mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-09-28 07:17:32 +00:00
7d4d116067
Summary:
Make Scalar Evolution able to propagate NSW and NUW flags from instructions to SCEVs in some cases. This is based on reasoning about when poison from instructions with these flags would trigger undefined behavior. This gives a 13% speed-up on some Eigen3-based Google-internal microbenchmarks for NVPTX.
There does not seem to be clear agreement about when poison should be considered to propagate through instructions. In this analysis, poison propagates only in cases where that should be uncontroversial.
This change makes LSR able to create induction variables for expressions like &ptr[i + offset] for loops like this:
for (int i = 0; i < limit; ++i) {
sum += ptr[i + offset];
}
Here ptr is a 64 bit pointer and offset is a 32 bit integer. For NVPTX, LSR currently creates an induction variable for i + offset instead, which is not as fast. Improving this situation is what brings the 13% speed-up on some Eigen3-based Google-internal microbenchmarks for NVPTX.
There are more details in this discussion on llvmdev.
June: http://lists.cs.uiuc.edu/pipermail/llvmdev/2015-June/thread.html#87234
July: http://lists.cs.uiuc.edu/pipermail/llvmdev/2015-July/thread.html#87392
Patch by Bjarke Roune
Reviewers: eliben, atrick, sanjoy
Subscribers: majnemer, hfinkel, jingyue, meheff, llvm-commits
Differential Revision: http://reviews.llvm.org/D11212
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@243460 91177308-0d34-0410-b5e6-96231b3b80d8
37 lines
1.1 KiB
LLVM
37 lines
1.1 KiB
LLVM
; RUN: opt -loop-reduce -S < %s | FileCheck %s
|
|
|
|
target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
|
|
target triple = "nvptx64-unknown-unknown"
|
|
|
|
; LSR used not to be able to generate a float* induction variable in
|
|
; these cases due to scalar evolution not propagating nsw from an
|
|
; instruction to the SCEV, preventing distributing sext into the
|
|
; corresponding addrec.
|
|
|
|
define float @testadd(float* %input, i32 %offset, i32 %numIterations) {
|
|
; CHECK-LABEL: @testadd
|
|
; CHECK: sext i32 %offset to i64
|
|
; CHECK: loop:
|
|
; CHECK-DAG: phi float*
|
|
; CHECK-DAG: phi i32
|
|
; CHECK-NOT: sext
|
|
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%i = phi i32 [ %nexti, %loop ], [ 0, %entry ]
|
|
%sum = phi float [ %nextsum, %loop ], [ 0.000000e+00, %entry ]
|
|
%index32 = add nuw nsw i32 %i, %offset
|
|
%index64 = sext i32 %index32 to i64
|
|
%ptr = getelementptr inbounds float, float* %input, i64 %index64
|
|
%addend = load float, float* %ptr, align 4
|
|
%nextsum = fadd float %sum, %addend
|
|
%nexti = add nuw nsw i32 %i, 1
|
|
%exitcond = icmp eq i32 %nexti, %numIterations
|
|
br i1 %exitcond, label %exit, label %loop
|
|
|
|
exit:
|
|
ret float %nextsum
|
|
}
|