fix #17098, bad codegen from too many i1 casts #17225
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This affected code using tuples of Bools. Previously, we always represented Bool as i1 except in storage. Now we represent Bool as i8 most of the time, and truncate to i1 only just before use in branches.
|
lgtm. this definitely seems like it'll be simpler |
|
So does this mean people could hide payloads in the upper bits of julia bools? |
|
As part of this, it might be worth reverting #16687 and running nanosoldier. |
|
Yes, I guess you could hide payloads. We could stop that pretty easily I think by zeroing the top bits whenever something is reinterpreted to Bool. However for now we need this performance. |
|
This seems to have also fixed the SIMD regression caused by bd06d27. Not sure why it broke in the first place though.... |
|
Should we do another nanosoldier run against 0.4? |
earl
pushed a commit
to earl/llvm-mirror
that referenced
this pull request
Jul 19, 2016
Summary: Currently, InstCombine is already able to fold expressions of the form `logic(cast(A), cast(B))` to the simpler form `cast(logic(A, B))`, where logic designates one of `and`/`or`/`xor`. This transformation is implemented in `foldCastedBitwiseLogic()` in InstCombineAndOrXor.cpp. However, this optimization will not be performed if both `A` and `B` are `icmp` instructions. The decision to preclude casts of `icmp` instructions originates in r48715 in combination with r261707, and can be best understood by the title of the former one: > Transform (zext (or (icmp), (icmp))) to (or (zext (cimp), (zext icmp))) if at least one of the (zext icmp) can be transformed to eliminate an icmp. Apparently, it introduced a transformation that is a reverse of the transformation that is done in `foldCastedBitwiseLogic()`. Its purpose is to expose pairs of `zext icmp` that would subsequently be optimized by `transformZExtICmp()` in InstCombineCasts.cpp. Therefore, in order to avoid an endless loop of switching back and forth between these two transformations, the one in `foldCastedBitwiseLogic()` has been restricted to exclude `icmp` instructions which is mirrored in the responsible check: `if ((!isa<ICmpInst>(Cast0Src) || !isa<ICmpInst>(Cast1Src)) && ...` This check seems to sort out more cases than necessary because: - the reverse transformation is obviously done for `or` instructions only - and also not every `zext icmp` pair is necessarily the result of this reverse transformation Therefore we now remove this check and replace it by a more finegrained one in `shouldOptimizeCast()` that now rejects only those `logic(zext(icmp), zext(icmp))` that would be able to be optimized by `transformZExtICmp()`, which also avoids the mentioned endless loop. That means we are now able to also simplify expressions of the form `logic(cast(icmp), cast(icmp))` to `cast(logic(icmp, icmp))` (`cast` being an arbitrary `CastInst`). As an example, consider the following IR snippet ``` %1 = icmp sgt i64 %a, %b %2 = zext i1 %1 to i8 %3 = icmp slt i64 %a, %c %4 = zext i1 %3 to i8 %5 = and i8 %2, %4 ``` which would now be transformed to ``` %1 = icmp sgt i64 %a, %b %2 = icmp slt i64 %a, %c %3 = and i1 %1, %2 %4 = zext i1 %3 to i8 ``` This issue became apparent when experimenting with the programming language Julia, which makes use of LLVM. Currently, Julia lowers its `Bool` datatype to LLVM's `i8` (also see JuliaLang/julia#17225). In fact, the above IR example is the lowered form of the Julia snippet `(a > b) & (a < c)`. Like shown above, this may introduce `zext` operations, casting between `i1` and `i8`, which could for example hinder ScalarEvolution and Polly on certain code. Reviewers: grosser, vtjnash, majnemer Subscribers: majnemer, llvm-commits Differential Revision: https://reviews.llvm.org/D22511 Contributed-by: Matthias Reisinger git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275989 91177308-0d34-0410-b5e6-96231b3b80d8
trombonehero
pushed a commit
to cadets/llvm
that referenced
this pull request
Jul 21, 2016
Summary: Currently, InstCombine is already able to fold expressions of the form `logic(cast(A), cast(B))` to the simpler form `cast(logic(A, B))`, where logic designates one of `and`/`or`/`xor`. This transformation is implemented in `foldCastedBitwiseLogic()` in InstCombineAndOrXor.cpp. However, this optimization will not be performed if both `A` and `B` are `icmp` instructions. The decision to preclude casts of `icmp` instructions originates in r48715 in combination with r261707, and can be best understood by the title of the former one: > Transform (zext (or (icmp), (icmp))) to (or (zext (cimp), (zext icmp))) if at least one of the (zext icmp) can be transformed to eliminate an icmp. Apparently, it introduced a transformation that is a reverse of the transformation that is done in `foldCastedBitwiseLogic()`. Its purpose is to expose pairs of `zext icmp` that would subsequently be optimized by `transformZExtICmp()` in InstCombineCasts.cpp. Therefore, in order to avoid an endless loop of switching back and forth between these two transformations, the one in `foldCastedBitwiseLogic()` has been restricted to exclude `icmp` instructions which is mirrored in the responsible check: `if ((!isa<ICmpInst>(Cast0Src) || !isa<ICmpInst>(Cast1Src)) && ...` This check seems to sort out more cases than necessary because: - the reverse transformation is obviously done for `or` instructions only - and also not every `zext icmp` pair is necessarily the result of this reverse transformation Therefore we now remove this check and replace it by a more finegrained one in `shouldOptimizeCast()` that now rejects only those `logic(zext(icmp), zext(icmp))` that would be able to be optimized by `transformZExtICmp()`, which also avoids the mentioned endless loop. That means we are now able to also simplify expressions of the form `logic(cast(icmp), cast(icmp))` to `cast(logic(icmp, icmp))` (`cast` being an arbitrary `CastInst`). As an example, consider the following IR snippet ``` %1 = icmp sgt i64 %a, %b %2 = zext i1 %1 to i8 %3 = icmp slt i64 %a, %c %4 = zext i1 %3 to i8 %5 = and i8 %2, %4 ``` which would now be transformed to ``` %1 = icmp sgt i64 %a, %b %2 = icmp slt i64 %a, %c %3 = and i1 %1, %2 %4 = zext i1 %3 to i8 ``` This issue became apparent when experimenting with the programming language Julia, which makes use of LLVM. Currently, Julia lowers its `Bool` datatype to LLVM's `i8` (also see JuliaLang/julia#17225). In fact, the above IR example is the lowered form of the Julia snippet `(a > b) & (a < c)`. Like shown above, this may introduce `zext` operations, casting between `i1` and `i8`, which could for example hinder ScalarEvolution and Polly on certain code. Reviewers: grosser, vtjnash, majnemer Subscribers: majnemer, llvm-commits Differential Revision: https://reviews.llvm.org/D22511 Contributed-by: Matthias Reisinger git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@275989 91177308-0d34-0410-b5e6-96231b3b80d8
mfasi
pushed a commit
to mfasi/julia
that referenced
this pull request
Sep 5, 2016
This reverts commit 526695c. Jeff's fix to codegen on Bools, JuliaLang#17225, should make this unnecessary.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Previously, we always represented Bool as i1 except in storage. Now we represent Bool as i8 most of the time, and truncate to i1 only just before use in branches.