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/annotate-kernel-features-hs...

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

323 lines
11 KiB
LLVM
Raw Normal View History

AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -amdgpu-annotate-kernel-features %s | FileCheck -check-prefix=HSA %s
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
declare i32 @llvm.amdgcn.workgroup.id.x() #0
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
declare i32 @llvm.amdgcn.workgroup.id.y() #0
declare i32 @llvm.amdgcn.workgroup.id.z() #0
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
declare i32 @llvm.amdgcn.workitem.id.x() #0
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
declare i32 @llvm.amdgcn.workitem.id.y() #0
declare i32 @llvm.amdgcn.workitem.id.z() #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
declare i8 addrspace(4)* @llvm.amdgcn.dispatch.ptr() #0
declare i8 addrspace(4)* @llvm.amdgcn.queue.ptr() #0
declare i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr() #0
declare i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr() #0
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
declare i64 @llvm.amdgcn.dispatch.id() #0
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_workitem_id_x() #1 {
define void @use_workitem_id_x() #1 {
%val = call i32 @llvm.amdgcn.workitem.id.x()
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
; HSA: define void @use_workitem_id_y() #2 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_workitem_id_y() #1 {
%val = call i32 @llvm.amdgcn.workitem.id.y()
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_workitem_id_z() #3 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_workitem_id_z() #1 {
%val = call i32 @llvm.amdgcn.workitem.id.z()
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_workgroup_id_x() #4 {
define void @use_workgroup_id_x() #1 {
%val = call i32 @llvm.amdgcn.workgroup.id.x()
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
; HSA: define void @use_workgroup_id_y() #5 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_workgroup_id_y() #1 {
%val = call i32 @llvm.amdgcn.workgroup.id.y()
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_workgroup_id_z() #6 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_workgroup_id_z() #1 {
%val = call i32 @llvm.amdgcn.workgroup.id.z()
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_dispatch_ptr() #7 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_dispatch_ptr() #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
%dispatch.ptr = call i8 addrspace(4)* @llvm.amdgcn.dispatch.ptr()
store volatile i8 addrspace(4)* %dispatch.ptr, i8 addrspace(4)* addrspace(1)* undef
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_queue_ptr() #8 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_queue_ptr() #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
%queue.ptr = call i8 addrspace(4)* @llvm.amdgcn.queue.ptr()
store volatile i8 addrspace(4)* %queue.ptr, i8 addrspace(4)* addrspace(1)* undef
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_dispatch_id() #9 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_dispatch_id() #1 {
%val = call i64 @llvm.amdgcn.dispatch.id()
store volatile i64 %val, i64 addrspace(1)* undef
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_workgroup_id_y_workgroup_id_z() #10 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_workgroup_id_y_workgroup_id_z() #1 {
%val0 = call i32 @llvm.amdgcn.workgroup.id.y()
%val1 = call i32 @llvm.amdgcn.workgroup.id.z()
store volatile i32 %val0, i32 addrspace(1)* undef
store volatile i32 %val1, i32 addrspace(1)* undef
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_workitem_id_x() #1 {
define void @func_indirect_use_workitem_id_x() #1 {
call void @use_workitem_id_x()
ret void
}
; HSA: define void @kernel_indirect_use_workitem_id_x() #1 {
define void @kernel_indirect_use_workitem_id_x() #1 {
call void @use_workitem_id_x()
ret void
}
; HSA: define void @func_indirect_use_workitem_id_y() #2 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_workitem_id_y() #1 {
call void @use_workitem_id_y()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_workitem_id_z() #3 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_workitem_id_z() #1 {
call void @use_workitem_id_z()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_workgroup_id_x() #4 {
define void @func_indirect_use_workgroup_id_x() #1 {
call void @use_workgroup_id_x()
ret void
}
; HSA: define void @kernel_indirect_use_workgroup_id_x() #4 {
define void @kernel_indirect_use_workgroup_id_x() #1 {
call void @use_workgroup_id_x()
ret void
}
; HSA: define void @func_indirect_use_workgroup_id_y() #5 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_workgroup_id_y() #1 {
call void @use_workgroup_id_y()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_workgroup_id_z() #6 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_workgroup_id_z() #1 {
call void @use_workgroup_id_z()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_indirect_use_workgroup_id_y() #5 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_indirect_use_workgroup_id_y() #1 {
call void @func_indirect_use_workgroup_id_y()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @indirect_x2_use_workgroup_id_y() #5 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @indirect_x2_use_workgroup_id_y() #1 {
call void @func_indirect_indirect_use_workgroup_id_y()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_dispatch_ptr() #7 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_dispatch_ptr() #1 {
call void @use_dispatch_ptr()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_queue_ptr() #8 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_queue_ptr() #1 {
call void @use_queue_ptr()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_dispatch_id() #9 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_dispatch_id() #1 {
call void @use_dispatch_id()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_workgroup_id_y_workgroup_id_z() #11 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @func_indirect_use_workgroup_id_y_workgroup_id_z() #1 {
call void @func_indirect_use_workgroup_id_y_workgroup_id_z()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @recursive_use_workitem_id_y() #2 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @recursive_use_workitem_id_y() #1 {
%val = call i32 @llvm.amdgcn.workitem.id.y()
store volatile i32 %val, i32 addrspace(1)* undef
call void @recursive_use_workitem_id_y()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @call_recursive_use_workitem_id_y() #2 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @call_recursive_use_workitem_id_y() #1 {
call void @recursive_use_workitem_id_y()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_group_to_flat_addrspacecast(i32 addrspace(3)* %ptr) #8 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_group_to_flat_addrspacecast(i32 addrspace(3)* %ptr) #1 {
AMDGPU: Fix tests using old number for constant address space llvm-svn: 341770
2018-09-10 10:54:25 +08:00
%stof = addrspacecast i32 addrspace(3)* %ptr to i32 addrspace(4)*
store volatile i32 0, i32 addrspace(4)* %stof
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_group_to_flat_addrspacecast_gfx9(i32 addrspace(3)* %ptr) #12 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_group_to_flat_addrspacecast_gfx9(i32 addrspace(3)* %ptr) #2 {
AMDGPU: Fix tests using old number for constant address space llvm-svn: 341770
2018-09-10 10:54:25 +08:00
%stof = addrspacecast i32 addrspace(3)* %ptr to i32 addrspace(4)*
store volatile i32 0, i32 addrspace(4)* %stof
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_group_to_flat_addrspacecast_queue_ptr_gfx9(i32 addrspace(3)* %ptr) #13 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @use_group_to_flat_addrspacecast_queue_ptr_gfx9(i32 addrspace(3)* %ptr) #2 {
AMDGPU: Fix tests using old number for constant address space llvm-svn: 341770
2018-09-10 10:54:25 +08:00
%stof = addrspacecast i32 addrspace(3)* %ptr to i32 addrspace(4)*
store volatile i32 0, i32 addrspace(4)* %stof
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
call void @func_indirect_use_queue_ptr()
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @indirect_use_group_to_flat_addrspacecast() #8 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @indirect_use_group_to_flat_addrspacecast() #1 {
call void @use_group_to_flat_addrspacecast(i32 addrspace(3)* null)
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @indirect_use_group_to_flat_addrspacecast_gfx9() #11 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @indirect_use_group_to_flat_addrspacecast_gfx9() #1 {
call void @use_group_to_flat_addrspacecast_gfx9(i32 addrspace(3)* null)
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @indirect_use_group_to_flat_addrspacecast_queue_ptr_gfx9() #8 {
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
define void @indirect_use_group_to_flat_addrspacecast_queue_ptr_gfx9() #1 {
call void @use_group_to_flat_addrspacecast_queue_ptr_gfx9(i32 addrspace(3)* null)
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @use_kernarg_segment_ptr() #14 {
AMDGPU: Detect kernarg segment pointer This is necessary to pass the kernarg segment pointer to callee functions. Also don't unconditionally enable for kernels. llvm-svn: 307978
2017-07-14 08:11:13 +08:00
define void @use_kernarg_segment_ptr() #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
%kernarg.segment.ptr = call i8 addrspace(4)* @llvm.amdgcn.kernarg.segment.ptr()
store volatile i8 addrspace(4)* %kernarg.segment.ptr, i8 addrspace(4)* addrspace(1)* undef
AMDGPU: Detect kernarg segment pointer This is necessary to pass the kernarg segment pointer to callee functions. Also don't unconditionally enable for kernels. llvm-svn: 307978
2017-07-14 08:11:13 +08:00
ret void
}
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: define void @func_indirect_use_kernarg_segment_ptr() #14 {
AMDGPU: Detect kernarg segment pointer This is necessary to pass the kernarg segment pointer to callee functions. Also don't unconditionally enable for kernels. llvm-svn: 307978
2017-07-14 08:11:13 +08:00
define void @func_indirect_use_kernarg_segment_ptr() #1 {
call void @use_kernarg_segment_ptr()
ret void
}
AMDGPU: Annotate implicitarg.ptr usage We need to pass something to functions for this to work. It isn't derivable just from the kernarg segment pointer because the implicit arguments are placed after the kernel arguments. Also fixes missing test for the intrinsic. llvm-svn: 309398
2017-07-28 23:52:08 +08:00
; HSA: define amdgpu_kernel void @kern_use_implicitarg_ptr() #15 {
define amdgpu_kernel void @kern_use_implicitarg_ptr() #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
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
store volatile i8 addrspace(4)* %implicitarg.ptr, i8 addrspace(4)* addrspace(1)* undef
AMDGPU: Annotate implicitarg.ptr usage We need to pass something to functions for this to work. It isn't derivable just from the kernarg segment pointer because the implicit arguments are placed after the kernel arguments. Also fixes missing test for the intrinsic. llvm-svn: 309398
2017-07-28 23:52:08 +08:00
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define void @use_implicitarg_ptr() #16 {
AMDGPU: Detect kernarg segment pointer This is necessary to pass the kernarg segment pointer to callee functions. Also don't unconditionally enable for kernels. llvm-svn: 307978
2017-07-14 08:11:13 +08:00
define void @use_implicitarg_ptr() #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
%implicitarg.ptr = call i8 addrspace(4)* @llvm.amdgcn.implicitarg.ptr()
store volatile i8 addrspace(4)* %implicitarg.ptr, i8 addrspace(4)* addrspace(1)* undef
AMDGPU: Detect kernarg segment pointer This is necessary to pass the kernarg segment pointer to callee functions. Also don't unconditionally enable for kernels. llvm-svn: 307978
2017-07-14 08:11:13 +08:00
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define void @func_indirect_use_implicitarg_ptr() #16 {
AMDGPU: Detect kernarg segment pointer This is necessary to pass the kernarg segment pointer to callee functions. Also don't unconditionally enable for kernels. llvm-svn: 307978
2017-07-14 08:11:13 +08:00
define void @func_indirect_use_implicitarg_ptr() #1 {
call void @use_implicitarg_ptr()
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: declare void @external.func() #17
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
declare void @external.func() #3
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define internal void @defined.func() #17 {
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
define internal void @defined.func() #3 {
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define void @func_call_external() #17 {
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
define void @func_call_external() #3 {
call void @external.func()
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define void @func_call_defined() #17 {
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
define void @func_call_defined() #3 {
call void @defined.func()
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define void @func_call_asm() #18 {
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
define void @func_call_asm() #3 {
call void asm sideeffect "", ""() #3
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define amdgpu_kernel void @kern_call_external() #19 {
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
define amdgpu_kernel void @kern_call_external() #3 {
call void @external.func()
ret void
}
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: define amdgpu_kernel void @func_kern_defined() #19 {
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
define amdgpu_kernel void @func_kern_defined() #3 {
call void @defined.func()
ret void
}
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
attributes #0 = { nounwind readnone speculatable }
attributes #1 = { nounwind "target-cpu"="fiji" }
attributes #2 = { nounwind "target-cpu"="gfx900" }
AMDGPU: Annotate necessity of flat-scratch-init As an approximation of the existing handling to avoid regressions. Fixes using too many registers with calls on subtargets with the SGPR allocation bug. llvm-svn: 308326
2017-07-19 00:44:58 +08:00
attributes #3 = { nounwind }
AMDGPU: Annotate call graph with used features Previously this wouldn't detect used features indirectly used in callee functions. llvm-svn: 307967
2017-07-14 05:43:42 +08:00
; HSA: attributes #0 = { nounwind readnone speculatable }
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: attributes #1 = { nounwind "amdgpu-work-item-id-x" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #2 = { nounwind "amdgpu-work-item-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #3 = { nounwind "amdgpu-work-item-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #4 = { nounwind "amdgpu-work-group-id-x" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #5 = { nounwind "amdgpu-work-group-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #6 = { nounwind "amdgpu-work-group-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #7 = { nounwind "amdgpu-dispatch-ptr" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #8 = { nounwind "amdgpu-queue-ptr" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #9 = { nounwind "amdgpu-dispatch-id" "target-cpu"="fiji" "uniform-work-group-size"="false" }
AMDGPU: Annotate features from x work item/group IDs. This wasn't necessary before since they are always enabled for kernels, but this is necessary if they need to be forwarded to a callable function. llvm-svn: 308226
2017-07-18 06:35:50 +08:00
; HSA: attributes #10 = { nounwind "amdgpu-work-group-id-y" "amdgpu-work-group-id-z" "target-cpu"="fiji" }
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: attributes #11 = { nounwind "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #12 = { nounwind "target-cpu"="gfx900" "uniform-work-group-size"="false" }
; HSA: attributes #13 = { nounwind "amdgpu-queue-ptr" "target-cpu"="gfx900" "uniform-work-group-size"="false" }
; HSA: attributes #14 = { nounwind "amdgpu-kernarg-segment-ptr" "target-cpu"="fiji" "uniform-work-group-size"="false" }
AMDGPU: Annotate implicitarg.ptr usage We need to pass something to functions for this to work. It isn't derivable just from the kernarg segment pointer because the implicit arguments are placed after the kernel arguments. Also fixes missing test for the intrinsic. llvm-svn: 309398
2017-07-28 23:52:08 +08:00
; HSA: attributes #15 = { nounwind "amdgpu-implicitarg-ptr" "target-cpu"="fiji" }
AMDGPU: Handle "uniform-work-group-size" attribute (fix for RADV) A previous patch for "uniform-work-group-size" attribute was found to break some RADV and possibly radeon SI tests and had to be retracted. This patch fixes that. Differential Revision: http://reviews.llvm.org/D58993 llvm-svn: 355574
2019-03-07 08:54:04 +08:00
; HSA: attributes #16 = { nounwind "amdgpu-implicitarg-ptr" "target-cpu"="fiji" "uniform-work-group-size"="false" }
; HSA: attributes #17 = { nounwind "uniform-work-group-size"="false" }
; HSA: attributes #18 = { nounwind }
; HSA: attributes #19 = { nounwind "amdgpu-flat-scratch" "uniform-work-group-size"="false" }