maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[RISCV] Disable interleaving scalar loops in the loop vectorizer. 

The loop vectorizer can interleave scalar loops even if it doesn't
vectorize them. I don't believe we intended to enable this when
we enabled interleaving for vector instructions.

Disable interleaving for VF=1 like X86 and AMDGPU already do. Test
lifted from AMDGPU.

Differential Revision: https://reviews.llvm.org/D115975
This commit is contained in:
Craig Topper 2021-12-23 08:11:09 -06:00
parent a3f50fb06d
commit a9486a40f7
2 changed files with 46 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/RISCV/RISCVTargetTransformInfo.h
View File

@ -185,7 +185,9 @@ public:
}
unsigned getMaxInterleaveFactor(unsigned VF) {
return ST->getMaxInterleaveFactor();
// If the loop will not be vectorized, don't interleave the loop.
// Let regular unroll to unroll the loop.
return VF == 1 ? 1 : ST->getMaxInterleaveFactor();
}
};

43
llvm/test/Transforms/LoopVectorize/RISCV/unroll-in-loop-vectorizer.ll Normal file
View File

@ -0,0 +1,43 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=riscv64 -mattr=+experimental-v -loop-vectorize < %s | FileCheck %s
; Make sure we don't unroll scalar loops in the loop vectorizer.
;
define void @small_loop(i32* nocapture %inArray, i32 %size) nounwind {
; CHECK-LABEL: @small_loop(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp sgt i32 [[SIZE:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[LOOP_PREHEADER:%.*]], label [[EXIT:%.*]]
; CHECK: loop.preheader:
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[IV1:%.*]], [[LOOP]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[INARRAY:%.*]], i32 [[IV]]
; CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = add nsw i32 [[TMP2]], 6
; CHECK-NEXT: store i32 [[TMP3]], i32* [[TMP1]], align 4
; CHECK-NEXT: [[IV1]] = add i32 [[IV]], 1
; CHECK-NEXT: [[COND:%.*]] = icmp eq i32 [[IV1]], [[SIZE]]
; CHECK-NEXT: br i1 [[COND]], label [[EXIT_LOOPEXIT:%.*]], label [[LOOP]]
; CHECK: exit.loopexit:
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
%0 = icmp sgt i32 %size, 0
br i1 %0, label %loop, label %exit
loop: ; preds = %entry, %loop
%iv = phi i32 [ %iv1, %loop ], [ 0, %entry ]
%1 = getelementptr inbounds i32, i32* %inArray, i32 %iv
%2 = load i32, i32* %1, align 4
%3 = add nsw i32 %2, 6
store i32 %3, i32* %1, align 4
%iv1 = add i32 %iv, 1
%cond = icmp eq i32 %iv1, %size
br i1 %cond, label %exit, label %loop
exit: ; preds = %loop, %entry
ret void
}