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/constant-fold-mi-operands.ll

145 lines
5.1 KiB
LLVM
Raw Normal View History

AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
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 -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; GCN-LABEL: {{^}}fold_mi_v_and_0:
; GCN: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
; GCN-NOT: [[RESULT]]
; GCN: buffer_store_dword [[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @fold_mi_v_and_0(i32 addrspace(1)* %out) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%x = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
%size = call i32 @llvm.amdgcn.groupstaticsize()
%and = and i32 %size, %x
store i32 %and, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_s_and_0:
; GCN: v_mov_b32_e32 [[RESULT:v[0-9]+]], 0{{$}}
; GCN-NOT: [[RESULT]]
; GCN: buffer_store_dword [[RESULT]]
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 @fold_mi_s_and_0(i32 addrspace(1)* %out, i32 %x) #0 {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%size = call i32 @llvm.amdgcn.groupstaticsize()
%and = and i32 %size, %x
store i32 %and, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_v_or_0:
[AMDGPU][MC] Corrected several VI opcodes to avoid printing _e64 See bug 32936: https://bugs.llvm.org//show_bug.cgi?id=32936 Reviewers: artem.tamazov, vpykhtin Differential Revision: https://reviews.llvm.org/D33123 llvm-svn: 303070
2017-05-15 22:28:23 +08:00
; GCN: v_mbcnt_lo_u32_b32{{(_e64)*}} [[RESULT:v[0-9]+]]
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; GCN-NOT: [[RESULT]]
; GCN: buffer_store_dword [[RESULT]]
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 @fold_mi_v_or_0(i32 addrspace(1)* %out) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%x = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
%size = call i32 @llvm.amdgcn.groupstaticsize()
%or = or i32 %size, %x
store i32 %or, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_s_or_0:
; GCN: s_load_dword [[SVAL:s[0-9]+]]
; GCN-NOT: [[SVAL]]
; GCN: v_mov_b32_e32 [[VVAL:v[0-9]+]], [[SVAL]]
; GCN-NOT: [[VVAL]]
; GCN: buffer_store_dword [[VVAL]]
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 @fold_mi_s_or_0(i32 addrspace(1)* %out, i32 %x) #0 {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%size = call i32 @llvm.amdgcn.groupstaticsize()
%or = or i32 %size, %x
store i32 %or, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_v_xor_0:
[AMDGPU][MC] Corrected several VI opcodes to avoid printing _e64 See bug 32936: https://bugs.llvm.org//show_bug.cgi?id=32936 Reviewers: artem.tamazov, vpykhtin Differential Revision: https://reviews.llvm.org/D33123 llvm-svn: 303070
2017-05-15 22:28:23 +08:00
; GCN: v_mbcnt_lo_u32_b32{{(_e64)*}} [[RESULT:v[0-9]+]]
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; GCN-NOT: [[RESULT]]
; GCN: buffer_store_dword [[RESULT]]
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 @fold_mi_v_xor_0(i32 addrspace(1)* %out) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%x = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
%size = call i32 @llvm.amdgcn.groupstaticsize()
%xor = xor i32 %size, %x
store i32 %xor, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_s_xor_0:
; GCN: s_load_dword [[SVAL:s[0-9]+]]
; GCN-NOT: [[SVAL]]
; GCN: v_mov_b32_e32 [[VVAL:v[0-9]+]], [[SVAL]]
; GCN-NOT: [[VVAL]]
; GCN: buffer_store_dword [[VVAL]]
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 @fold_mi_s_xor_0(i32 addrspace(1)* %out, i32 %x) #0 {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%size = call i32 @llvm.amdgcn.groupstaticsize()
%xor = xor i32 %size, %x
store i32 %xor, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_s_not_0:
; GCN: v_mov_b32_e32 [[RESULT:v[0-9]+]], -1{{$}}
; GCN-NOT: [[RESULT]]
; GCN: buffer_store_dword [[RESULT]]
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @fold_mi_s_not_0(i32 addrspace(1)* %out, i32 %x) #0 {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%size = call i32 @llvm.amdgcn.groupstaticsize()
%xor = xor i32 %size, -1
store i32 %xor, i32 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_v_not_0:
[AMDGPU][MC] Corrected several VI opcodes to avoid printing _e64 See bug 32936: https://bugs.llvm.org//show_bug.cgi?id=32936 Reviewers: artem.tamazov, vpykhtin Differential Revision: https://reviews.llvm.org/D33123 llvm-svn: 303070
2017-05-15 22:28:23 +08:00
; GCN: v_bcnt_u32_b32{{(_e64)*}} v[[RESULT_LO:[0-9]+]], v{{[0-9]+}}, 0{{$}}
; GCN: v_bcnt_u32_b32{{(_e32)*(_e64)*}} v[[RESULT_LO:[0-9]+]], v{{[0-9]+}}, v[[RESULT_LO]]{{$}}
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; GCN-NEXT: v_not_b32_e32 v[[RESULT_LO]]
; GCN-NEXT: v_mov_b32_e32 v[[RESULT_HI:[0-9]+]], -1{{$}}
; GCN-NEXT: buffer_store_dwordx2 v{{\[}}[[RESULT_LO]]:[[RESULT_HI]]{{\]}}
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 @fold_mi_v_not_0(i64 addrspace(1)* %out) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%vreg = load volatile i64, i64 addrspace(1)* undef
%ctpop = call i64 @llvm.ctpop.i64(i64 %vreg)
%xor = xor i64 %ctpop, -1
store i64 %xor, i64 addrspace(1)* %out
ret void
}
; The neg1 appears after folding the not 0
; GCN-LABEL: {{^}}fold_mi_or_neg1:
; GCN: buffer_load_dwordx2
; GCN: buffer_load_dwordx2 v{{\[}}[[VREG1_LO:[0-9]+]]:[[VREG1_HI:[0-9]+]]{{\]}}
[AMDGPU][MC] Corrected several VI opcodes to avoid printing _e64 See bug 32936: https://bugs.llvm.org//show_bug.cgi?id=32936 Reviewers: artem.tamazov, vpykhtin Differential Revision: https://reviews.llvm.org/D33123 llvm-svn: 303070
2017-05-15 22:28:23 +08:00
; GCN: v_bcnt_u32_b32{{(_e64)*}} v[[RESULT_LO:[0-9]+]], v{{[0-9]+}}, 0{{$}}
; GCN: v_bcnt_u32_b32{{(_e32)*(_e64)*}} v[[RESULT_LO:[0-9]+]], v{{[0-9]+}}, v[[RESULT_LO]]{{$}}
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; GCN-DAG: v_not_b32_e32 v[[RESULT_LO]], v[[RESULT_LO]]
AMDGPU: Allow SIShrinkInstructions to work in non-SSA Immediates can be folded as long as the immediate is a vreg. Also undo commuting instructions if it didn't fold an immediate. llvm-svn: 307575
2017-07-11 03:53:57 +08:00
; GCN-DAG: v_or_b32_e32 v[[RESULT_LO]], v[[RESULT_LO]], v[[VREG1_LO]]
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
; GCN-DAG: v_mov_b32_e32 v[[RESULT_HI:[0-9]+]], v[[VREG1_HI]]
; GCN: buffer_store_dwordx2 v{{\[}}[[RESULT_LO]]:[[RESULT_HI]]{{\]}}
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 @fold_mi_or_neg1(i64 addrspace(1)* %out) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%vreg0 = load volatile i64, i64 addrspace(1)* undef
%vreg1 = load volatile i64, i64 addrspace(1)* undef
%ctpop = call i64 @llvm.ctpop.i64(i64 %vreg0)
%xor = xor i64 %ctpop, -1
%or = or i64 %xor, %vreg1
store i64 %or, i64 addrspace(1)* %out
ret void
}
; GCN-LABEL: {{^}}fold_mi_and_neg1:
; GCN: v_bcnt_u32_b32
; GCN: v_bcnt_u32_b32
; GCN: v_not_b32
; GCN: v_and_b32
; GCN-NOT: v_and_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 @fold_mi_and_neg1(i64 addrspace(1)* %out) {
AMDGPU: Improve splitting 64-bit bit ops by constants This addresses a TODO to handle operations besides and. This also starts eliminating no-op operations with a constant that can emerge later. llvm-svn: 281488
2016-09-14 23:19:03 +08:00
%vreg0 = load volatile i64, i64 addrspace(1)* undef
%vreg1 = load volatile i64, i64 addrspace(1)* undef
%ctpop = call i64 @llvm.ctpop.i64(i64 %vreg0)
%xor = xor i64 %ctpop, -1
%and = and i64 %xor, %vreg1
store i64 %and, i64 addrspace(1)* %out
ret void
}
declare i64 @llvm.ctpop.i64(i64) #1
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #1
declare i32 @llvm.amdgcn.groupstaticsize() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }