89ae085859
VPVectorPointer for part 0 is just the pointer operand. Simplify it after unrolling. This removes a large number of redundant GEPs with index 0. PR: https://github.com/llvm/llvm-project/pull/149735
62 lines
2.8 KiB
LLVM
62 lines
2.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
|
|
; RUN: opt -p loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -S < %s | FileCheck %s
|
|
|
|
define void @neg_cond(ptr noalias %p, ptr noalias %q) {
|
|
; CHECK-LABEL: define void @neg_cond(
|
|
; CHECK-SAME: ptr noalias [[P:%.*]], ptr noalias [[Q:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*]]:
|
|
; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
|
|
; CHECK: [[VECTOR_PH]]:
|
|
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
|
|
; CHECK: [[VECTOR_BODY]]:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i32, ptr [[P]], i32 [[INDEX]]
|
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP0]], align 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp ne <4 x i32> [[WIDE_LOAD]], splat (i32 42)
|
|
; CHECK-NEXT: [[TMP4:%.*]] = select <4 x i1> [[TMP3]], <4 x i32> splat (i32 42), <4 x i32> splat (i32 43)
|
|
; CHECK-NEXT: store <4 x i32> [[TMP4]], ptr [[TMP0]], align 4
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP5:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
|
|
; CHECK-NEXT: br i1 [[TMP5]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: [[MIDDLE_BLOCK]]:
|
|
; CHECK-NEXT: br label %[[EXIT:.*]]
|
|
; CHECK: [[SCALAR_PH]]:
|
|
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 0, %[[ENTRY]] ]
|
|
; CHECK-NEXT: br label %[[LOOP:.*]]
|
|
; CHECK: [[LOOP]]:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
|
|
; CHECK-NEXT: [[P_GEP:%.*]] = getelementptr i32, ptr [[P]], i32 [[IV]]
|
|
; CHECK-NEXT: [[X:%.*]] = load i32, ptr [[P_GEP]], align 4
|
|
; CHECK-NEXT: [[Q_GEP:%.*]] = getelementptr i32, ptr [[Q]], i32 [[IV]]
|
|
; CHECK-NEXT: [[Y:%.*]] = load i32, ptr [[Q_GEP]], align 4
|
|
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[X]], 42
|
|
; CHECK-NEXT: [[NOT:%.*]] = xor i1 [[CMP]], true
|
|
; CHECK-NEXT: [[SEL:%.*]] = select i1 [[NOT]], i32 42, i32 43
|
|
; CHECK-NEXT: store i32 [[SEL]], ptr [[P_GEP]], align 4
|
|
; CHECK-NEXT: [[IV_NEXT]] = add i32 [[IV]], 1
|
|
; CHECK-NEXT: [[DONE:%.*]] = icmp eq i32 [[IV_NEXT]], 1024
|
|
; CHECK-NEXT: br i1 [[DONE]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i32 [0, %entry], [%iv.next, %loop]
|
|
%p.gep = getelementptr i32, ptr %p, i32 %iv
|
|
%x = load i32, ptr %p.gep
|
|
%q.gep = getelementptr i32, ptr %q, i32 %iv
|
|
%y = load i32, ptr %q.gep
|
|
%cmp = icmp eq i32 %x, 42
|
|
%not = xor i1 %cmp, 1
|
|
%sel = select i1 %not, i32 42, i32 43
|
|
store i32 %sel, ptr %p.gep
|
|
%iv.next = add i32 %iv, 1
|
|
%done = icmp eq i32 %iv.next, 1024
|
|
br i1 %done, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|