50b9ca4dda
After https://github.com/llvm/llvm-project/pull/153643, there may be a BranchOnCond with constant condition in the entry block. Simplify those in removeBranchOnConst. This removes a number of redundant conditional branch from entry blocks. In some cases, it may also make the original scalar loop unreachable, because we know it will never execute. In that case, we need to remove the loop from LoopInfo, because all unreachable blocks may dominate each other, making LoopInfo invalid. In those cases, we can also completely remove the loop, for which I'll share a follow-up patch. Depends on https://github.com/llvm/llvm-project/pull/153643. PR: https://github.com/llvm/llvm-project/pull/154510
106 lines
4.4 KiB
LLVM
106 lines
4.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -mtriple=s390x-unknown-linux -mcpu=z13 -passes=loop-vectorize,dce,instcombine -force-vector-width=2 < %s | FileCheck %s
|
|
;
|
|
; Test that loop vectorizer does not generate vector addresses that must then
|
|
; always be extracted.
|
|
|
|
; Check that the addresses for a scalarized memory access is not extracted
|
|
; from a vector register.
|
|
define i32 @foo(ptr nocapture %A) {
|
|
; CHECK-LABEL: @foo(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[DOTIDX:%.*]] = shl nsw i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[A:%.*]], i64 [[DOTIDX]]
|
|
; CHECK-NEXT: [[DOTIDX1:%.*]] = shl i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, ptr [[A]], i64 [[DOTIDX1]]
|
|
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr i8, ptr [[TMP1]], i64 16
|
|
; CHECK-NEXT: store i32 4, ptr [[TMP2]], align 4
|
|
; CHECK-NEXT: store i32 4, ptr [[TMP3]], align 4
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 10000
|
|
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br label [[FOR_END:%.*]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: br i1 poison, label [[FOR_END]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret i32 poison
|
|
;
|
|
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%0 = shl nsw i64 %indvars.iv, 2
|
|
%arrayidx = getelementptr inbounds i32, ptr %A, i64 %0
|
|
store i32 4, ptr %arrayidx, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 10000
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret i32 poison
|
|
}
|
|
|
|
|
|
; Check that a load of address is scalarized.
|
|
define i32 @foo1(ptr nocapture noalias %A, ptr nocapture %PtrPtr) {
|
|
; CHECK-LABEL: @foo1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds ptr, ptr [[PTRPTR:%.*]], i64 [[INDEX]]
|
|
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr ptr, ptr [[PTRPTR]], i64 [[INDEX]]
|
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i8, ptr [[TMP11]], i64 8
|
|
; CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TMP1]], align 8
|
|
; CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TMP2]], align 8
|
|
; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[TMP3]], align 4
|
|
; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr [[TMP4]], align 4
|
|
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP5]], i64 0
|
|
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP6]], i64 1
|
|
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[INDEX]]
|
|
; CHECK-NEXT: store <2 x i32> [[TMP8]], ptr [[TMP9]], align 4
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
|
|
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 10000
|
|
; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: br label [[FOR_END:%.*]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: br i1 poison, label [[FOR_END]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret i32 poison
|
|
;
|
|
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%ptr = getelementptr inbounds ptr, ptr %PtrPtr, i64 %indvars.iv
|
|
%el = load ptr, ptr %ptr
|
|
%v = load i32, ptr %el
|
|
%arrayidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
|
|
store i32 %v, ptr %arrayidx, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 10000
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret i32 poison
|
|
}
|