df387661c4
If I understand correctly there was a point where we used to need this before it was implied by Zvl*b. Now that it is though and we use -mattr=+v in pretty much every test we can remove it. In unroll-in-loop-vectorizer.ll we can force a VF of 1 instead by using -force-vector-width=1, and in scalable-basics.ll the two RUN lines were the same so I merged them.
44 lines
1.8 KiB
LLVM
44 lines
1.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -mtriple=riscv64 -mattr=+v -passes=loop-vectorize -scalable-vectorization=off -force-vector-width=1 < %s | FileCheck %s
|
|
|
|
; Make sure we don't unroll scalar loops in the loop vectorizer.
|
|
;
|
|
define void @small_loop(ptr 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, ptr [[INARRAY:%.*]], i32 [[IV]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[TMP1]], align 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = add nsw i32 [[TMP2]], 6
|
|
; CHECK-NEXT: store i32 [[TMP3]], ptr [[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, ptr %inArray, i32 %iv
|
|
%2 = load i32, ptr %1, align 4
|
|
%3 = add nsw i32 %2, 6
|
|
store i32 %3, ptr %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
|
|
}
|