maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Restore atomic fp feature on FP atomic instruction definitions 

9931b1f7a4 switched this to checking for
the two specific subtargets, instead of the dedicated feature. This
broke supporting functions which force added the feature when emitting
targets that do not actually support them. This stil does not work for
the targets that use the gfx6/7 or gfx10 encodings.
This commit is contained in:
Matt Arsenault 2021-04-09 18:40:59 -04:00
parent 2786e673c7
commit ed633a1daa
2 changed files with 27 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/AMDGPU/FLATInstructions.td
View File

@ -1539,7 +1539,7 @@ defm SCRATCH_STORE_DWORDX2 : FLAT_Real_AllAddr_vi <0x1d>;
defm SCRATCH_STORE_DWORDX3 : FLAT_Real_AllAddr_vi <0x1e>;
defm SCRATCH_STORE_DWORDX4 : FLAT_Real_AllAddr_vi <0x1f>;
let SubtargetPredicate = isGFX908orGFX90A in {
let SubtargetPredicate = HasAtomicFaddInsts in {
defm GLOBAL_ATOMIC_ADD_F32 : FLAT_Global_Real_Atomics_vi <0x04d, 0>;
defm GLOBAL_ATOMIC_PK_ADD_F16 : FLAT_Global_Real_Atomics_vi <0x04e, 0>;
}

26
llvm/test/CodeGen/AMDGPU/global-atomics-fp-wrong-subtarget.ll Normal file
View File

@ -0,0 +1,26 @@
; RUN: llc -march=amdgcn -mcpu=gfx803 < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=gfx803 -filetype=obj < %s | llvm-objdump --triple=amdgcn--amdhsa --mcpu=gfx803 -d - | FileCheck -check-prefix=DISASSEMBLY-VI %s
; Make sure we can encode and don't fail on functions which have
; instructions not actually supported by the subtarget.
; FIXME: This will still fail for gfx6/7 and gfx10 subtargets.
; DISASSEMBLY-VI: .long 0xdd348000 // {{[0-9]+}}: DD348000
; DISASSEMBLY-VI-NEXT: v_cndmask_b32_e32 v0, v0, v0, vcc // {{[0-9]+}}: 00000100
define amdgpu_kernel void @global_atomic_fadd_noret_f32_wrong_subtarget(float addrspace(1)* %ptr) #0 {
; GCN-LABEL: global_atomic_fadd_noret_f32_wrong_subtarget:
; GCN: ; %bb.0:
; GCN-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
; GCN-NEXT: v_mov_b32_e32 v0, 0
; GCN-NEXT: v_mov_b32_e32 v1, 4.0
; GCN-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GCN-NEXT: global_atomic_add_f32 v0, v1, s[0:1]
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: buffer_wbinvl1_vol
; GCN-NEXT: s_endpgm
%result = atomicrmw fadd float addrspace(1)* %ptr, float 4.0 syncscope("agent") seq_cst
ret void
}
attributes #0 = { "denormal-fp-math-f32"="preserve-sign,preserve-sign" "target-features"="+atomic-fadd-insts" "amdgpu-unsafe-fp-atomics"="true" }