60b1967c39
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
101 lines
7.4 KiB
YAML
101 lines
7.4 KiB
YAML
# RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -stress-regalloc=3 -start-before=greedy -stop-after=stack-slot-coloring -o - %s | FileCheck -check-prefixes=SHARE,GCN %s
|
|
# RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -stress-regalloc=3 -start-before=greedy -stop-after=stack-slot-coloring -no-stack-slot-sharing -o - %s | FileCheck -check-prefixes=NOSHARE,GCN %s
|
|
|
|
# Make sure that stack slot coloring doesn't try to merge frame
|
|
# indexes used for SGPR spilling with those that aren't.
|
|
# Even when stack slot sharing was disabled, it was still moving the
|
|
# FI ID used for an SGPR spill to a normal frame index.
|
|
|
|
--- |
|
|
|
|
define void @sgpr_spill_wrong_stack_id(float addrspace(1)* nocapture readnone %arg, float addrspace(1)* noalias %arg1) {
|
|
bb:
|
|
%tmp = load i32, i32 addrspace(1)* null, align 4
|
|
call void @func(i32 undef)
|
|
call void @func(i32 %tmp)
|
|
unreachable
|
|
}
|
|
|
|
declare void @func(i32)
|
|
|
|
...
|
|
---
|
|
|
|
# GCN-LABEL: name: sgpr_spill_wrong_stack_id
|
|
# SHARE: stack:
|
|
# SHARE: - { id: 0, name: '', type: spill-slot, offset: 0, size: 4, alignment: 4,
|
|
# SHARE: stack-id: default, callee-saved-register: '', callee-saved-restored: true,
|
|
# SHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
# SHARE: - { id: 1, name: '', type: spill-slot, offset: 0, size: 8, alignment: 4,
|
|
# SHARE: stack-id: sgpr-spill, callee-saved-register: '', callee-saved-restored: true,
|
|
# SHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
# SHARE: - { id: 2, name: '', type: spill-slot, offset: 0, size: 4, alignment: 4,
|
|
# SHARE: stack-id: sgpr-spill, callee-saved-register: '', callee-saved-restored: true,
|
|
# SHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
|
|
# SHARE: SI_SPILL_S32_SAVE $sgpr32, %stack.2, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (store 4 into %stack.2, addrspace 5)
|
|
# SHARE: SI_SPILL_V32_SAVE killed $vgpr0, %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
|
|
# SHARE: SI_SPILL_S64_SAVE killed renamable $sgpr4_sgpr5, %stack.1, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (store 8 into %stack.1, align 4, addrspace 5)
|
|
# SHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 8 from %stack.1, align 4, addrspace 5)
|
|
# SHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit undef $vgpr0
|
|
# SHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.2, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 4 from %stack.2, addrspace 5)
|
|
# SHARE: $vgpr0 = SI_SPILL_V32_RESTORE %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
|
|
# SHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 8 from %stack.1, align 4, addrspace 5)
|
|
# SHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0
|
|
# SHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.2, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 4 from %stack.2, addrspace 5)
|
|
|
|
# NOSHARE: stack:
|
|
# NOSHARE: - { id: 0, name: '', type: spill-slot, offset: 0, size: 4, alignment: 4,
|
|
# NOSHARE: stack-id: default, callee-saved-register: '', callee-saved-restored: true,
|
|
# NOSHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
# NOSHARE: - { id: 1, name: '', type: spill-slot, offset: 0, size: 8, alignment: 4,
|
|
# NOSHARE: stack-id: sgpr-spill, callee-saved-register: '', callee-saved-restored: true,
|
|
# NOSHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
# NOSHARE: - { id: 2, name: '', type: spill-slot, offset: 0, size: 4, alignment: 4,
|
|
# NOSHARE: stack-id: sgpr-spill, callee-saved-register: '', callee-saved-restored: true,
|
|
# NOSHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
# NOSHARE: - { id: 3, name: '', type: spill-slot, offset: 0, size: 4, alignment: 4,
|
|
# NOSHARE: stack-id: sgpr-spill, callee-saved-register: '', callee-saved-restored: true,
|
|
# NOSHARE: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
|
|
|
|
# NOSHARE: SI_SPILL_S32_SAVE $sgpr32, %stack.2, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (store 4 into %stack.2, addrspace 5)
|
|
# NOSHARE: SI_SPILL_V32_SAVE killed $vgpr0, %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
|
|
# NOSHARE: SI_SPILL_S64_SAVE killed renamable $sgpr4_sgpr5, %stack.1, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (store 8 into %stack.1, align 4, addrspace 5)
|
|
# NOSHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 8 from %stack.1, align 4, addrspace 5)
|
|
# NOSHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit undef $vgpr0
|
|
# NOSHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.2, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 4 from %stack.2, addrspace 5)
|
|
# NOSHARE: SI_SPILL_S32_SAVE $sgpr32, %stack.3, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (store 4 into %stack.3, addrspace 5)
|
|
# NOSHARE: $vgpr0 = SI_SPILL_V32_RESTORE %stack.0, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
|
|
# NOSHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 8 from %stack.1, align 4, addrspace 5)
|
|
# NOSHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $vgpr0
|
|
# NOSHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.3, implicit $exec, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr32 :: (load 4 from %stack.3, addrspace 5)
|
|
|
|
...
|
|
|
|
name: sgpr_spill_wrong_stack_id
|
|
tracksRegLiveness: true
|
|
frameInfo:
|
|
hasCalls: true
|
|
machineFunctionInfo:
|
|
scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
|
|
frameOffsetReg: $sgpr32
|
|
stackPtrOffsetReg: $sgpr32
|
|
body: |
|
|
bb.0:
|
|
%0:sreg_32_xm0 = COPY $sgpr32
|
|
%1:vreg_64 = IMPLICIT_DEF
|
|
%2:vgpr_32 = FLAT_LOAD_DWORD %1, 0, 0, 0, 0, implicit $exec, implicit $flat_scr
|
|
%3:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
|
|
ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
|
|
dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit undef $vgpr0
|
|
$sgpr32 = COPY %0
|
|
%4:sreg_32_xm0 = COPY $sgpr32
|
|
ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
|
|
ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
|
|
$vgpr0 = COPY %2
|
|
dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit killed $vgpr0
|
|
$sgpr32 = COPY %4
|
|
ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
|
|
|
|
...
|