mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
179532ade9
Summary:
This patch define and implement amdgcn image intrinsics with sampler.
1. define vdata type to be llvm_anyfloat_ty, address type to be llvm_anyfloat_ty,
and rsrc type to be llvm_anyint_ty. As a result, we expect the intrinsics name
to have three suffixes to overload each of these three types;
2. D128 as well as two other flags are implied in the three types, for example,
if you use v8i32 as resource type, then r128 is 0!
3. don't expose TFE flag, and other flags are exposed in the instruction order:
unrm, glc, slc, lwe and da.
Differential Revision: http://reviews.llvm.org/D22838
Reviewed by:
arsenm and tstellarAMD
llvm-svn: 278291
38 lines
1.9 KiB
LLVM
38 lines
1.9 KiB
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck --check-prefix=GCN %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefix=GCN %s
|
|
|
|
; GCN-LABEL: {{^}}getlod:
|
|
; GCN: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v[0-9]+}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf da
|
|
define void @getlod(<4 x float> addrspace(1)* %out) {
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.getlod.v4f32.f32.v8i32(float undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 1)
|
|
store <4 x float> %r, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}getlod_v2:
|
|
; GCN: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf da
|
|
define void @getlod_v2(<4 x float> addrspace(1)* %out) {
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.getlod.v4f32.v2f32.v8i32(<2 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 1)
|
|
store <4 x float> %r, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}getlod_v4:
|
|
; GCN: image_get_lod {{v\[[0-9]+:[0-9]+\]}}, {{v\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}} dmask:0xf da
|
|
define void @getlod_v4(<4 x float> addrspace(1)* %out) {
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.getlod.v4f32.v4f32.v8i32(<4 x float> undef, <8 x i32> undef, <4 x i32> undef, i32 15, i1 0, i1 0, i1 0, i1 0, i1 1)
|
|
store <4 x float> %r, <4 x float> addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.getlod.v4f32.f32.v8i32(float, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
|
|
declare <4 x float> @llvm.amdgcn.image.getlod.v4f32.v2f32.v8i32(<2 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
|
|
declare <4 x float> @llvm.amdgcn.image.getlod.v4f32.v4f32.v8i32(<4 x float>, <8 x i32>, <4 x i32>, i32, i1, i1, i1, i1, i1) #0
|
|
|
|
|
|
attributes #0 = { nounwind readnone }
|