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.readlane.ll

62 lines
2.5 KiB
LLVM
Raw Normal View History

Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck %s
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
declare i32 @llvm.amdgcn.readlane(i32, i32) #0
; CHECK-LABEL: {{^}}test_readlane_sreg:
; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, s{{[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 @test_readlane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
%readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 %src1)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_readlane_imm_sreg:
; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[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 @test_readlane_imm_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
%readlane = call i32 @llvm.amdgcn.readlane(i32 32, i32 %src1)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
AMDGPU: Move v_readlane lane select from VGPR to SGPR Summary: Fix a compiler bug when the lane select happens to end up in a VGPR. Clarify the semantic of the corresponding intrinsic to be that of the corresponding GLSL: the lane select must be uniform across a wave front, otherwise results are undefined. Reviewers: arsenm Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D32343 llvm-svn: 301197
2017-04-25 01:17:36 +08:00
; CHECK-LABEL: {{^}}test_readlane_vregs:
; CHECK: v_readfirstlane_b32 [[LANE:s[0-9]+]], v{{[0-9]+}}
; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, [[LANE]]
define amdgpu_kernel void @test_readlane_vregs(i32 addrspace(1)* %out, <2 x i32> addrspace(1)* %in) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.in = getelementptr <2 x i32>, <2 x i32> addrspace(1)* %in, i32 %tid
%args = load <2 x i32>, <2 x i32> addrspace(1)* %gep.in
%value = extractelement <2 x i32> %args, i32 0
%lane = extractelement <2 x i32> %args, i32 1
%readlane = call i32 @llvm.amdgcn.readlane(i32 %value, i32 %lane)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
; TODO: m0 should be folded.
; CHECK-LABEL: {{^}}test_readlane_m0_sreg:
; CHECK: s_mov_b32 m0, -1
AMDGPU/SI: Add back reverted SGPR spilling code, but disable it suggested as a better solution by Matt llvm-svn: 287942
2016-11-26 01:37:09 +08:00
; CHECK: s_mov_b32 [[COPY_M0:s[0-9]+]], m0
; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], [[COPY_M0]]
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[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 @test_readlane_m0_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
%m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
%readlane = call i32 @llvm.amdgcn.readlane(i32 %m0, i32 %src1)
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
; CHECK-LABEL: {{^}}test_readlane_imm:
; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, 32
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 @test_readlane_imm(i32 addrspace(1)* %out, i32 %src0) #1 {
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
%readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 32) #0
store i32 %readlane, i32 addrspace(1)* %out, align 4
ret void
}
AMDGPU: Move v_readlane lane select from VGPR to SGPR Summary: Fix a compiler bug when the lane select happens to end up in a VGPR. Clarify the semantic of the corresponding intrinsic to be that of the corresponding GLSL: the lane select must be uniform across a wave front, otherwise results are undefined. Reviewers: arsenm Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D32343 llvm-svn: 301197
2017-04-25 01:17:36 +08:00
declare i32 @llvm.amdgcn.workitem.id.x() #2
AMDGCN/SI: Implement readlane/readfirstlane intrinsics Summary: This patch implements readlane/readfirstlane intrinsics. TODO: need to define a new register class to consider the case that the source could be a vector register or M0. Reviewed by: arsenm and tstellarAMD Differential Revision: http://reviews.llvm.org/D22489 llvm-svn: 279660
2016-08-25 04:35:23 +08:00
attributes #0 = { nounwind readnone convergent }
attributes #1 = { nounwind }
AMDGPU: Move v_readlane lane select from VGPR to SGPR Summary: Fix a compiler bug when the lane select happens to end up in a VGPR. Clarify the semantic of the corresponding intrinsic to be that of the corresponding GLSL: the lane select must be uniform across a wave front, otherwise results are undefined. Reviewers: arsenm Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D32343 llvm-svn: 301197
2017-04-25 01:17:36 +08:00
attributes #2 = { nounwind readnone }