maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ds.permute.ll

23 lines
918 B
LLVM
Raw Normal View History

AMDGPU/SI: Implement DS_PERMUTE/DS_BPERMUTE Instruction Definitions and Intrinsics Summary: This patch impleemnts DS_PERMUTE/DS_BPERMUTE instruction definitions and intrinsics, which are new since VI. Reviewers: tstellarAMD, arsenm Subscribers: llvm-commits, arsenm Differential Revision: http://reviews.llvm.org/D17614 llvm-svn: 262356
2016-03-02 01:51:23 +08:00
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
declare i32 @llvm.amdgcn.ds.permute(i32, i32) #0
AMDGPU/SI: Add offset field to ds_permute/ds_bpermute instructions Summary: These instructions can add an immediate offset to the address, like other ds instructions. Reviewers: arsenm Subscribers: arsenm, scchan Differential Revision: http://reviews.llvm.org/D19233 llvm-svn: 268043
2016-04-29 22:34:26 +08:00
; CHECK-LABEL: {{^}}ds_permute:
AMDGPU/SI: Implement DS_PERMUTE/DS_BPERMUTE Instruction Definitions and Intrinsics Summary: This patch impleemnts DS_PERMUTE/DS_BPERMUTE instruction definitions and intrinsics, which are new since VI. Reviewers: tstellarAMD, arsenm Subscribers: llvm-commits, arsenm Differential Revision: http://reviews.llvm.org/D17614 llvm-svn: 262356
2016-03-02 01:51:23 +08:00
; CHECK: ds_permute_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @ds_permute(i32 addrspace(1)* %out, i32 %index, i32 %src) nounwind {
Revert "AMDGPU/SI: Do not generate s_waitcnt after ds_permute/ds_bpermute" This reverts commit r263720. Just confirmed that s_waitcnt is required after ds_permute/ds_bpermute. llvm-svn: 265992
2016-04-12 04:38:40 +08:00
%bpermute = call i32 @llvm.amdgcn.ds.permute(i32 %index, i32 %src) #0
store i32 %bpermute, i32 addrspace(1)* %out, align 4
AMDGPU/SI: Implement DS_PERMUTE/DS_BPERMUTE Instruction Definitions and Intrinsics Summary: This patch impleemnts DS_PERMUTE/DS_BPERMUTE instruction definitions and intrinsics, which are new since VI. Reviewers: tstellarAMD, arsenm Subscribers: llvm-commits, arsenm Differential Revision: http://reviews.llvm.org/D17614 llvm-svn: 262356
2016-03-02 01:51:23 +08:00
ret void
}
AMDGPU/SI: Add offset field to ds_permute/ds_bpermute instructions Summary: These instructions can add an immediate offset to the address, like other ds instructions. Reviewers: arsenm Subscribers: arsenm, scchan Differential Revision: http://reviews.llvm.org/D19233 llvm-svn: 268043
2016-04-29 22:34:26 +08:00
; CHECK-LABEL: {{^}}ds_permute_imm_offset:
; CHECK: ds_permute_b32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}} offset:4
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @ds_permute_imm_offset(i32 addrspace(1)* %out, i32 %base_index, i32 %src) nounwind {
AMDGPU/SI: Add offset field to ds_permute/ds_bpermute instructions Summary: These instructions can add an immediate offset to the address, like other ds instructions. Reviewers: arsenm Subscribers: arsenm, scchan Differential Revision: http://reviews.llvm.org/D19233 llvm-svn: 268043
2016-04-29 22:34:26 +08:00
%index = add i32 %base_index, 4
%bpermute = call i32 @llvm.amdgcn.ds.permute(i32 %index, i32 %src) #0
store i32 %bpermute, i32 addrspace(1)* %out, align 4
ret void
}
AMDGPU/SI: Implement DS_PERMUTE/DS_BPERMUTE Instruction Definitions and Intrinsics Summary: This patch impleemnts DS_PERMUTE/DS_BPERMUTE instruction definitions and intrinsics, which are new since VI. Reviewers: tstellarAMD, arsenm Subscribers: llvm-commits, arsenm Differential Revision: http://reviews.llvm.org/D17614 llvm-svn: 262356
2016-03-02 01:51:23 +08:00
attributes #0 = { nounwind readnone convergent }