mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
fad4cbdb84
Summary: These new image intrinsics contain the texture type as part of their name and have each component of the address/coordinate as individual parameters. This is a preparatory step for implementing the A16 feature, where coordinates are passed as half-floats or -ints, but the Z compare value and texel offsets are still full dwords, making it difficult or impossible to distinguish between A16 on or off in the old-style intrinsics. Additionally, these intrinsics pass the 'texfailpolicy' and 'cachectrl' as i32 bit fields to reduce operand clutter and allow for future extensibility. v2: - gather4 supports 2darray images - fix a bug with 1D images on SI Change-Id: I099f309e0a394082a5901ea196c3967afb867f04 Reviewers: arsenm, rampitec, b-sumner Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D44939 llvm-svn: 329166
20 lines
1.2 KiB
LLVM
20 lines
1.2 KiB
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefix=GCN -check-prefix=UNPACKED %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX81 %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -check-prefix=GCN -check-prefix=PACKED -check-prefix=GFX9 %s
|
|
|
|
; GCN-LABEL: {{^}}image_gather4_b_2d_v4f16:
|
|
; UNPACKED: image_gather4_b v[0:3], v[0:3], s[0:7], s[8:11] dmask:0x4 d16{{$}}
|
|
; PACKED: image_gather4_b v[0:1], v[0:3], s[0:7], s[8:11] dmask:0x4 d16{{$}}
|
|
define amdgpu_ps <2 x float> @image_gather4_b_2d_v4f16(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, float %s, float %t) {
|
|
main_body:
|
|
%tex = call <4 x half> @llvm.amdgcn.image.gather4.b.2d.v4f16.f32.f32(i32 4, float %bias, float %s, float %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 false, i32 0, i32 0)
|
|
%r = bitcast <4 x half> %tex to <2 x float>
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
declare <4 x half> @llvm.amdgcn.image.gather4.b.2d.v4f16.f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readonly }
|
|
attributes #2 = { nounwind readnone }
|