mirror of
https://github.com/RPCSX/llvm.git
synced 2025-01-07 12:30:44 +00:00
ea7a0c0467
This makes it possible to distinguish between mesa shaders and other kernels even in the presence of compute shaders. Patch By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Differential Revision: http://reviews.llvm.org/D18559 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@265589 91177308-0d34-0410-b5e6-96231b3b80d8
45 lines
2.3 KiB
LLVM
45 lines
2.3 KiB
LLVM
;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s
|
|
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s
|
|
|
|
;CHECK-LABEL: {{^}}getlod:
|
|
;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x3 da
|
|
define amdgpu_ps void @getlod() {
|
|
main_body:
|
|
%r = call <4 x float> @llvm.SI.getlod.i32(i32 undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
|
|
%r0 = extractelement <4 x float> %r, i32 0
|
|
%r1 = extractelement <4 x float> %r, i32 1
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r0, float %r1)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}getlod_v2:
|
|
;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x3 da
|
|
define amdgpu_ps void @getlod_v2() {
|
|
main_body:
|
|
%r = call <4 x float> @llvm.SI.getlod.v2i32(<2 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
|
|
%r0 = extractelement <4 x float> %r, i32 0
|
|
%r1 = extractelement <4 x float> %r, i32 1
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r0, float %r1)
|
|
ret void
|
|
}
|
|
|
|
;CHECK-LABEL: {{^}}getlod_v4:
|
|
;CHECK: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0x3 da
|
|
define amdgpu_ps void @getlod_v4() {
|
|
main_body:
|
|
%r = call <4 x float> @llvm.SI.getlod.v4i32(<4 x i32> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0)
|
|
%r0 = extractelement <4 x float> %r, i32 0
|
|
%r1 = extractelement <4 x float> %r, i32 1
|
|
call void @llvm.SI.export(i32 15, i32 1, i32 1, i32 0, i32 1, float %r0, float %r1, float %r0, float %r1)
|
|
ret void
|
|
}
|
|
|
|
|
|
declare <4 x float> @llvm.SI.getlod.i32(i32, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #0
|
|
declare <4 x float> @llvm.SI.getlod.v2i32(<2 x i32>, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #0
|
|
declare <4 x float> @llvm.SI.getlod.v4i32(<4 x i32>, <8 x i32>, <4 x i32>, i32, i32, i32, i32, i32, i32, i32, i32) #0
|
|
|
|
declare void @llvm.SI.export(i32, i32, i32, i32, i32, float, float, float, float)
|
|
|
|
attributes #0 = { nounwind readnone }
|