mirror of
https://github.com/RPCSX/llvm.git
synced 2026-01-31 01:05:23 +01:00
d019e8638a
This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@292982 91177308-0d34-0410-b5e6-96231b3b80d8
53 lines
2.1 KiB
LLVM
53 lines
2.1 KiB
LLVM
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GCN -check-prefix=FUNC %s
|
|
; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
|
|
|
|
declare float @llvm.copysign.f32(float, float) nounwind readnone
|
|
declare <2 x float> @llvm.copysign.v2f32(<2 x float>, <2 x float>) nounwind readnone
|
|
declare <4 x float> @llvm.copysign.v4f32(<4 x float>, <4 x float>) nounwind readnone
|
|
|
|
; Try to identify arg based on higher address.
|
|
; FUNC-LABEL: {{^}}test_copysign_f32:
|
|
; SI: s_load_dword [[SMAG:s[0-9]+]], {{.*}} 0xb
|
|
; SI: s_load_dword [[SSIGN:s[0-9]+]], {{.*}} 0xc
|
|
; VI: s_load_dword [[SMAG:s[0-9]+]], {{.*}} 0x2c
|
|
; VI: s_load_dword [[SSIGN:s[0-9]+]], {{.*}} 0x30
|
|
; GCN-DAG: v_mov_b32_e32 [[VSIGN:v[0-9]+]], [[SSIGN]]
|
|
; GCN-DAG: v_mov_b32_e32 [[VMAG:v[0-9]+]], [[SMAG]]
|
|
; GCN-DAG: s_brev_b32 [[SCONST:s[0-9]+]], -2
|
|
; GCN: v_bfi_b32 [[RESULT:v[0-9]+]], [[SCONST]], [[VMAG]], [[VSIGN]]
|
|
; GCN: buffer_store_dword [[RESULT]],
|
|
; GCN: s_endpgm
|
|
|
|
; EG: BFI_INT
|
|
define void @test_copysign_f32(float addrspace(1)* %out, float %mag, float %sign) nounwind {
|
|
%result = call float @llvm.copysign.f32(float %mag, float %sign)
|
|
store float %result, float addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_copysign_v2f32:
|
|
; GCN: s_endpgm
|
|
|
|
; EG: BFI_INT
|
|
; EG: BFI_INT
|
|
define void @test_copysign_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %mag, <2 x float> %sign) nounwind {
|
|
%result = call <2 x float> @llvm.copysign.v2f32(<2 x float> %mag, <2 x float> %sign)
|
|
store <2 x float> %result, <2 x float> addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
; FUNC-LABEL: {{^}}test_copysign_v4f32:
|
|
; GCN: s_endpgm
|
|
|
|
; EG: BFI_INT
|
|
; EG: BFI_INT
|
|
; EG: BFI_INT
|
|
; EG: BFI_INT
|
|
define void @test_copysign_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %mag, <4 x float> %sign) nounwind {
|
|
%result = call <4 x float> @llvm.copysign.v4f32(<4 x float> %mag, <4 x float> %sign)
|
|
store <4 x float> %result, <4 x float> addrspace(1)* %out, align 16
|
|
ret void
|
|
}
|
|
|