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-graphics.ll

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

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
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=carrizo -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=VI -check-prefix=ALL %s
AMDGPU: Buffer descriptor changes for GFX9 Reviewers: arsenm Subscribers: qcolombet, kzhuravl, wdng, nhaehnle, yaxunl, tony-tye, dstuttard, tpr Differential Revision: https://reviews.llvm.org/D31158 llvm-svn: 298397
2017-03-22 01:00:39 +08:00
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -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
; ALL-LABEL: {{^}}large_alloca_pixel_shader:
[AMDGPU] Add Scratch Wave Offset to Scratch Buffer Descriptor in entry functions Add the scratch wave offset to the scratch buffer descriptor (SRSrc) in the entry function prologue. This allows us to removes the scratch wave offset register from the calling convention ABI. As part of this change, allow the use of an inline constant zero for the SOffset of MUBUF instructions accessing the stack in entry functions when a frame pointer is not requested/required. Entry functions with calls still need to set up the calling convention ABI stack pointer register, and reference it in order to address arguments of called functions. The ABI stack pointer register remains unswizzled, but is now wave-relative instead of queue-relative. Non-entry functions also use an inline constant zero SOffset for wave-relative scratch access, but continue to use the stack and frame pointers as before. When the stack or frame pointer is converted to a swizzled offset it is now scaled directly, as the scratch wave offset no longer needs to be subtracted first. Update llvm/docs/AMDGPUUsage.rst to reflect these changes to the calling convention. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75138
2020-01-22 06:27:57 +08:00
; GCN-DAG: s_mov_b32 s4, SCRATCH_RSRC_DWORD0
; GCN-DAG: s_mov_b32 s5, SCRATCH_RSRC_DWORD1
; GCN-DAG: s_mov_b32 s6, -1
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
[AMDGPU] Add Scratch Wave Offset to Scratch Buffer Descriptor in entry functions Add the scratch wave offset to the scratch buffer descriptor (SRSrc) in the entry function prologue. This allows us to removes the scratch wave offset register from the calling convention ABI. As part of this change, allow the use of an inline constant zero for the SOffset of MUBUF instructions accessing the stack in entry functions when a frame pointer is not requested/required. Entry functions with calls still need to set up the calling convention ABI stack pointer register, and reference it in order to address arguments of called functions. The ABI stack pointer register remains unswizzled, but is now wave-relative instead of queue-relative. Non-entry functions also use an inline constant zero SOffset for wave-relative scratch access, but continue to use the stack and frame pointers as before. When the stack or frame pointer is converted to a swizzled offset it is now scaled directly, as the scratch wave offset no longer needs to be subtracted first. Update llvm/docs/AMDGPUUsage.rst to reflect these changes to the calling convention. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75138
2020-01-22 06:27:57 +08:00
; CI-DAG: s_mov_b32 s7, 0xe8f000
; VI-DAG: s_mov_b32 s7, 0xe80000
; GFX9-DAG: s_mov_b32 s7, 0xe00000
; GCN: s_add_u32 s4, s4, s0
; GCN: s_addc_u32 s5, s5, 0
; GCN: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 offen
; GCN: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 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
; ALL: ; ScratchSize: 32772
AMDGPU: Add a shader calling convention This makes it possible to distinguish between mesa shaders and other kernels even in the presence of compute shaders. Patch By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Differential Revision: http://reviews.llvm.org/D18559 llvm-svn: 265589
2016-04-07 03:40:20 +08:00
define amdgpu_ps void @large_alloca_pixel_shader(i32 %x, i32 %y) #0 {
[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
%large = alloca [8192 x i32], align 4, addrspace(5)
%gep = getelementptr [8192 x i32], [8192 x i32] addrspace(5)* %large, i32 0, i32 8191
store volatile i32 %x, i32 addrspace(5)* %gep
%gep1 = getelementptr [8192 x i32], [8192 x i32] addrspace(5)* %large, i32 0, i32 %y
%val = load volatile i32, i32 addrspace(5)* %gep1
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
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
; ALL-LABEL: {{^}}large_alloca_pixel_shader_inreg:
[AMDGPU] Add Scratch Wave Offset to Scratch Buffer Descriptor in entry functions Add the scratch wave offset to the scratch buffer descriptor (SRSrc) in the entry function prologue. This allows us to removes the scratch wave offset register from the calling convention ABI. As part of this change, allow the use of an inline constant zero for the SOffset of MUBUF instructions accessing the stack in entry functions when a frame pointer is not requested/required. Entry functions with calls still need to set up the calling convention ABI stack pointer register, and reference it in order to address arguments of called functions. The ABI stack pointer register remains unswizzled, but is now wave-relative instead of queue-relative. Non-entry functions also use an inline constant zero SOffset for wave-relative scratch access, but continue to use the stack and frame pointers as before. When the stack or frame pointer is converted to a swizzled offset it is now scaled directly, as the scratch wave offset no longer needs to be subtracted first. Update llvm/docs/AMDGPUUsage.rst to reflect these changes to the calling convention. Tags: #llvm Differential Revision: https://reviews.llvm.org/D75138
2020-01-22 06:27:57 +08:00
; GCN-DAG: s_mov_b32 s4, SCRATCH_RSRC_DWORD0
; GCN-DAG: s_mov_b32 s5, SCRATCH_RSRC_DWORD1
; GCN-DAG: s_mov_b32 s6, -1
; CI-DAG: s_mov_b32 s7, 0xe8f000
; VI-DAG: s_mov_b32 s7, 0xe80000
; GFX9-DAG: s_mov_b32 s7, 0xe00000
; GCN: s_add_u32 s4, s4, s2
; GCN: s_addc_u32 s5, s5, 0
; GCN: buffer_store_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 offen
; GCN: buffer_load_dword {{v[0-9]+}}, {{v[0-9]+}}, s[4:7], 0 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
; ALL: ; ScratchSize: 32772
AMDGPU: Add a shader calling convention This makes it possible to distinguish between mesa shaders and other kernels even in the presence of compute shaders. Patch By: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl> Differential Revision: http://reviews.llvm.org/D18559 llvm-svn: 265589
2016-04-07 03:40:20 +08:00
define amdgpu_ps void @large_alloca_pixel_shader_inreg(i32 inreg %x, i32 inreg %y) #0 {
[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
%large = alloca [8192 x i32], align 4, addrspace(5)
%gep = getelementptr [8192 x i32], [8192 x i32] addrspace(5)* %large, i32 0, i32 8191
store volatile i32 %x, i32 addrspace(5)* %gep
%gep1 = getelementptr [8192 x i32], [8192 x i32] addrspace(5)* %large, i32 0, i32 %y
%val = load volatile i32, i32 addrspace(5)* %gep1
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
store volatile i32 %val, i32 addrspace(1)* undef
ret void
}
attributes #0 = { nounwind }