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/large-alloca-compute.ll

58 lines
2.3 KiB
LLVM
Raw Normal View History

AMDGPU: Remove SIPrepareScratchRegs It does not work because of emergency stack slots. This pass was supposed to eliminate dummy registers for the spill instructions, but the register scavenger can introduce more during PrologEpilogInserter, so some would end up left behind if they were needed. The potential for spilling the scratch resource descriptor and offset register makes doing something like this overly complicated. Reserve registers to use for the resource descriptor and use them directly in eliminateFrameIndex. Also removes creating another scratch resource descriptor when directly selecting scratch MUBUF instructions. The choice of which registers are reserved is temporary. For now it attempts to pick the next available registers after the user and system SGPRs. llvm-svn: 254329
2015-12-01 05:15:53 +08:00
; RUN: llc -march=amdgcn -mcpu=bonaire < %s | FileCheck -check-prefix=GCN -check-prefix=CI -check-prefix=ALL %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=ALL %s
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=bonaire -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefix=GCNHSA -check-prefix=CIHSA -check-prefix=ALL %s
; RUN: llc -march=amdgcn -mcpu=tonga -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefix=GCNHSA -check-prefix=VIHSA -check-prefix=ALL %s
AMDGPU: Remove SIPrepareScratchRegs It does not work because of emergency stack slots. This pass was supposed to eliminate dummy registers for the spill instructions, but the register scavenger can introduce more during PrologEpilogInserter, so some would end up left behind if they were needed. The potential for spilling the scratch resource descriptor and offset register makes doing something like this overly complicated. Reserve registers to use for the resource descriptor and use them directly in eliminateFrameIndex. Also removes creating another scratch resource descriptor when directly selecting scratch MUBUF instructions. The choice of which registers are reserved is temporary. For now it attempts to pick the next available registers after the user and system SGPRs. llvm-svn: 254329
2015-12-01 05:15:53 +08:00
; FIXME: align on alloca seems to be ignored for private_segment_alignment
; ALL-LABEL: {{^}}large_alloca_compute_shader:
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
; GCN: s_mov_b32 s8, SCRATCH_RSRC_DWORD0
; GCN: s_mov_b32 s9, SCRATCH_RSRC_DWORD1
; GCN: s_mov_b32 s10, -1
; CI: s_mov_b32 s11, 0x80f000
; VI: s_mov_b32 s11, 0x800000
AMDGPU: Remove SIPrepareScratchRegs It does not work because of emergency stack slots. This pass was supposed to eliminate dummy registers for the spill instructions, but the register scavenger can introduce more during PrologEpilogInserter, so some would end up left behind if they were needed. The potential for spilling the scratch resource descriptor and offset register makes doing something like this overly complicated. Reserve registers to use for the resource descriptor and use them directly in eliminateFrameIndex. Also removes creating another scratch resource descriptor when directly selecting scratch MUBUF instructions. The choice of which registers are reserved is temporary. For now it attempts to pick the next available registers after the user and system SGPRs. llvm-svn: 254329
2015-12-01 05:15:53 +08:00
; GCNHSA: .amd_kernel_code_t
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
; GCNHSA: compute_pgm_rsrc2_scratch_en = 1
; GCNHSA: compute_pgm_rsrc2_user_sgpr = 6
; GCNHSA: compute_pgm_rsrc2_tgid_x_en = 1
; GCNHSA: compute_pgm_rsrc2_tgid_y_en = 0
; GCNHSA: compute_pgm_rsrc2_tgid_z_en = 0
; GCNHSA: compute_pgm_rsrc2_tg_size_en = 0
; GCNHSA: compute_pgm_rsrc2_tidig_comp_cnt = 0
; GCNHSA: enable_sgpr_private_segment_buffer = 1
; GCNHSA: enable_sgpr_dispatch_ptr = 0
; GCNHSA: enable_sgpr_queue_ptr = 0
; GCNHSA: enable_sgpr_kernarg_segment_ptr = 1
; GCNHSA: enable_sgpr_dispatch_id = 0
; GCNHSA: enable_sgpr_flat_scratch_init = 0
; GCNHSA: enable_sgpr_private_segment_size = 0
; GCNHSA: enable_sgpr_grid_workgroup_count_x = 0
; GCNHSA: enable_sgpr_grid_workgroup_count_y = 0
; GCNHSA: enable_sgpr_grid_workgroup_count_z = 0
; GCNHSA: workitem_private_segment_byte_size = 0
AMDGPU: Remove SIPrepareScratchRegs It does not work because of emergency stack slots. This pass was supposed to eliminate dummy registers for the spill instructions, but the register scavenger can introduce more during PrologEpilogInserter, so some would end up left behind if they were needed. The potential for spilling the scratch resource descriptor and offset register makes doing something like this overly complicated. Reserve registers to use for the resource descriptor and use them directly in eliminateFrameIndex. Also removes creating another scratch resource descriptor when directly selecting scratch MUBUF instructions. The choice of which registers are reserved is temporary. For now it attempts to pick the next available registers after the user and system SGPRs. llvm-svn: 254329
2015-12-01 05:15:53 +08:00
; GCNHSA: private_segment_alignment = 4
; GCNHSA: .end_amd_kernel_code_t
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
; GCNHSA: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], s7 offen
; GCNHSA: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], s7 offen
AMDGPU: Remove SIPrepareScratchRegs It does not work because of emergency stack slots. This pass was supposed to eliminate dummy registers for the spill instructions, but the register scavenger can introduce more during PrologEpilogInserter, so some would end up left behind if they were needed. The potential for spilling the scratch resource descriptor and offset register makes doing something like this overly complicated. Reserve registers to use for the resource descriptor and use them directly in eliminateFrameIndex. Also removes creating another scratch resource descriptor when directly selecting scratch MUBUF instructions. The choice of which registers are reserved is temporary. For now it attempts to pick the next available registers after the user and system SGPRs. llvm-svn: 254329
2015-12-01 05:15:53 +08:00
; Scratch size = alloca size + emergency stack slot
; ALL: ; ScratchSize: 32772
define void @large_alloca_compute_shader(i32 %x, i32 %y) #0 {
%large = alloca [8192 x i32], align 4
%gep = getelementptr [8192 x i32], [8192 x i32]* %large, i32 0, i32 8191
store volatile i32 %x, i32* %gep
%gep1 = getelementptr [8192 x i32], [8192 x i32]* %large, i32 0, i32 %y
%val = load volatile i32, i32* %gep1
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
attributes #0 = { nounwind }