diff options
author | Philip Reames <listmail@philipreames.com> | 2021-11-12 11:35:28 -0800 |
---|---|---|
committer | Philip Reames <listmail@philipreames.com> | 2021-11-12 11:40:50 -0800 |
commit | de2fed61528a5584dc54c47f6754408597be24de (patch) | |
tree | 03f77d24f1f978894205a5d88c4566e1c120c70c /llvm/lib/Transforms/Utils/LoopUnroll.cpp | |
parent | da25f968a90ad4560fc920a6d18fc2a0221d2750 (diff) | |
download | llvm-de2fed61528a5584dc54c47f6754408597be24de.zip llvm-de2fed61528a5584dc54c47f6754408597be24de.tar.gz llvm-de2fed61528a5584dc54c47f6754408597be24de.tar.bz2 |
[unroll] Keep unrolled iterations with initial iteration
The unrolling code was previously inserting new cloned blocks at the end of the function. The result of this with typical loop structures is that the new iterations are placed far from the initial iteration.
With unrolling, the general assumption is that the a) the loop is reasonable hot, and b) the first Count-1 copies of the loop are rarely (if ever) loop exiting. As such, placing Count-1 copies out of line is a fairly poor code placement choice. We'd much rather fall through into the hot (non-exiting) path. For code with branch profiles, later layout would fix this, but this may have a positive impact on non-PGO compiled code.
However, the real motivation for this change isn't performance. Its readability and human understanding. Having to jump around long distances in an IR file to trace an unrolled loop structure is error prone and tedious.
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUnroll.cpp')
-rw-r--r-- | llvm/lib/Transforms/Utils/LoopUnroll.cpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/llvm/lib/Transforms/Utils/LoopUnroll.cpp b/llvm/lib/Transforms/Utils/LoopUnroll.cpp index ce46392..b0c622b 100644 --- a/llvm/lib/Transforms/Utils/LoopUnroll.cpp +++ b/llvm/lib/Transforms/Utils/LoopUnroll.cpp @@ -514,6 +514,10 @@ LoopUnrollResult llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI, SmallVector<MDNode *, 6> LoopLocalNoAliasDeclScopes; identifyNoAliasScopesToClone(L->getBlocks(), LoopLocalNoAliasDeclScopes); + // We place the unrolled iterations immediately after the original loop + // latch. This is a reasonable default placement if we don't have block + // frequencies, and if we do, well the layout will be adjusted later. + auto BlockInsertPt = std::next(LatchBlock->getIterator()); for (unsigned It = 1; It != ULO.Count; ++It) { SmallVector<BasicBlock *, 8> NewBlocks; SmallDenseMap<const Loop *, Loop *, 4> NewLoops; @@ -522,7 +526,7 @@ LoopUnrollResult llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI, for (LoopBlocksDFS::RPOIterator BB = BlockBegin; BB != BlockEnd; ++BB) { ValueToValueMapTy VMap; BasicBlock *New = CloneBasicBlock(*BB, VMap, "." + Twine(It)); - Header->getParent()->getBasicBlockList().push_back(New); + Header->getParent()->getBasicBlockList().insert(BlockInsertPt, New); assert((*BB != Header || LI->getLoopFor(*BB) == L) && "Header should not be in a sub-loop"); |