mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
59de807f62
This is the groundwork required to implement strictfp. For now, this should be NFC for regular instructoins (many instructions just gain an extra use of a reserved register). Regalloc won't rematerialize instructions with reads of physical registers, but we were suffering from that anyway with the exec reads. Should add it for all the related FP uses (possibly with some extras). I did not add it to either the gpr index mode instructions (or every single VALU instruction) since it's a ridiculous feature already modeled as an arbitrary side effect. Also work towards marking instructions with FP exceptions. This doesn't actually set the bit yet since this would start to change codegen. It seems nofpexcept is currently not implied from the regular IR FP operations. Add it to some MIR tests where I think it might matter.
96 lines
3.0 KiB
YAML
96 lines
3.0 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GCN,XNACK,GCX9 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GCN,NOXNACK,GFX9 %s
|
|
# RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=-WavefrontSize32,+WavefrontSize64 -verify-machineinstrs -run-pass post-RA-hazard-rec %s -o - | FileCheck -check-prefixes=GCN,NOXNACK,GFX10 %s
|
|
|
|
# GCN-LABEL: name: break_smem_clause_simple_load_smrd8_ptr_hidden_bundle
|
|
# GCN: bb.0:
|
|
# GCN: }
|
|
# XNACK-NEXT: S_NOP
|
|
# NOXNACK-NOT: S_NOP
|
|
# GCN: S_LOAD_DWORDX2_IMM
|
|
---
|
|
name: break_smem_clause_simple_load_smrd8_ptr_hidden_bundle
|
|
body: |
|
|
bb.0:
|
|
BUNDLE implicit-def $sgpr6_sgpr7 {
|
|
$sgpr10_sgpr11 = S_LOAD_DWORDX2_IMM $sgpr12_sgpr13, 0, 0, 0
|
|
}
|
|
$sgpr14_sgpr15 = S_LOAD_DWORDX2_IMM $sgpr10_sgpr11, 0, 0, 0
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
# GFX9-LABEL: name: hazard_precedes_bundle
|
|
# GFX9: S_MOV_B32
|
|
# GFX9-NEXT: S_NOP
|
|
# GFX9: BUNDLE
|
|
# GFX9-NEXT: S_NOP
|
|
---
|
|
name: hazard_precedes_bundle
|
|
body: |
|
|
bb.0:
|
|
$m0 = S_MOV_B32 $sgpr7
|
|
S_SENDMSG 3, implicit $exec, implicit $m0
|
|
$m0 = S_MOV_B32 $sgpr8
|
|
BUNDLE implicit-def $vgpr0 {
|
|
$vgpr0 = V_INTERP_P1_F32 killed $vgpr4, 0, 0, implicit $mode, implicit $m0, implicit $exec
|
|
}
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
# GCN-LABEL: name: vmem_vcc_hazard_ignore_bundle_instr
|
|
# GCN: S_LOAD_DWORDX2_IMM
|
|
# GCN-NEXT: }
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN: BUFFER_LOAD_DWORD_OFFEN
|
|
---
|
|
name: vmem_vcc_hazard_ignore_bundle_instr
|
|
body: |
|
|
bb.0:
|
|
$sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
|
|
$vgpr0 = IMPLICIT_DEF
|
|
BUNDLE implicit-def $vgpr1, implicit $vgpr0, implicit $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec {
|
|
$vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
|
|
}
|
|
BUNDLE implicit-def $sgpr0_sgpr1, implicit $sgpr10_sgpr11 {
|
|
$sgpr0_sgpr1 = S_LOAD_DWORDX2_IMM $sgpr10_sgpr11, 0, 0, 0
|
|
}
|
|
$vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, 0, 0, implicit $exec
|
|
S_ENDPGM 0
|
|
...
|
|
|
|
# GCN-LABEL: name: vmem_vcc_min_of_two_after_bundle
|
|
# GCN: bb.2:
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: S_NOP
|
|
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
|
|
---
|
|
name: vmem_vcc_min_of_two_after_bundle
|
|
body: |
|
|
bb.0:
|
|
successors: %bb.2
|
|
|
|
BUNDLE implicit-def $vgpr1, implicit $vgpr0 {
|
|
$sgpr0_sgpr1_sgpr2_sgpr3 = IMPLICIT_DEF
|
|
$vgpr0 = IMPLICIT_DEF
|
|
$vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
|
|
}
|
|
S_NOP 0
|
|
S_BRANCH %bb.2
|
|
|
|
bb.1:
|
|
successors: %bb.2
|
|
|
|
BUNDLE implicit-def $vgpr1, implicit $vgpr0 {
|
|
$vgpr1 = V_ADDC_U32_e32 $vgpr0, $vgpr0, implicit-def $vcc, implicit $vcc, implicit $exec
|
|
}
|
|
|
|
bb.2:
|
|
$vgpr1 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, $vcc_lo, 0, 0, 0, 0, 0, 0, implicit $exec
|
|
...
|