycfg.NumLoopExitsDeleted | 20 | 497 | 477 | 2385.00% | 2385.00% |
| loop-simplifycfg.NumTerminatorsFolded | 336 | 619 | 283 | 84.23% | 84.23% |
| loop-unroll.NumCompletelyUnrolled | 11032 | 11029 | -3 | -0.03% | 0.03% |
| loop-unroll.NumUnrolled | 12529 | 12525 | -4 | -0.03% | 0.03% |
| mem2reg.NumDeadAlloca | 10221 | 10222 | 1 | 0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192106 | 192073 | -33 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637643 | 637652 | 9 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 812 | 814 | 2 | 0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 282934 | 282998 | 64 | 0.02% | 0.02% |
| scalar-evolution.NumTripCountsNotComputed | 106718 | 106691 | -27 | -0.03% | 0.03% |
| simple-loop-unswitch.NumBranches | 4752 | 5185 | 433 | 9.11% | 9.11% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 503 | 925 | 422 | 83.90% | 83.90% |
| simple-loop-unswitch.NumSwitches | 18 | 20 | 2 | 11.11% | 11.11% |
| simple-loop-unswitch.NumTrivial | 95 | 179 | 84 | 88.42% | 88.42% |
{F15983613} {F15983615} {F15983616}
(this is vanilla llvm testsuite + rawspeed + darktable)
As an example of the code where early LICM only is bad, see:
https://godbolt.org/z/GzEbacs4K
This does have an observable compile-time regression of +~0.5% geomean
https://llvm-compile-time-tracker.com/compare.php?from=7c5222e4d1a3a14f029e5f614c9aefd0fa505f1e&to=5d81826c3411982ca26e46b9d0aff34c80577664&stat=instructions
but i think that's basically nothing, and there's potential that it might
be avoidable in the future by fixing clang to produce alignment information
on function arguments, thus making the second run unneeded.
Differential Revision: https://reviews.llvm.org/D99249
2021-04-02 09:40:12 +02:00
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Loop Invariant Code Motion
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Rotate Loops
|
|
|
|
|
; GCN-O2-NEXT: Loop Invariant Code Motion
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Legacy Divergence Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Unswitch loops
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Recognize loop idioms
|
2020-11-25 17:38:51 +01:00
|
|
|
; GCN-O2-NEXT: Induction Variable Simplification
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Delete dead loops
|
|
|
|
|
; GCN-O2-NEXT: Unroll loops
|
[amdgpu] Run SROA after loop unrolling.
Summary: - There are promotable `alloca`s after loop unrolling.
Reviewers: rampitec, arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, nikic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D84252
2020-07-20 07:09:13 +02:00
|
|
|
; GCN-O2-NEXT: SROA
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: MergedLoadStoreMotion
|
|
|
|
|
; GCN-O2-NEXT: Phi Values Analysis
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Memory Dependence Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Global Value Numbering
|
|
|
|
|
; GCN-O2-NEXT: Sparse Conditional Constant Propagation
|
|
|
|
|
; GCN-O2-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O2-NEXT: Bit-Tracking Dead Code Elimination
|
2021-01-10 10:52:01 +01:00
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Lazy Value Information Analysis
|
|
|
|
|
; GCN-O2-NEXT: Jump Threading
|
|
|
|
|
; GCN-O2-NEXT: Value Propagation
|
2020-10-21 11:21:50 +02:00
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Aggressive Dead Code Elimination
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
2020-09-26 18:56:15 +02:00
|
|
|
; GCN-O2-NEXT: Memory SSA
|
2021-01-10 10:52:01 +01:00
|
|
|
; GCN-O2-NEXT: MemCpy Optimization
|
2021-06-08 22:23:08 +02:00
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
2021-06-20 18:03:30 +02:00
|
|
|
; GCN-O2-NEXT: Dead Store Elimination
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
2020-10-16 09:42:18 +02:00
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
2020-09-16 04:12:10 +02:00
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Loop Invariant Code Motion
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: A No-Op Barrier Pass
|
|
|
|
|
; GCN-O2-NEXT: Eliminate Available Externally Globals
|
|
|
|
|
; GCN-O2-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O2-NEXT: Deduce function attributes in RPO
|
|
|
|
|
; GCN-O2-NEXT: Global Variable Optimizer
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Dead Global Elimination
|
|
|
|
|
; GCN-O2-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O2-NEXT: Globals Alias Analysis
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Float to int
|
|
|
|
|
; GCN-O2-NEXT: Lower constant intrinsics
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Rotate Loops
|
|
|
|
|
; GCN-O2-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Loop Distribution
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O2-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Inject TLI Mappings
|
|
|
|
|
; GCN-O2-NEXT: Loop Vectorization
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Load Elimination
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Inject TLI Mappings
|
|
|
|
|
; GCN-O2-NEXT: SLP Vectorizer
|
2020-05-22 18:13:18 +02:00
|
|
|
; GCN-O2-NEXT: Optimize scalar/vector ops
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Unroll loops
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Memory SSA
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
2020-09-16 04:12:10 +02:00
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Loop Invariant Code Motion
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Warn about non-applied transformations
|
|
|
|
|
; GCN-O2-NEXT: Alignment from assumptions
|
|
|
|
|
; GCN-O2-NEXT: Strip Unused Function Prototypes
|
|
|
|
|
; GCN-O2-NEXT: Dead Global Elimination
|
|
|
|
|
; GCN-O2-NEXT: Merge Duplicate Global Constants
|
[LPM] Port CGProfilePass from NPM to LPM
Reviewers: hans, chandlerc!, asbirlea, nikic
Reviewed By: hans, nikic
Subscribers: steven_wu, dexonsmith, nikic, echristo, void, zhizhouy, cfe-commits, aeubanks, MaskRay, jvesely, nhaehnle, hiraditya, kerbowa, llvm-commits
Tags: #llvm, #clang
Differential Revision: https://reviews.llvm.org/D83013
2020-07-08 21:30:28 +02:00
|
|
|
; GCN-O2-NEXT: Call Graph Profile
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O2-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O2-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O2-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O2-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O2-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O2-NEXT: Loop Sink
|
|
|
|
|
; GCN-O2-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O2-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O2-NEXT: Remove redundant instructions
|
|
|
|
|
; GCN-O2-NEXT: Hoist/decompose integer division and remainder
|
|
|
|
|
; GCN-O2-NEXT: Simplify the CFG
|
2020-11-13 10:46:55 +01:00
|
|
|
; GCN-O2-NEXT: Annotation Remarks
|
2020-05-21 20:58:35 +02:00
|
|
|
|
|
|
|
|
; GCN-O2-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
|
|
|
|
|
; GCN-O2-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
|
|
|
|
|
; GCN-O2-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O2-NEXT: Target Library Information
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
|
|
|
|
|
; GCN-O2-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O2-NEXT: Target Library Information
|
|
|
|
|
; GCN-O2-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O2-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O2-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O2-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O2-NEXT: Block Frequency Analysis
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; GCN-O3: Pass Arguments:
|
|
|
|
|
; GCN-O3-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O3-NEXT: AMDGPU Address space based Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: External Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O3-NEXT: Target Library Information
|
|
|
|
|
; GCN-O3-NEXT: Type-Based Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: Scoped NoAlias Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Early propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O3-NEXT: Replace builtin math calls with that native versions.
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Simplify well-known AMD library calls
|
2021-04-12 20:51:51 +02:00
|
|
|
; GCN-O3-NEXT: Lower 'expect' Intrinsics
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: SROA
|
|
|
|
|
; GCN-O3-NEXT: Early CSE
|
|
|
|
|
|
|
|
|
|
; GCN-O3-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O3-NEXT: Target Library Information
|
|
|
|
|
; GCN-O3-NEXT: Target Transform Information
|
|
|
|
|
; GCN-O3-NEXT: Target Pass Configuration
|
|
|
|
|
; GCN-O3-NEXT: Type-Based Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: Scoped NoAlias Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: AMDGPU Address space based Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: External Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: Assumption Cache Tracker
|
|
|
|
|
; GCN-O3-NEXT: Profile summary info
|
|
|
|
|
; GCN-O3-NEXT: ModulePass Manager
|
2020-11-16 10:49:04 +01:00
|
|
|
; GCN-O3-NEXT: Annotation2Metadata
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Force set function attributes
|
|
|
|
|
; GCN-O3-NEXT: Infer set function attributes
|
|
|
|
|
; GCN-O3-NEXT: Unify multiple OpenCL metadata due to linking
|
|
|
|
|
; GCN-O3-NEXT: AMDGPU Printf lowering
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Late propagate attributes from kernels to functions
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Call-site splitting
|
|
|
|
|
; GCN-O3-NEXT: Interprocedural Sparse Conditional Constant Propagation
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Called Value Propagation
|
|
|
|
|
; GCN-O3-NEXT: Global Variable Optimizer
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Promote Memory to Register
|
|
|
|
|
; GCN-O3-NEXT: Dead Argument Elimination
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O3-NEXT: Globals Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: Call Graph SCC Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Remove unused exception handling info
|
2021-01-06 06:11:21 +01:00
|
|
|
; GCN-O3-NEXT: Function Integration/Inlining
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: OpenMP specific optimizations
|
|
|
|
|
; GCN-O3-NEXT: Deduce function attributes
|
|
|
|
|
; GCN-O3-NEXT: Promote 'by reference' arguments to scalars
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Infer address spaces
|
|
|
|
|
; GCN-O3-NEXT: AMDGPU Kernel Attributes
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
2020-05-21 01:24:06 +02:00
|
|
|
; GCN-O3-NEXT: AMDGPU Promote Alloca to vector
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: SROA
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Memory SSA
|
|
|
|
|
; GCN-O3-NEXT: Early CSE w/ MemorySSA
|
|
|
|
|
; GCN-O3-NEXT: Speculatively execute instructions if target has divergent branches
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Lazy Value Information Analysis
|
|
|
|
|
; GCN-O3-NEXT: Jump Threading
|
|
|
|
|
; GCN-O3-NEXT: Value Propagation
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Combine pattern based expressions
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Conditionally eliminate dead library calls
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: PGOMemOPSize
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Tail Call Elimination
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: Reassociate expressions
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
[PassManager] Run additional LICM before LoopRotate
Loop rotation often has to perform code duplication
from header into preheader, which introduces PHI nodes.
>>! In D99204, @thopre wrote:
>
> With loop peeling, it is important that unnecessary PHIs be avoided or
> it will leads to spurious peeling. One source of such PHIs is loop
> rotation which creates PHIs for invariant loads. Those PHIs are
> particularly problematic since loop peeling is now run as part of simple
> loop unrolling before GVN is run, and are thus a source of spurious
> peeling.
>
> Note that while some of the load can be hoisted and eventually
> eliminated by instruction combine, this is not always possible due to
> alignment issue. In particular, the motivating example [1] was a load
> inside a class instance which cannot be hoisted because the `this'
> pointer has an alignment of 1.
>
> [1] http://lists.llvm.org/pipermail/llvm-dev/attachments/20210312/4ce73c47/attachment.cpp
Now, we could enhance LoopRotate to avoid duplicating code when not needed,
but instead hoist loop-invariant code, but isn't that a code duplication? (*sic*)
We have LICM, and in fact we already run it right after LoopRotation.
We could try to move it to before LoopRotation,
that is basically free from compile-time perspective:
https://llvm-compile-time-tracker.com/compare.php?from=6c93eb4477d88af046b915bc955c03693b2cbb58&to=a4bee6d07732b1184c436da489040b912f0dc271&stat=instructions
But, looking at stats, i think it isn't great that we would no longer do LICM after LoopRotation, in particular:
| statistic name | LoopRotate-LICM | LICM-LoopRotate | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9015799 | -131 | 0.00% | 0.00% |
| indvars.NumElimCmp | 3536 | 3544 | 8 | 0.23% | 0.23% |
| indvars.NumElimExt | 36725 | 36580 | -145 | -0.39% | 0.39% |
| indvars.NumElimIV | 1197 | 1187 | -10 | -0.84% | 0.84% |
| indvars.NumElimIdentity | 143 | 136 | -7 | -4.90% | 4.90% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29890 | 48 | 0.16% | 0.16% |
| indvars.NumReplaced | 2293 | 2227 | -66 | -2.88% | 2.88% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26329 | -109 | -0.41% | 0.41% |
| instcount.TotalBlocks | 1178338 | 1173840 | -4498 | -0.38% | 0.38% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9896139 | -9303 | -0.09% | 0.09% |
| lcssa.NumLCSSA | 425871 | 423961 | -1910 | -0.45% | 0.45% |
| licm.NumHoisted | 378357 | 378753 | 396 | 0.10% | 0.10% |
| licm.NumMovedCalls | 2193 | 2208 | 15 | 0.68% | 0.68% |
| licm.NumMovedLoads | 35899 | 31821 | -4078 | -11.36% | 11.36% |
| licm.NumPromoted | 11178 | 11154 | -24 | -0.21% | 0.21% |
| licm.NumSunk | 13359 | 13587 | 228 | 1.71% | 1.71% |
| loop-delete.NumDeleted | 8547 | 8402 | -145 | -1.70% | 1.70% |
| loop-instsimplify.NumSimplified | 12876 | 11890 | -986 | -7.66% | 7.66% |
| loop-peel.NumPeeled | 1008 | 925 | -83 | -8.23% | 8.23% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42003 | -12 | -0.03% | 0.03% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 242 | 2 | 0.83% | 0.83% |
| loop-simplifycfg.NumLoopExitsDeleted | 497 | 20 | -477 | -95.98% | 95.98% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 336 | -282 | -45.63% | 45.63% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11032 | 4 | 0.04% | 0.04% |
| loop-unroll.NumUnrolled | 12608 | 12529 | -79 | -0.63% | 0.63% |
| mem2reg.NumDeadAlloca | 10222 | 10221 | -1 | -0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192110 | 192106 | -4 | 0.00% | 0.00% |
| mem2reg.NumSingleStore | 637650 | 637643 | -7 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 814 | 812 | -2 | -0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282934 | -174 | -0.06% | 0.06% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106718 | 6 | 0.01% | 0.01% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
... but that actually regresses LICM (-12% `licm.NumMovedLoads`),
loop-simplifycfg (`NumLoopExitsDeleted`, `NumTerminatorsFolded`),
simple-loop-unswitch (`NumTrivial`).
What if we instead have LICM both before and after LoopRotate?
| statistic name | LoopRotate-LICM | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9014474 | -1456 | -0.02% | 0.02% |
| indvars.NumElimCmp | 3536 | 3546 | 10 | 0.28% | 0.28% |
| indvars.NumElimExt | 36725 | 36681 | -44 | -0.12% | 0.12% |
| indvars.NumElimIV | 1197 | 1185 | -12 | -1.00% | 1.00% |
| indvars.NumElimIdentity | 143 | 146 | 3 | 2.10% | 2.10% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29899 | 57 | 0.19% | 0.19% |
| indvars.NumReplaced | 2293 | 2299 | 6 | 0.26% | 0.26% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26404 | -34 | -0.13% | 0.13% |
| instcount.TotalBlocks | 1178338 | 1173652 | -4686 | -0.40% | 0.40% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9895452 | -9990 | -0.10% | 0.10% |
| lcssa.NumLCSSA | 425871 | 425373 | -498 | -0.12% | 0.12% |
| licm.NumHoisted | 378357 | 383352 | 4995 | 1.32% | 1.32% |
| licm.NumMovedCalls | 2193 | 2204 | 11 | 0.50% | 0.50% |
| licm.NumMovedLoads | 35899 | 35755 | -144 | -0.40% | 0.40% |
| licm.NumPromoted | 11178 | 11163 | -15 | -0.13% | 0.13% |
| licm.NumSunk | 13359 | 14321 | 962 | 7.20% | 7.20% |
| loop-delete.NumDeleted | 8547 | 8538 | -9 | -0.11% | 0.11% |
| loop-instsimplify.NumSimplified | 12876 | 12041 | -835 | -6.48% | 6.48% |
| loop-peel.NumPeeled | 1008 | 924 | -84 | -8.33% | 8.33% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42005 | -10 | -0.02% | 0.02% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 241 | 1 | 0.42% | 0.42% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 619 | 1 | 0.16% | 0.16% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11029 | 1 | 0.01% | 0.01% |
| loop-unroll.NumUnrolled | 12608 | 12525 | -83 | -0.66% | 0.66% |
| mem2reg.NumPHIInsert | 192110 | 192073 | -37 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637650 | 637652 | 2 | 0.00% | 0.00% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282998 | -110 | -0.04% | 0.04% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106691 | -21 | -0.02% | 0.02% |
| simple-loop-unswitch.NumBranches | 5178 | 5185 | 7 | 0.14% | 0.14% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 925 | 11 | 1.20% | 1.20% |
| simple-loop-unswitch.NumTrivial | 183 | 179 | -4 | -2.19% | 2.19% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
I.e. we end up with less instructions, less peeling, more LICM activity,
also note how none of those 4 regressions are here. Namely:
| statistic name | LICM-LoopRotate | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015799 | 9014474 | -1325 | -0.01% | 0.01% |
| indvars.NumElimCmp | 3544 | 3546 | 2 | 0.06% | 0.06% |
| indvars.NumElimExt | 36580 | 36681 | 101 | 0.28% | 0.28% |
| indvars.NumElimIV | 1187 | 1185 | -2 | -0.17% | 0.17% |
| indvars.NumElimIdentity | 136 | 146 | 10 | 7.35% | 7.35% |
| indvars.NumLFTR | 29890 | 29899 | 9 | 0.03% | 0.03% |
| indvars.NumReplaced | 2227 | 2299 | 72 | 3.23% | 3.23% |
| indvars.NumWidened | 26329 | 26404 | 75 | 0.28% | 0.28% |
| instcount.TotalBlocks | 1173840 | 1173652 | -188 | -0.02% | 0.02% |
| instcount.TotalInsts | 9896139 | 9895452 | -687 | -0.01% | 0.01% |
| lcssa.NumLCSSA | 423961 | 425373 | 1412 | 0.33% | 0.33% |
| licm.NumHoisted | 378753 | 383352 | 4599 | 1.21% | 1.21% |
| licm.NumMovedCalls | 2208 | 2204 | -4 | -0.18% | 0.18% |
| licm.NumMovedLoads | 31821 | 35755 | 3934 | 12.36% | 12.36% |
| licm.NumPromoted | 11154 | 11163 | 9 | 0.08% | 0.08% |
| licm.NumSunk | 13587 | 14321 | 734 | 5.40% | 5.40% |
| loop-delete.NumDeleted | 8402 | 8538 | 136 | 1.62% | 1.62% |
| loop-instsimplify.NumSimplified | 11890 | 12041 | 151 | 1.27% | 1.27% |
| loop-peel.NumPeeled | 925 | 924 | -1 | -0.11% | 0.11% |
| loop-rotate.NumRotated | 42003 | 42005 | 2 | 0.00% | 0.00% |
| loop-simplifycfg.NumLoopBlocksDeleted | 242 | 241 | -1 | -0.41% | 0.41% |
| loop-simplifycfg.NumLoopExitsDeleted | 20 | 497 | 477 | 2385.00% | 2385.00% |
| loop-simplifycfg.NumTerminatorsFolded | 336 | 619 | 283 | 84.23% | 84.23% |
| loop-unroll.NumCompletelyUnrolled | 11032 | 11029 | -3 | -0.03% | 0.03% |
| loop-unroll.NumUnrolled | 12529 | 12525 | -4 | -0.03% | 0.03% |
| mem2reg.NumDeadAlloca | 10221 | 10222 | 1 | 0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192106 | 192073 | -33 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637643 | 637652 | 9 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 812 | 814 | 2 | 0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 282934 | 282998 | 64 | 0.02% | 0.02% |
| scalar-evolution.NumTripCountsNotComputed | 106718 | 106691 | -27 | -0.03% | 0.03% |
| simple-loop-unswitch.NumBranches | 4752 | 5185 | 433 | 9.11% | 9.11% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 503 | 925 | 422 | 83.90% | 83.90% |
| simple-loop-unswitch.NumSwitches | 18 | 20 | 2 | 11.11% | 11.11% |
| simple-loop-unswitch.NumTrivial | 95 | 179 | 84 | 88.42% | 88.42% |
{F15983613} {F15983615} {F15983616}
(this is vanilla llvm testsuite + rawspeed + darktable)
As an example of the code where early LICM only is bad, see:
https://godbolt.org/z/GzEbacs4K
This does have an observable compile-time regression of +~0.5% geomean
https://llvm-compile-time-tracker.com/compare.php?from=7c5222e4d1a3a14f029e5f614c9aefd0fa505f1e&to=5d81826c3411982ca26e46b9d0aff34c80577664&stat=instructions
but i think that's basically nothing, and there's potential that it might
be avoidable in the future by fixing clang to produce alignment information
on function arguments, thus making the second run unneeded.
Differential Revision: https://reviews.llvm.org/D99249
2021-04-02 09:40:12 +02:00
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Memory SSA
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
[PassManager] Run additional LICM before LoopRotate
Loop rotation often has to perform code duplication
from header into preheader, which introduces PHI nodes.
>>! In D99204, @thopre wrote:
>
> With loop peeling, it is important that unnecessary PHIs be avoided or
> it will leads to spurious peeling. One source of such PHIs is loop
> rotation which creates PHIs for invariant loads. Those PHIs are
> particularly problematic since loop peeling is now run as part of simple
> loop unrolling before GVN is run, and are thus a source of spurious
> peeling.
>
> Note that while some of the load can be hoisted and eventually
> eliminated by instruction combine, this is not always possible due to
> alignment issue. In particular, the motivating example [1] was a load
> inside a class instance which cannot be hoisted because the `this'
> pointer has an alignment of 1.
>
> [1] http://lists.llvm.org/pipermail/llvm-dev/attachments/20210312/4ce73c47/attachment.cpp
Now, we could enhance LoopRotate to avoid duplicating code when not needed,
but instead hoist loop-invariant code, but isn't that a code duplication? (*sic*)
We have LICM, and in fact we already run it right after LoopRotation.
We could try to move it to before LoopRotation,
that is basically free from compile-time perspective:
https://llvm-compile-time-tracker.com/compare.php?from=6c93eb4477d88af046b915bc955c03693b2cbb58&to=a4bee6d07732b1184c436da489040b912f0dc271&stat=instructions
But, looking at stats, i think it isn't great that we would no longer do LICM after LoopRotation, in particular:
| statistic name | LoopRotate-LICM | LICM-LoopRotate | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9015799 | -131 | 0.00% | 0.00% |
| indvars.NumElimCmp | 3536 | 3544 | 8 | 0.23% | 0.23% |
| indvars.NumElimExt | 36725 | 36580 | -145 | -0.39% | 0.39% |
| indvars.NumElimIV | 1197 | 1187 | -10 | -0.84% | 0.84% |
| indvars.NumElimIdentity | 143 | 136 | -7 | -4.90% | 4.90% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29890 | 48 | 0.16% | 0.16% |
| indvars.NumReplaced | 2293 | 2227 | -66 | -2.88% | 2.88% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26329 | -109 | -0.41% | 0.41% |
| instcount.TotalBlocks | 1178338 | 1173840 | -4498 | -0.38% | 0.38% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9896139 | -9303 | -0.09% | 0.09% |
| lcssa.NumLCSSA | 425871 | 423961 | -1910 | -0.45% | 0.45% |
| licm.NumHoisted | 378357 | 378753 | 396 | 0.10% | 0.10% |
| licm.NumMovedCalls | 2193 | 2208 | 15 | 0.68% | 0.68% |
| licm.NumMovedLoads | 35899 | 31821 | -4078 | -11.36% | 11.36% |
| licm.NumPromoted | 11178 | 11154 | -24 | -0.21% | 0.21% |
| licm.NumSunk | 13359 | 13587 | 228 | 1.71% | 1.71% |
| loop-delete.NumDeleted | 8547 | 8402 | -145 | -1.70% | 1.70% |
| loop-instsimplify.NumSimplified | 12876 | 11890 | -986 | -7.66% | 7.66% |
| loop-peel.NumPeeled | 1008 | 925 | -83 | -8.23% | 8.23% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42003 | -12 | -0.03% | 0.03% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 242 | 2 | 0.83% | 0.83% |
| loop-simplifycfg.NumLoopExitsDeleted | 497 | 20 | -477 | -95.98% | 95.98% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 336 | -282 | -45.63% | 45.63% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11032 | 4 | 0.04% | 0.04% |
| loop-unroll.NumUnrolled | 12608 | 12529 | -79 | -0.63% | 0.63% |
| mem2reg.NumDeadAlloca | 10222 | 10221 | -1 | -0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192110 | 192106 | -4 | 0.00% | 0.00% |
| mem2reg.NumSingleStore | 637650 | 637643 | -7 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 814 | 812 | -2 | -0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282934 | -174 | -0.06% | 0.06% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106718 | 6 | 0.01% | 0.01% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
... but that actually regresses LICM (-12% `licm.NumMovedLoads`),
loop-simplifycfg (`NumLoopExitsDeleted`, `NumTerminatorsFolded`),
simple-loop-unswitch (`NumTrivial`).
What if we instead have LICM both before and after LoopRotate?
| statistic name | LoopRotate-LICM | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015930 | 9014474 | -1456 | -0.02% | 0.02% |
| indvars.NumElimCmp | 3536 | 3546 | 10 | 0.28% | 0.28% |
| indvars.NumElimExt | 36725 | 36681 | -44 | -0.12% | 0.12% |
| indvars.NumElimIV | 1197 | 1185 | -12 | -1.00% | 1.00% |
| indvars.NumElimIdentity | 143 | 146 | 3 | 2.10% | 2.10% |
| indvars.NumElimRem | 4 | 5 | 1 | 25.00% | 25.00% |
| indvars.NumLFTR | 29842 | 29899 | 57 | 0.19% | 0.19% |
| indvars.NumReplaced | 2293 | 2299 | 6 | 0.26% | 0.26% |
| indvars.NumSimplifiedSDiv | 6 | 8 | 2 | 33.33% | 33.33% |
| indvars.NumWidened | 26438 | 26404 | -34 | -0.13% | 0.13% |
| instcount.TotalBlocks | 1178338 | 1173652 | -4686 | -0.40% | 0.40% |
| instcount.TotalFuncs | 111825 | 111829 | 4 | 0.00% | 0.00% |
| instcount.TotalInsts | 9905442 | 9895452 | -9990 | -0.10% | 0.10% |
| lcssa.NumLCSSA | 425871 | 425373 | -498 | -0.12% | 0.12% |
| licm.NumHoisted | 378357 | 383352 | 4995 | 1.32% | 1.32% |
| licm.NumMovedCalls | 2193 | 2204 | 11 | 0.50% | 0.50% |
| licm.NumMovedLoads | 35899 | 35755 | -144 | -0.40% | 0.40% |
| licm.NumPromoted | 11178 | 11163 | -15 | -0.13% | 0.13% |
| licm.NumSunk | 13359 | 14321 | 962 | 7.20% | 7.20% |
| loop-delete.NumDeleted | 8547 | 8538 | -9 | -0.11% | 0.11% |
| loop-instsimplify.NumSimplified | 12876 | 12041 | -835 | -6.48% | 6.48% |
| loop-peel.NumPeeled | 1008 | 924 | -84 | -8.33% | 8.33% |
| loop-rotate.NumNotRotatedDueToHeaderSize | 368 | 365 | -3 | -0.82% | 0.82% |
| loop-rotate.NumRotated | 42015 | 42005 | -10 | -0.02% | 0.02% |
| loop-simplifycfg.NumLoopBlocksDeleted | 240 | 241 | 1 | 0.42% | 0.42% |
| loop-simplifycfg.NumTerminatorsFolded | 618 | 619 | 1 | 0.16% | 0.16% |
| loop-unroll.NumCompletelyUnrolled | 11028 | 11029 | 1 | 0.01% | 0.01% |
| loop-unroll.NumUnrolled | 12608 | 12525 | -83 | -0.66% | 0.66% |
| mem2reg.NumPHIInsert | 192110 | 192073 | -37 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637650 | 637652 | 2 | 0.00% | 0.00% |
| scalar-evolution.NumTripCountsComputed | 283108 | 282998 | -110 | -0.04% | 0.04% |
| scalar-evolution.NumTripCountsNotComputed | 106712 | 106691 | -21 | -0.02% | 0.02% |
| simple-loop-unswitch.NumBranches | 5178 | 5185 | 7 | 0.14% | 0.14% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 925 | 11 | 1.20% | 1.20% |
| simple-loop-unswitch.NumTrivial | 183 | 179 | -4 | -2.19% | 2.19% |
| simple-loop-unswitch.NumBranches | 5178 | 4752 | -426 | -8.23% | 8.23% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 914 | 503 | -411 | -44.97% | 44.97% |
| simple-loop-unswitch.NumSwitches | 20 | 18 | -2 | -10.00% | 10.00% |
| simple-loop-unswitch.NumTrivial | 183 | 95 | -88 | -48.09% | 48.09% |
I.e. we end up with less instructions, less peeling, more LICM activity,
also note how none of those 4 regressions are here. Namely:
| statistic name | LICM-LoopRotate | LICM-LoopRotate-LICM | Δ | % | abs(%) |
| asm-printer.EmittedInsts | 9015799 | 9014474 | -1325 | -0.01% | 0.01% |
| indvars.NumElimCmp | 3544 | 3546 | 2 | 0.06% | 0.06% |
| indvars.NumElimExt | 36580 | 36681 | 101 | 0.28% | 0.28% |
| indvars.NumElimIV | 1187 | 1185 | -2 | -0.17% | 0.17% |
| indvars.NumElimIdentity | 136 | 146 | 10 | 7.35% | 7.35% |
| indvars.NumLFTR | 29890 | 29899 | 9 | 0.03% | 0.03% |
| indvars.NumReplaced | 2227 | 2299 | 72 | 3.23% | 3.23% |
| indvars.NumWidened | 26329 | 26404 | 75 | 0.28% | 0.28% |
| instcount.TotalBlocks | 1173840 | 1173652 | -188 | -0.02% | 0.02% |
| instcount.TotalInsts | 9896139 | 9895452 | -687 | -0.01% | 0.01% |
| lcssa.NumLCSSA | 423961 | 425373 | 1412 | 0.33% | 0.33% |
| licm.NumHoisted | 378753 | 383352 | 4599 | 1.21% | 1.21% |
| licm.NumMovedCalls | 2208 | 2204 | -4 | -0.18% | 0.18% |
| licm.NumMovedLoads | 31821 | 35755 | 3934 | 12.36% | 12.36% |
| licm.NumPromoted | 11154 | 11163 | 9 | 0.08% | 0.08% |
| licm.NumSunk | 13587 | 14321 | 734 | 5.40% | 5.40% |
| loop-delete.NumDeleted | 8402 | 8538 | 136 | 1.62% | 1.62% |
| loop-instsimplify.NumSimplified | 11890 | 12041 | 151 | 1.27% | 1.27% |
| loop-peel.NumPeeled | 925 | 924 | -1 | -0.11% | 0.11% |
| loop-rotate.NumRotated | 42003 | 42005 | 2 | 0.00% | 0.00% |
| loop-simplifycfg.NumLoopBlocksDeleted | 242 | 241 | -1 | -0.41% | 0.41% |
| loop-simplifycfg.NumLoopExitsDeleted | 20 | 497 | 477 | 2385.00% | 2385.00% |
| loop-simplifycfg.NumTerminatorsFolded | 336 | 619 | 283 | 84.23% | 84.23% |
| loop-unroll.NumCompletelyUnrolled | 11032 | 11029 | -3 | -0.03% | 0.03% |
| loop-unroll.NumUnrolled | 12529 | 12525 | -4 | -0.03% | 0.03% |
| mem2reg.NumDeadAlloca | 10221 | 10222 | 1 | 0.01% | 0.01% |
| mem2reg.NumPHIInsert | 192106 | 192073 | -33 | -0.02% | 0.02% |
| mem2reg.NumSingleStore | 637643 | 637652 | 9 | 0.00% | 0.00% |
| scalar-evolution.NumBruteForceTripCountsComputed | 812 | 814 | 2 | 0.25% | 0.25% |
| scalar-evolution.NumTripCountsComputed | 282934 | 282998 | 64 | 0.02% | 0.02% |
| scalar-evolution.NumTripCountsNotComputed | 106718 | 106691 | -27 | -0.03% | 0.03% |
| simple-loop-unswitch.NumBranches | 4752 | 5185 | 433 | 9.11% | 9.11% |
| simple-loop-unswitch.NumCostMultiplierSkipped | 503 | 925 | 422 | 83.90% | 83.90% |
| simple-loop-unswitch.NumSwitches | 18 | 20 | 2 | 11.11% | 11.11% |
| simple-loop-unswitch.NumTrivial | 95 | 179 | 84 | 88.42% | 88.42% |
{F15983613} {F15983615} {F15983616}
(this is vanilla llvm testsuite + rawspeed + darktable)
As an example of the code where early LICM only is bad, see:
https://godbolt.org/z/GzEbacs4K
This does have an observable compile-time regression of +~0.5% geomean
https://llvm-compile-time-tracker.com/compare.php?from=7c5222e4d1a3a14f029e5f614c9aefd0fa505f1e&to=5d81826c3411982ca26e46b9d0aff34c80577664&stat=instructions
but i think that's basically nothing, and there's potential that it might
be avoidable in the future by fixing clang to produce alignment information
on function arguments, thus making the second run unneeded.
Differential Revision: https://reviews.llvm.org/D99249
2021-04-02 09:40:12 +02:00
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Loop Invariant Code Motion
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Rotate Loops
|
|
|
|
|
; GCN-O3-NEXT: Loop Invariant Code Motion
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Legacy Divergence Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Unswitch loops
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Recognize loop idioms
|
2020-11-25 17:38:51 +01:00
|
|
|
; GCN-O3-NEXT: Induction Variable Simplification
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Delete dead loops
|
|
|
|
|
; GCN-O3-NEXT: Unroll loops
|
[amdgpu] Run SROA after loop unrolling.
Summary: - There are promotable `alloca`s after loop unrolling.
Reviewers: rampitec, arsenm
Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, kerbowa, nikic, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D84252
2020-07-20 07:09:13 +02:00
|
|
|
; GCN-O3-NEXT: SROA
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: MergedLoadStoreMotion
|
|
|
|
|
; GCN-O3-NEXT: Phi Values Analysis
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Memory Dependence Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Global Value Numbering
|
|
|
|
|
; GCN-O3-NEXT: Sparse Conditional Constant Propagation
|
|
|
|
|
; GCN-O3-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O3-NEXT: Bit-Tracking Dead Code Elimination
|
2021-01-10 10:52:01 +01:00
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Lazy Value Information Analysis
|
|
|
|
|
; GCN-O3-NEXT: Jump Threading
|
|
|
|
|
; GCN-O3-NEXT: Value Propagation
|
2020-10-21 11:21:50 +02:00
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Aggressive Dead Code Elimination
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
2020-09-26 18:56:15 +02:00
|
|
|
; GCN-O3-NEXT: Memory SSA
|
2021-01-10 10:52:01 +01:00
|
|
|
; GCN-O3-NEXT: MemCpy Optimization
|
2021-06-08 22:23:08 +02:00
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
2021-06-20 18:03:30 +02:00
|
|
|
; GCN-O3-NEXT: Dead Store Elimination
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
2020-10-16 09:42:18 +02:00
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
2020-09-16 04:12:10 +02:00
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Loop Invariant Code Motion
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: A No-Op Barrier Pass
|
|
|
|
|
; GCN-O3-NEXT: Eliminate Available Externally Globals
|
|
|
|
|
; GCN-O3-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O3-NEXT: Deduce function attributes in RPO
|
|
|
|
|
; GCN-O3-NEXT: Global Variable Optimizer
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Dead Global Elimination
|
|
|
|
|
; GCN-O3-NEXT: CallGraph Construction
|
|
|
|
|
; GCN-O3-NEXT: Globals Alias Analysis
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Float to int
|
|
|
|
|
; GCN-O3-NEXT: Lower constant intrinsics
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Rotate Loops
|
|
|
|
|
; GCN-O3-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Loop Distribution
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O3-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Inject TLI Mappings
|
|
|
|
|
; GCN-O3-NEXT: Loop Vectorization
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Loop Access Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Load Elimination
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Demanded bits analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Inject TLI Mappings
|
|
|
|
|
; GCN-O3-NEXT: SLP Vectorizer
|
2020-05-22 18:13:18 +02:00
|
|
|
; GCN-O3-NEXT: Optimize scalar/vector ops
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Unroll loops
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Combine redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Memory SSA
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
2020-09-16 04:12:10 +02:00
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Loop Invariant Code Motion
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Warn about non-applied transformations
|
|
|
|
|
; GCN-O3-NEXT: Alignment from assumptions
|
|
|
|
|
; GCN-O3-NEXT: Strip Unused Function Prototypes
|
|
|
|
|
; GCN-O3-NEXT: Dead Global Elimination
|
|
|
|
|
; GCN-O3-NEXT: Merge Duplicate Global Constants
|
[LPM] Port CGProfilePass from NPM to LPM
Reviewers: hans, chandlerc!, asbirlea, nikic
Reviewed By: hans, nikic
Subscribers: steven_wu, dexonsmith, nikic, echristo, void, zhizhouy, cfe-commits, aeubanks, MaskRay, jvesely, nhaehnle, hiraditya, kerbowa, llvm-commits
Tags: #llvm, #clang
Differential Revision: https://reviews.llvm.org/D83013
2020-07-08 21:30:28 +02:00
|
|
|
; GCN-O3-NEXT: Call Graph Profile
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
2020-05-21 20:58:35 +02:00
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Canonicalize natural loops
|
|
|
|
|
; GCN-O3-NEXT: LCSSA Verifier
|
|
|
|
|
; GCN-O3-NEXT: Loop-Closed SSA Form Pass
|
|
|
|
|
; GCN-O3-NEXT: Basic Alias Analysis (stateless AA impl)
|
|
|
|
|
; GCN-O3-NEXT: Function Alias Analysis Results
|
|
|
|
|
; GCN-O3-NEXT: Scalar Evolution Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Loop Pass Manager
|
|
|
|
|
; GCN-O3-NEXT: Loop Sink
|
|
|
|
|
; GCN-O3-NEXT: Lazy Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Lazy Block Frequency Analysis
|
|
|
|
|
; GCN-O3-NEXT: Optimization Remark Emitter
|
|
|
|
|
; GCN-O3-NEXT: Remove redundant instructions
|
|
|
|
|
; GCN-O3-NEXT: Hoist/decompose integer division and remainder
|
|
|
|
|
; GCN-O3-NEXT: Simplify the CFG
|
2020-11-13 10:46:55 +01:00
|
|
|
; GCN-O3-NEXT: Annotation Remarks
|
2020-05-21 20:58:35 +02:00
|
|
|
|
|
|
|
|
; GCN-O3-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
|
|
|
|
|
; GCN-O3-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
|
|
|
|
|
; GCN-O3-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O3-NEXT: Target Library Information
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
|
|
|
|
|
; GCN-O3-NEXT: Pass Arguments:
|
|
|
|
|
; GCN-O3-NEXT: Target Library Information
|
|
|
|
|
; GCN-O3-NEXT: FunctionPass Manager
|
|
|
|
|
; GCN-O3-NEXT: Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Natural Loop Information
|
|
|
|
|
; GCN-O3-NEXT: Post-Dominator Tree Construction
|
|
|
|
|
; GCN-O3-NEXT: Branch Probability Analysis
|
|
|
|
|
; GCN-O3-NEXT: Block Frequency Analysis
|
|
|
|
|
|
|
|
|
|
define void @empty() {
|
|
|
|
|
ret void
|
|
|
|
|
}
|
