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
64 lines
2.9 KiB
LLVM
64 lines
2.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: opt < %s -passes=loop-vectorize,dce,instcombine -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s
|
|
|
|
; From a simple program with two address spaces:
|
|
; char Y[4*10000] __attribute__((address_space(1)));
|
|
; char X[4*10000];
|
|
; int main() {
|
|
; for (int i = 0; i < 4*10000; ++i)
|
|
; X[i] = Y[i] + 1;
|
|
; return 0;
|
|
;}
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
@Y = common addrspace(1) global [40000 x i8] zeroinitializer, align 16
|
|
@X = common global [40000 x i8] zeroinitializer, align 16
|
|
|
|
define i32 @main() #0 {
|
|
; CHECK-LABEL: define i32 @main
|
|
; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
|
|
; 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: [[TMP0:%.*]] = getelementptr inbounds i8, ptr addrspace(1) @Y, i64 [[INDEX]]
|
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr addrspace(1) [[TMP0]], align 1
|
|
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i8> [[WIDE_LOAD]], splat (i8 1)
|
|
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr @X, i64 [[INDEX]]
|
|
; CHECK-NEXT: store <4 x i8> [[TMP1]], ptr [[TMP2]], align 1
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 40000
|
|
; CHECK-NEXT: br i1 [[TMP3]], 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 0
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds [40000 x i8], ptr addrspace(1) @Y, i64 0, i64 %indvars.iv
|
|
%0 = load i8, ptr addrspace(1) %arrayidx, align 1
|
|
%add = add i8 %0, 1
|
|
%arrayidx3 = getelementptr inbounds [40000 x i8], ptr @X, i64 0, i64 %indvars.iv
|
|
store i8 %add, ptr %arrayidx3, align 1
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 40000
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret i32 0
|
|
}
|
|
|
|
attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
|