1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/test/CodeGen/AMDGPU/llvm.amdgcn.ds.ordered.add.gfx10.ll
Nicolai Haehnle b7ef706144 AMDGPU/GFX10: implement ds_ordered_count changes
Summary:
ds_ordered_count can now simultaneously operate on up to 4 dwords
in a single instruction, which are taken from (and returned to)
lanes 0..3 of a single VGPR.

Change-Id: I19b6e7b0732b617c10a779a7f9c0303eec7dd276

Reviewers: mareko, arsenm, rampitec

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D63716

llvm-svn: 364815
2019-07-01 17:17:52 +00:00

24 lines
1.1 KiB
LLVM

; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=GCN %s
; FUNC-LABEL: {{^}}ds_ordered_add:
; GCN-DAG: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
; GCN-DAG: s_mov_b32 m0,
; GCN: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:772 gds
define amdgpu_kernel void @ds_ordered_add(i32 addrspace(2)* inreg %gds, i32 addrspace(1)* %out) {
%val = call i32@llvm.amdgcn.ds.ordered.add(i32 addrspace(2)* %gds, i32 31, i32 0, i32 0, i1 false, i32 16777217, i1 true, i1 true)
store i32 %val, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}ds_ordered_add_4dw:
; GCN-DAG: v_mov_b32_e32 v[[INCR:[0-9]+]], 31
; GCN-DAG: s_mov_b32 m0,
; GCN: ds_ordered_count v{{[0-9]+}}, v[[INCR]] offset:49924 gds
define amdgpu_kernel void @ds_ordered_add_4dw(i32 addrspace(2)* inreg %gds, i32 addrspace(1)* %out) {
%val = call i32@llvm.amdgcn.ds.ordered.add(i32 addrspace(2)* %gds, i32 31, i32 0, i32 0, i1 false, i32 67108865, i1 true, i1 true)
store i32 %val, i32 addrspace(1)* %out
ret void
}
declare i32 @llvm.amdgcn.ds.ordered.add(i32 addrspace(2)* nocapture, i32, i32, i32, i1, i32, i1, i1)