mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-01-14 00:32:55 +00:00
4070037e3c
The folding of unary operations through a vector compare and mask operation is only safe if the unary operation result is of the same size as its input. For example, it's not safe for [su]itofp from v4i32 to v4f64. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213799 91177308-0d34-0410-b5e6-96231b3b80d8
57 lines
2.2 KiB
LLVM
57 lines
2.2 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin | FileCheck %s
|
|
|
|
define <4 x float> @foo(<4 x float> %val, <4 x float> %test) nounwind {
|
|
; CHECK-LABEL: LCPI0_0:
|
|
; CHECK-NEXT: .long 1065353216 ## float 1.000000e+00
|
|
; CHECK-NEXT: .long 1065353216 ## float 1.000000e+00
|
|
; CHECK-NEXT: .long 1065353216 ## float 1.000000e+00
|
|
; CHECK-NEXT: .long 1065353216 ## float 1.000000e+00
|
|
; CHECK-LABEL: foo:
|
|
; CHECK: cmpeqps %xmm1, %xmm0
|
|
; CHECK-NEXT: andps LCPI0_0(%rip), %xmm0
|
|
; CHECK-NEXT: retq
|
|
|
|
%cmp = fcmp oeq <4 x float> %val, %test
|
|
%ext = zext <4 x i1> %cmp to <4 x i32>
|
|
%result = sitofp <4 x i32> %ext to <4 x float>
|
|
ret <4 x float> %result
|
|
}
|
|
|
|
; Make sure the operation doesn't try to get folded when the sizes don't match,
|
|
; as that ends up crashing later when trying to form a bitcast operation for
|
|
; the folded nodes.
|
|
define void @foo1(<4 x float> %val, <4 x float> %test, <4 x double>* %p) nounwind {
|
|
; CHECK-LABEL: LCPI1_0:
|
|
; CHECK-NEXT: .long 1 ## 0x1
|
|
; CHECK-NEXT: .long 1 ## 0x1
|
|
; CHECK-NEXT: .long 1 ## 0x1
|
|
; CHECK-NEXT: .long 1 ## 0x1
|
|
; CHECK-LABEL: foo1:
|
|
; FIXME: The operation gets scalarized. If/when the compiler learns to better
|
|
; use [V]CVTDQ2PD, this will need updated.
|
|
; CHECK: cvtsi2sdq
|
|
; CHECK: cvtsi2sdq
|
|
; CHECK: cvtsi2sdq
|
|
; CHECK: cvtsi2sdq
|
|
%cmp = fcmp oeq <4 x float> %val, %test
|
|
%ext = zext <4 x i1> %cmp to <4 x i32>
|
|
%result = sitofp <4 x i32> %ext to <4 x double>
|
|
store <4 x double> %result, <4 x double>* %p
|
|
ret void
|
|
}
|
|
|
|
; Also test the general purpose constant folding of int->fp.
|
|
define void @foo2(<4 x float>* noalias %result) nounwind {
|
|
; CHECK-LABEL: LCPI2_0:
|
|
; CHECK-NEXT: .long 1082130432 ## float 4.000000e+00
|
|
; CHECK-NEXT: .long 1084227584 ## float 5.000000e+00
|
|
; CHECK-NEXT: .long 1086324736 ## float 6.000000e+00
|
|
; CHECK-NEXT: .long 1088421888 ## float 7.000000e+00
|
|
; CHECK-LABEL: foo2:
|
|
; CHECK: movaps LCPI2_0(%rip), %xmm0
|
|
|
|
%val = uitofp <4 x i32> <i32 4, i32 5, i32 6, i32 7> to <4 x float>
|
|
store <4 x float> %val, <4 x float>* %result
|
|
ret void
|
|
}
|