mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-01 15:11:24 +00:00
67297cd956
This commit enables forming vector extloads for ARM.
It only does so for legal types, and when we can't fold the extension
in a wide/long form of the user instruction.
Enabling it for larger types isn't as good an idea on ARM as it is on
X86, because:
- we pretend that extloads are legal, but end up generating vld+vmov
- we have instructions like vld {dN, dM}, which can't be generated
when we "manually expand" extloads to vld+vmov.
For legal types, the combine doesn't fire that often: in the
integration tests only in a big endian testcase, where it removes a
pointless AND.
Related to rdar://19723053
Differential Revision: http://reviews.llvm.org/D7423
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@231396 91177308-0d34-0410-b5e6-96231b3b80d8
31 lines
726 B
LLVM
31 lines
726 B
LLVM
; RUN: llc -mtriple armv7 %s -o - | FileCheck %s
|
|
|
|
; CHECK-LABEL: f:
|
|
define float @f(<4 x i16>* nocapture %in) {
|
|
; CHECK: vld1
|
|
; CHECK: vmovl.u16
|
|
; CHECK-NOT: vand
|
|
%1 = load <4 x i16>, <4 x i16>* %in
|
|
; CHECK: vcvt.f32.u32
|
|
%2 = uitofp <4 x i16> %1 to <4 x float>
|
|
%3 = extractelement <4 x float> %2, i32 0
|
|
%4 = extractelement <4 x float> %2, i32 1
|
|
%5 = extractelement <4 x float> %2, i32 2
|
|
|
|
; CHECK: vadd.f32
|
|
%6 = fadd float %3, %4
|
|
%7 = fadd float %6, %5
|
|
|
|
ret float %7
|
|
}
|
|
|
|
define float @g(<4 x i16>* nocapture %in) {
|
|
; CHECK: vldr
|
|
%1 = load <4 x i16>, <4 x i16>* %in
|
|
; CHECK-NOT: uxth
|
|
%2 = extractelement <4 x i16> %1, i32 0
|
|
; CHECK: vcvt.f32.u32
|
|
%3 = uitofp i16 %2 to float
|
|
ret float %3
|
|
}
|