462cb3cd6c
If the gep is nusw (usually via inbounds) and the offset is non-negative, we can infer nuw. Proof: https://alive2.llvm.org/ce/z/ihztLy
111 lines
5.5 KiB
LLVM
111 lines
5.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=loop-vectorize,instcombine -force-vector-width=4 -force-vector-interleave=1 -S | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
|
|
|
|
;
|
|
define void @vector_gep_stored(ptr %a, ptr %b, i64 %n) {
|
|
; CHECK-LABEL: @vector_gep_stored(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[SMAX:%.*]] = call i64 @llvm.smax.i64(i64 [[N:%.*]], i64 1)
|
|
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp slt i64 [[N]], 4
|
|
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[SMAX]], 9223372036854775804
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: vector.body:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], <4 x i64> [[VEC_IND]]
|
|
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds ptr, ptr [[A:%.*]], i64 [[INDEX]]
|
|
; CHECK-NEXT: store <4 x ptr> [[TMP0]], ptr [[TMP1]], align 8
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4)
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
|
|
; CHECK-NEXT: br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[SMAX]], [[N_VEC]]
|
|
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
|
|
; CHECK-NEXT: [[VAR0:%.*]] = getelementptr inbounds nuw i32, ptr [[B]], i64 [[I]]
|
|
; CHECK-NEXT: [[VAR1:%.*]] = getelementptr inbounds nuw ptr, ptr [[A]], i64 [[I]]
|
|
; CHECK-NEXT: store ptr [[VAR0]], ptr [[VAR1]], align 8
|
|
; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
|
|
; CHECK-NEXT: br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP3:![0-9]+]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
|
|
%var0 = getelementptr inbounds i32, ptr %b, i64 %i
|
|
%var1 = getelementptr inbounds ptr, ptr %a, i64 %i
|
|
store ptr %var0, ptr %var1, align 8
|
|
%i.next = add nuw nsw i64 %i, 1
|
|
%cond = icmp slt i64 %i.next, %n
|
|
br i1 %cond, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
;
|
|
define void @uniform_vector_gep_stored(ptr %a, ptr %b, i64 %n) {
|
|
; CHECK-LABEL: @uniform_vector_gep_stored(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: [[SMAX:%.*]] = call i64 @llvm.smax.i64(i64 [[N:%.*]], i64 1)
|
|
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp slt i64 [[N]], 4
|
|
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
|
|
; CHECK: vector.ph:
|
|
; CHECK-NEXT: [[N_VEC:%.*]] = and i64 [[SMAX]], 9223372036854775804
|
|
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds nuw i8, ptr [[B:%.*]], i64 4
|
|
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
|
|
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <4 x ptr> [[DOTSPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
|
|
; 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 [[A:%.*]], i64 [[INDEX]]
|
|
; CHECK-NEXT: store <4 x ptr> [[DOTSPLAT]], ptr [[TMP1]], align 8
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
|
|
; CHECK-NEXT: br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
; CHECK: middle.block:
|
|
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[SMAX]], [[N_VEC]]
|
|
; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
|
|
; CHECK: scalar.ph:
|
|
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
|
|
; CHECK-NEXT: [[VAR0:%.*]] = getelementptr inbounds nuw i8, ptr [[B]], i64 4
|
|
; CHECK-NEXT: [[VAR1:%.*]] = getelementptr inbounds nuw ptr, ptr [[A]], i64 [[I]]
|
|
; CHECK-NEXT: store ptr [[VAR0]], ptr [[VAR1]], align 8
|
|
; CHECK-NEXT: [[I_NEXT]] = add nuw nsw i64 [[I]], 1
|
|
; CHECK-NEXT: [[COND:%.*]] = icmp slt i64 [[I_NEXT]], [[N]]
|
|
; CHECK-NEXT: br i1 [[COND]], label [[FOR_BODY]], label [[FOR_END]], !llvm.loop [[LOOP5:![0-9]+]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i = phi i64 [ %i.next, %for.body ], [ 0, %entry ]
|
|
%var0 = getelementptr inbounds i32, ptr %b, i64 1
|
|
%var1 = getelementptr inbounds ptr, ptr %a, i64 %i
|
|
store ptr %var0, ptr %var1, align 8
|
|
%i.next = add nuw nsw i64 %i, 1
|
|
%cond = icmp slt i64 %i.next, %n
|
|
br i1 %cond, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|