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.AMDGPU.read.workdim.ll

38 lines
1.4 KiB
LLVM
Raw Normal View History

AMDGPU: Rework how private buffer passed for HSA If we know we have stack objects, we reserve the registers that the private buffer resource and wave offset are passed and use them directly. If not, reserve the last 5 SGPRs just in case we need to spill. After register allocation, try to pick the next available registers instead of the last SGPRs, and then insert copies from the inputs to the reserved registers in the progloue. This also only selectively enables all of the input registers which are really required instead of always enabling them. llvm-svn: 254331
2015-12-01 05:16:03 +08:00
; RUN: llc -march=amdgcn -mcpu=SI -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=SI-NOHSA -check-prefix=GCN-NOHSA -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=VI-NOHSA -check-prefix=GCN -check-prefix=GCN-NOHSA -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}read_workdim:
; EG: MEM_RAT_CACHELESS STORE_RAW [[VAL:T[0-9]+\.X]]
Revert "ScheduleDAGInstrs: Rework schedule graph builder." This works mostly fine but breaks some stage 1 builders when compiling compiler-rt on i386. Revert for further investigation as I can't see an obvious cause/fix. This reverts commit r254577. llvm-svn: 254586
2015-12-03 11:01:10 +08:00
; EG: MOV [[VAL]], KC0[2].Z
AMDGPU: Rework how private buffer passed for HSA If we know we have stack objects, we reserve the registers that the private buffer resource and wave offset are passed and use them directly. If not, reserve the last 5 SGPRs just in case we need to spill. After register allocation, try to pick the next available registers instead of the last SGPRs, and then insert copies from the inputs to the reserved registers in the progloue. This also only selectively enables all of the input registers which are really required instead of always enabling them. llvm-svn: 254331
2015-12-01 05:16:03 +08:00
; SI-NOHSA: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0xb
; VI-NOHSA: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0x2c
; GCN-NOHSA: v_mov_b32_e32 [[VVAL:v[0-9]+]], [[VAL]]
; GCN-NOHSA: buffer_store_dword [[VVAL]]
define void @read_workdim(i32 addrspace(1)* %out) {
entry:
%0 = call i32 @llvm.AMDGPU.read.workdim() #0
store i32 %0, i32 addrspace(1)* %out
ret void
}
; FUNC-LABEL: {{^}}read_workdim_known_bits:
; SI: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0xb
; VI: s_load_dword [[VAL:s[0-9]+]], s[0:1], 0x2c
; GCN-NOT: 0xff
; GCN: v_mov_b32_e32 [[VVAL:v[0-9]+]], [[VAL]]
; GCN: buffer_store_dword [[VVAL]]
define void @read_workdim_known_bits(i32 addrspace(1)* %out) {
entry:
%dim = call i32 @llvm.AMDGPU.read.workdim() #0
%shl = shl i32 %dim, 24
%shr = lshr i32 %shl, 24
store i32 %shr, i32 addrspace(1)* %out
ret void
}
declare i32 @llvm.AMDGPU.read.workdim() #0
attributes #0 = { readnone }