ee752134ac
Loads of <4 x i8> vectors were modeled as extremely expensive. And while we don't have a load instruction that supports this, it isn't that expensive to create a vector of i8 elements. The codegen for this was fixed/optimised in D105110. This now tweaks the cost model and enables SLP vectorisation of my motivating case loadi8.ll. Differential Revision: https://reviews.llvm.org/D103629
34 lines
1.0 KiB
LLVM
34 lines
1.0 KiB
LLVM
; REQUIRES: asserts
|
|
; RUN: opt < %s -force-vector-width=2 -force-vector-interleave=1 -loop-vectorize -S --debug-only=loop-vectorize 2>&1 | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64--linux-gnu"
|
|
|
|
%pair = type { i8, i8 }
|
|
|
|
; CHECK-LABEL: test
|
|
; CHECK: Found an estimated cost of 17 for VF 2 For instruction: {{.*}} load i8
|
|
; CHECK: Found an estimated cost of 0 for VF 2 For instruction: {{.*}} load i8
|
|
; CHECK: vector.body
|
|
; CHECK: load <4 x i8>
|
|
; CHECK: br i1 {{.*}}, label %middle.block, label %vector.body
|
|
|
|
define void @test(%pair* %p, i64 %n) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
|
|
%tmp0 = getelementptr %pair, %pair* %p, i64 %i, i32 0
|
|
%tmp1 = load i8, i8* %tmp0, align 1
|
|
%tmp2 = getelementptr %pair, %pair* %p, i64 %i, i32 1
|
|
%tmp3 = load i8, i8* %tmp2, align 1
|
|
%i.next = add nuw nsw i64 %i, 1
|
|
%cond = icmp eq i64 %i.next, %n
|
|
br i1 %cond, label %for.end, label %for.body
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|