mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-02-01 13:11:39 +01:00
6705a324ed
The hardware has created a real mess in the naming for add/sub, which have been renamed basically every generation. Switch the carry out pseudos to have the gfx9/gfx10 names. We were using the original SI/CI v_add_i32/v_sub_i32 names. Later targets reintroduced these names as carryless instructions with a saturating clamp bit, which we do not define. Do this rename so we can unambiguously add these missing instructions. The carry-in versions should also be renamed, but at least those had a consistent _u32 name to begin with. The 16-bit instructions were also renamed, but aren't ambiguous. This does regress assembler error message quality in some cases. In mismatched wave32/wave64 situations, this will switch from "unsupported instruction" to "invalid operand", with the error pointing at the wrong position. I couldn't quite follow how the assembler selects these, but the previous behavior seemed accidental to me. It looked like there was a partial attempt to handle this which was never completed (i.e. there is an AMDGPUOperand::isBoolReg but it isn't used for anything).
66 lines
3.2 KiB
YAML
66 lines
3.2 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx803 -run-pass si-memory-legalizer %s -o - | FileCheck -check-prefix=GCN %s
|
|
|
|
---
|
|
|
|
# GCN-LABEL: name: multiple_mem_operands
|
|
|
|
# GCN-LABEL: bb.3:
|
|
# GCN: S_WAITCNT 3952
|
|
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFEN
|
|
# GCN-NEXT: S_WAITCNT 3952
|
|
# GCN-NEXT: BUFFER_WBINVL1_VOL
|
|
|
|
name: multiple_mem_operands
|
|
body: |
|
|
bb.0.entry:
|
|
successors: %bb.1(0x30000000), %bb.2(0x50000000)
|
|
liveins: $sgpr0_sgpr1, $sgpr3
|
|
|
|
$sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 44, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
|
|
$sgpr8 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
|
|
$sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM $sgpr0_sgpr1, 36, 0, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(4)* undef`)
|
|
$sgpr9 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
|
|
$sgpr10 = S_MOV_B32 4294967295, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
|
|
$sgpr11 = S_MOV_B32 15204352, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
|
|
$vgpr0 = V_MOV_B32_e32 1, implicit $exec
|
|
BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into `i32 addrspace(5)* undef`)
|
|
S_WAITCNT 127
|
|
S_CMP_LG_U32 killed $sgpr2, 0, implicit-def $scc
|
|
S_WAITCNT 3855
|
|
$vgpr0 = V_MOV_B32_e32 2, implicit $exec
|
|
$vgpr1 = V_MOV_B32_e32 32772, implicit $exec
|
|
BUFFER_STORE_DWORD_OFFEN killed $vgpr0, killed $vgpr1, $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into `i32 addrspace(5)* undef`)
|
|
S_CBRANCH_SCC0 %bb.1, implicit killed $scc
|
|
|
|
bb.2:
|
|
successors: %bb.3(0x80000000)
|
|
liveins: $sgpr0_sgpr1, $sgpr4_sgpr5, $sgpr3, $sgpr8_sgpr9_sgpr10_sgpr11
|
|
|
|
$sgpr0 = S_LOAD_DWORD_IMM killed $sgpr0_sgpr1, 52, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
|
|
S_WAITCNT 3855
|
|
$vgpr0 = V_MOV_B32_e32 32772, implicit $exec
|
|
S_BRANCH %bb.3
|
|
|
|
bb.1:
|
|
successors: %bb.3(0x80000000)
|
|
liveins: $sgpr0_sgpr1, $sgpr4_sgpr5, $sgpr3, $sgpr8_sgpr9_sgpr10_sgpr11
|
|
|
|
$sgpr0 = S_LOAD_DWORD_IMM killed $sgpr0_sgpr1, 48, 0, 0 :: (non-temporal dereferenceable invariant load 4 from `i32 addrspace(4)* undef`)
|
|
S_WAITCNT 3855
|
|
$vgpr0 = V_MOV_B32_e32 4, implicit $exec
|
|
|
|
bb.3:
|
|
liveins: $sgpr3, $sgpr4_sgpr5, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $sgpr0
|
|
|
|
S_WAITCNT 127
|
|
$sgpr0 = S_LSHL_B32 killed $sgpr0, 2, implicit-def dead $scc
|
|
$vgpr0 = V_ADD_CO_U32_e32 killed $sgpr0, killed $vgpr0, implicit-def dead $vcc, implicit $exec
|
|
$vgpr0 = BUFFER_LOAD_DWORD_OFFEN killed $vgpr0, killed $sgpr8_sgpr9_sgpr10_sgpr11, $sgpr3, 0, 0, 0, 0, 0, 0, implicit $exec :: (load syncscope("agent-one-as") unordered 4 from `i32 addrspace(1)* undef`), (load syncscope("workgroup-one-as") seq_cst 4 from `[8192 x i32] addrspace(5)* undef`)
|
|
$vgpr1 = V_MOV_B32_e32 $sgpr4, implicit $exec, implicit-def $vgpr1_vgpr2, implicit $sgpr4_sgpr5
|
|
$vgpr2 = V_MOV_B32_e32 killed $sgpr5, implicit $exec, implicit $sgpr4_sgpr5, implicit $exec
|
|
S_WAITCNT 3952
|
|
FLAT_STORE_DWORD killed $vgpr1_vgpr2, killed $vgpr0, 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 4 into `i32 addrspace(1)* undef`)
|
|
S_ENDPGM 0
|
|
|
|
...
|