0338c55ea5
The transform updates all users of inductions to work based on EVL, instead of the VF directly. At the moment, widened inductions cannot be updated, so bail out if the plan contains any. This patch introduces a check before applying EVL transform. If any recipes in loop rely on RuntimeVF, the plan is discarded.
71 lines
3.1 KiB
LLVM
71 lines
3.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
|
|
; RUN: opt -passes=loop-vectorize -force-tail-folding-style=data-with-evl \
|
|
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
|
|
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck %s
|
|
|
|
; Make sure we do not vectorize a loop with a widened int induction.
|
|
define void @test_wide_integer_induction(ptr noalias %a, i64 %N) {
|
|
; CHECK-LABEL: define void @test_wide_integer_induction(
|
|
; CHECK-SAME: ptr noalias [[A:%.*]], i64 [[N:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[IV]]
|
|
; CHECK-NEXT: store i64 [[IV]], ptr [[ARRAYIDX]], align 8
|
|
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
|
|
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
|
|
store i64 %iv, ptr %arrayidx, align 8
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv.next, %N
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|
|
|
|
; Make sure we do not vectorize a loop with a widened ptr induction.
|
|
define void @test_wide_ptr_induction(ptr noalias %a, ptr noalias %b, i64 %N) {
|
|
; CHECK-LABEL: define void @test_wide_ptr_induction(
|
|
; CHECK-SAME: ptr noalias [[A:%.*]], ptr noalias [[B:%.*]], i64 [[N:%.*]]) #[[ATTR0]] {
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
|
|
; CHECK: for.body:
|
|
; CHECK-NEXT: [[EVL_BASED_IV:%.*]] = phi i64 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_EVL_NEXT:%.*]], [[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[ADDR:%.*]] = phi ptr [ [[INCDEC_PTR:%.*]], [[VECTOR_BODY]] ], [ [[B]], [[VECTOR_PH]] ]
|
|
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[ADDR]], i64 8
|
|
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i64, ptr [[A]], i64 [[EVL_BASED_IV]]
|
|
; CHECK-NEXT: store ptr [[ADDR]], ptr [[ARRAYIDX]], align 8
|
|
; CHECK-NEXT: [[INDEX_EVL_NEXT]] = add nuw nsw i64 [[EVL_BASED_IV]], 1
|
|
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDEX_EVL_NEXT]], [[N]]
|
|
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[VECTOR_BODY]]
|
|
; CHECK: for.cond.cleanup:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%addr = phi ptr [ %incdec.ptr, %for.body ], [ %b, %entry ]
|
|
%incdec.ptr = getelementptr inbounds i8, ptr %addr, i64 8
|
|
%arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
|
|
store ptr %addr, ptr %arrayidx, align 8
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv.next, %N
|
|
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
|
|
|
|
for.cond.cleanup:
|
|
ret void
|
|
}
|