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/target-cpu.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

112 lines
5.0 KiB
LLVM
Raw Normal View History

AMDGPU/SI: Extend promoting alloca to vector to arrays of up to 16 elements Summary: This patch extends the promotion of alloca to vector to the arrays of up to 16 elements. Also we introduce an option, -disable-promote-alloca-to-vector, to switch promotion to vector off, if needed. Reviewers: arsenm Differential Revision: https://reviews.llvm.org/D33559 llvm-svn: 325372
2018-02-17 03:14:17 +08:00
; RUN: llc -march=amdgcn -disable-promote-alloca-to-vector -verify-machineinstrs < %s | FileCheck %s
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
declare i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr() #1
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
declare i32 @llvm.amdgcn.workitem.id.x() #1
; CI+ intrinsic
declare void @llvm.amdgcn.s.dcache.inv.vol() #0
; VI+ intrinsic
declare void @llvm.amdgcn.s.dcache.wb() #0
; CHECK-LABEL: {{^}}target_none:
; CHECK: s_movk_i32 [[OFFSETREG:s[0-9]+]], 0x400
; CHECK: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, [[OFFSETREG]]
; CHECK: buffer_store_dword v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64
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 @target_none() #0 {
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%kernargs = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
%kernargs.gep = getelementptr inbounds i8, i8 addrspace(4)* %kernargs, i64 1024
%kernargs.gep.cast = bitcast i8 addrspace(4)* %kernargs.gep to i32 addrspace(1)* addrspace(4)*
%ptr = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %kernargs.gep.cast
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
%id = call i32 @llvm.amdgcn.workitem.id.x()
%id.ext = sext i32 %id to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %ptr, i64 %id.ext
store i32 0, i32 addrspace(1)* %gep
ret void
}
; CHECK-LABEL: {{^}}target_tahiti:
; CHECK: s_movk_i32 [[OFFSETREG:s[0-9]+]], 0x400
; CHECK: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, [[OFFSETREG]]
; CHECK: buffer_store_dword v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64
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 @target_tahiti() #1 {
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%kernargs = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
%kernargs.gep = getelementptr inbounds i8, i8 addrspace(4)* %kernargs, i64 1024
%kernargs.gep.cast = bitcast i8 addrspace(4)* %kernargs.gep to i32 addrspace(1)* addrspace(4)*
%ptr = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %kernargs.gep.cast
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
%id = call i32 @llvm.amdgcn.workitem.id.x()
%id.ext = sext i32 %id to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %ptr, i64 %id.ext
store i32 0, i32 addrspace(1)* %gep
ret void
}
; CHECK-LABEL: {{^}}target_bonaire:
; CHECK: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x100
; CHECK: buffer_store_dword v{{[0-9]+}}, v{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0 addr64
; CHECK: s_dcache_inv_vol
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 @target_bonaire() #3 {
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%kernargs = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
%kernargs.gep = getelementptr inbounds i8, i8 addrspace(4)* %kernargs, i64 1024
%kernargs.gep.cast = bitcast i8 addrspace(4)* %kernargs.gep to i32 addrspace(1)* addrspace(4)*
%ptr = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %kernargs.gep.cast
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
%id = call i32 @llvm.amdgcn.workitem.id.x()
%id.ext = sext i32 %id to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %ptr, i64 %id.ext
store i32 0, i32 addrspace(1)* %gep
call void @llvm.amdgcn.s.dcache.inv.vol()
ret void
}
; CHECK-LABEL: {{^}}target_fiji:
; CHECK: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x400
; CHECK: flat_store_dword
; CHECK: s_dcache_wb{{$}}
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 @target_fiji() #4 {
[AMDGPU] Change constant addr space to 4 Differential Revision: https://reviews.llvm.org/D43170 llvm-svn: 325030
2018-02-14 02:00:25 +08:00
%kernargs = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
%kernargs.gep = getelementptr inbounds i8, i8 addrspace(4)* %kernargs, i64 1024
%kernargs.gep.cast = bitcast i8 addrspace(4)* %kernargs.gep to i32 addrspace(1)* addrspace(4)*
%ptr = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(4)* %kernargs.gep.cast
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
%id = call i32 @llvm.amdgcn.workitem.id.x()
%id.ext = sext i32 %id to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %ptr, i64 %id.ext
store i32 0, i32 addrspace(1)* %gep
call void @llvm.amdgcn.s.dcache.wb()
ret void
}
; CHECK-LABEL: {{^}}promote_alloca_enabled:
; CHECK: ds_read_b32
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 @promote_alloca_enabled(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #5 {
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
entry:
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
%stack = alloca [5 x i32], align 4, addrspace(5)
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
%tmp = load i32, i32 addrspace(1)* %in, align 4
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32] addrspace(5)* %stack, i32 0, i32 %tmp
%load = load i32, i32 addrspace(5)* %arrayidx1
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
store i32 %load, i32 addrspace(1)* %out
ret void
}
; CHECK-LABEL: {{^}}promote_alloca_disabled:
; CHECK: SCRATCH_RSRC_DWORD0
; CHECK: SCRATCH_RSRC_DWORD1
; CHECK: ScratchSize: 24
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 @promote_alloca_disabled(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #6 {
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
entry:
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
%stack = alloca [5 x i32], align 4, addrspace(5)
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
%tmp = load i32, i32 addrspace(1)* %in, align 4
[AMDGPU] Switch to the new addr space mapping by default This requires corresponding clang change. Differential Revision: https://reviews.llvm.org/D40955 llvm-svn: 324101
2018-02-03 00:07:16 +08:00
%arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32] addrspace(5)* %stack, i32 0, i32 %tmp
%load = load i32, i32 addrspace(5)* %arrayidx1
AMDGPU: Implement per-function subtargets llvm-svn: 273940
2016-06-28 04:48:03 +08:00
store i32 %load, i32 addrspace(1)* %out
ret void
}
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
attributes #2 = { nounwind "target-cpu"="tahiti" }
attributes #3 = { nounwind "target-cpu"="bonaire" }
attributes #4 = { nounwind "target-cpu"="fiji" }
[AMDGPU] Wave and register controls - Implemented amdgpu-flat-work-group-size attribute - Implemented amdgpu-num-active-waves-per-eu attribute - Implemented amdgpu-num-sgpr attribute - Implemented amdgpu-num-vgpr attribute - Dynamic LDS constraints are in a separate patch Patch by Tom Stellard and Konstantin Zhuravlyov Differential Revision: https://reviews.llvm.org/D21562 llvm-svn: 280747
2016-09-07 04:22:28 +08:00
attributes #5 = { nounwind "target-features"="+promote-alloca" "amdgpu-waves-per-eu"="1,3" }
attributes #6 = { nounwind "target-features"="-promote-alloca" "amdgpu-waves-per-eu"="1,3" }