59728193a6
Fixed length vectors use scalable vector containers. With Zve32* and not Zvl64b, vscale is a 0.5 due RVVBitsPerBlock being 64. To support this correctly we need to lower RVVBitsPerBlock to 32 and change our type mapping. But we need to RVVBitsPerBlock to alway be >= ELEN. This means we need two different mapping depending on ELEN. That is a non-trivial amount of work so disable fixed lenght vectors without Zvl64b for now. We had almost no tests for Zve32x without Zvl64b which is probably why we never realized that it was broken. Fixes #102352.
42 lines
1.6 KiB
LLVM
42 lines
1.6 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=loop-vectorize -scalable-vectorization=on -mtriple riscv64-linux-gnu -mattr=+zve32f,+f -S 2>%t | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-p:64:64-i64:64-i128:128-n64-S128"
|
|
target triple = "riscv64"
|
|
|
|
; We can't vectorize with Zvl32b due to RVVBitsPerBlock being 64. Since our
|
|
; vscale value is vlen/RVVBitsPerBlock this makes vscale 0.
|
|
define void @vector_add_i16(ptr noalias nocapture %a, i16 %v, i64 %n) {
|
|
; CHECK-LABEL: @vector_add_i16(
|
|
; 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 i32, ptr [[A:%.*]], i64 [[IV]]
|
|
; CHECK-NEXT: [[ELEM:%.*]] = load i16, ptr [[ARRAYIDX]], align 2
|
|
; CHECK-NEXT: [[ADD:%.*]] = add i16 [[ELEM]], [[V:%.*]]
|
|
; CHECK-NEXT: store i16 [[ADD]], ptr [[ARRAYIDX]], align 2
|
|
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
|
|
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[IV_NEXT]], 1024
|
|
; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
|
|
; CHECK: for.end:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %iv
|
|
%elem = load i16, ptr %arrayidx
|
|
%add = add i16 %elem, %v
|
|
store i16 %add, ptr %arrayidx
|
|
%iv.next = add nuw nsw i64 %iv, 1
|
|
%exitcond.not = icmp eq i64 %iv.next, 1024
|
|
br i1 %exitcond.not, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|