mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
c7052955c8
Summary: In the same manner as struct.buffer.load / struct.buffer.store, allow struct.buffer.load.format / struct.buffer.store.format to return / accept any type. This simplifies front-end code gen. Reviewers: tpr, arsenm, nhaehnle Reviewed By: arsenm Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, t-tye, kerbowa, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D75789
52 lines
2.7 KiB
LLVM
52 lines
2.7 KiB
LLVM
; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs -show-mc-encoding | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
|
|
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_x:
|
|
; GCN: buffer_load_format_d16_x v{{[0-9]+}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
define amdgpu_ps half @buffer_load_format_d16_x(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
ret half %data
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_xy:
|
|
; UNPACKED: buffer_load_format_d16_xy v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
|
|
|
|
; PACKED: buffer_load_format_d16_xy v[[FULL:[0-9]+]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[FULL]]
|
|
define amdgpu_ps half @buffer_load_format_d16_xy(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%elt = extractelement <2 x half> %data, i32 1
|
|
ret half %elt
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_d16_xyzw:
|
|
; UNPACKED: buffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
|
|
|
|
; PACKED: buffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[HI]]
|
|
define amdgpu_ps half @buffer_load_format_d16_xyzw(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call <4 x half> @llvm.amdgcn.struct.buffer.load.format.v4f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%elt = extractelement <4 x half> %data, i32 3
|
|
ret half %elt
|
|
}
|
|
|
|
; GCN-LABEL: {{^}}buffer_load_format_i16_x:
|
|
; GCN: buffer_load_format_d16_x v{{[0-9]+}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
|
|
define amdgpu_ps half @buffer_load_format_i16_x(<4 x i32> inreg %rsrc) {
|
|
main_body:
|
|
%data = call i16 @llvm.amdgcn.struct.buffer.load.format.i16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
|
|
%fdata = bitcast i16 %data to half
|
|
ret half %fdata
|
|
}
|
|
|
|
declare half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare <4 x half> @llvm.amdgcn.struct.buffer.load.format.v4f16(<4 x i32>, i32, i32, i32, i32)
|
|
declare i16 @llvm.amdgcn.struct.buffer.load.format.i16(<4 x i32>, i32, i32, i32, i32)
|