mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 13:02:52 +02:00
1a5a919d2d
Summary: Now that we've made all the necessary backend changes, we can add a new intrinsic which exposes the new capabilities to IR producers. Since llvm.amdgpu.update.dpp is a strict superset of llvm.amdgpu.mov.dpp, we should deprecate the former. We also add tests for all the functionality that was added in previous changes, now that we can access it via an IR construct. Reviewers: tstellar, arsenm Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye Differential Revision: https://reviews.llvm.org/D34718 llvm-svn: 310399
18 lines
936 B
LLVM
18 lines
936 B
LLVM
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefix=VI -check-prefix=VI-OPT %s
|
|
; RUN: llc -O0 -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefix=VI -check-prefix=VI-NOOPT %s
|
|
|
|
; VI-LABEL: {{^}}dpp_test:
|
|
; VI: v_mov_b32_e32 v0, s{{[0-9]+}}
|
|
; VI: v_mov_b32_e32 v1, s{{[0-9]+}}
|
|
; VI: s_nop 1
|
|
; VI: v_mov_b32_dpp v0, v1 quad_perm:[1,0,0,0] row_mask:0x1 bank_mask:0x1 bound_ctrl:0 ; encoding: [0xfa,0x02,0x00,0x7e,0x01,0x01,0x08,0x11]
|
|
define amdgpu_kernel void @dpp_test(i32 addrspace(1)* %out, i32 %in1, i32 %in2) {
|
|
%tmp0 = call i32 @llvm.amdgcn.update.dpp.i32(i32 %in1, i32 %in2, i32 1, i32 1, i32 1, i1 1) #0
|
|
store i32 %tmp0, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1) #0
|
|
|
|
attributes #0 = { nounwind readnone convergent }
|