forked from OSchip/llvm-project
78 lines
3.5 KiB
LLVM
78 lines
3.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt -S -codegenprepare -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 < %s | FileCheck -check-prefix=OPT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
; Make sure we match the addressing mode offset of globla.atomic.fadd intrinsics across blocks.
|
|
|
|
define amdgpu_kernel void @test_sink_small_offset_global_atomic_fadd_f32(float addrspace(1)* %out, float addrspace(1)* %in) {
|
|
; OPT-LABEL: @test_sink_small_offset_global_atomic_fadd_f32(
|
|
; OPT-NEXT: entry:
|
|
; OPT-NEXT: [[OUT_GEP:%.*]] = getelementptr float, float addrspace(1)* [[OUT:%.*]], i32 999999
|
|
; OPT-NEXT: [[TID:%.*]] = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) [[ATTR3:#.*]]
|
|
; OPT-NEXT: [[CMP:%.*]] = icmp eq i32 [[TID]], 0
|
|
; OPT-NEXT: br i1 [[CMP]], label [[ENDIF:%.*]], label [[IF:%.*]]
|
|
; OPT: if:
|
|
; OPT-NEXT: [[TMP0:%.*]] = bitcast float addrspace(1)* [[IN:%.*]] to i8 addrspace(1)*
|
|
; OPT-NEXT: [[SUNKADDR:%.*]] = getelementptr i8, i8 addrspace(1)* [[TMP0]], i64 28
|
|
; OPT-NEXT: [[TMP1:%.*]] = bitcast i8 addrspace(1)* [[SUNKADDR]] to float addrspace(1)*
|
|
; OPT-NEXT: [[FADD2:%.*]] = call float @llvm.amdgcn.global.atomic.fadd.f32.p1f32.f32(float addrspace(1)* [[TMP1]], float 2.000000e+00)
|
|
; OPT-NEXT: [[VAL:%.*]] = load volatile float, float addrspace(1)* undef, align 4
|
|
; OPT-NEXT: br label [[ENDIF]]
|
|
; OPT: endif:
|
|
; OPT-NEXT: [[X:%.*]] = phi float [ [[VAL]], [[IF]] ], [ 0.000000e+00, [[ENTRY:%.*]] ]
|
|
; OPT-NEXT: store float [[X]], float addrspace(1)* [[OUT_GEP]], align 4
|
|
; OPT-NEXT: ret void
|
|
;
|
|
; GCN-LABEL: test_sink_small_offset_global_atomic_fadd_f32:
|
|
; GCN: ; %bb.0: ; %entry
|
|
; GCN-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GCN-NEXT: v_mbcnt_lo_u32_b32 v0, -1, 0
|
|
; GCN-NEXT: v_cmp_ne_u32_e32 vcc, 0, v0
|
|
; GCN-NEXT: v_mov_b32_e32 v0, 0
|
|
; GCN-NEXT: s_and_saveexec_b64 s[4:5], vcc
|
|
; GCN-NEXT: s_cbranch_execz BB0_2
|
|
; GCN-NEXT: ; %bb.1: ; %if
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: v_mov_b32_e32 v0, s2
|
|
; GCN-NEXT: v_mov_b32_e32 v1, s3
|
|
; GCN-NEXT: v_mov_b32_e32 v2, 2.0
|
|
; GCN-NEXT: global_atomic_add_f32 v[0:1], v2, off offset:28
|
|
; GCN-NEXT: global_load_dword v0, v[0:1], off
|
|
; GCN-NEXT: BB0_2: ; %endif
|
|
; GCN-NEXT: s_or_b64 exec, exec, s[4:5]
|
|
; GCN-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GCN-NEXT: v_mov_b32_e32 v1, s0
|
|
; GCN-NEXT: v_add_co_u32_e32 v1, vcc, 0x3d0000, v1
|
|
; GCN-NEXT: v_mov_b32_e32 v2, s1
|
|
; GCN-NEXT: v_addc_co_u32_e32 v2, vcc, 0, v2, vcc
|
|
; GCN-NEXT: s_waitcnt vmcnt(0)
|
|
; GCN-NEXT: global_store_dword v[1:2], v0, off offset:2300
|
|
; GCN-NEXT: s_endpgm
|
|
entry:
|
|
%out.gep = getelementptr float, float addrspace(1)* %out, i32 999999
|
|
%in.gep = getelementptr float, float addrspace(1)* %in, i32 7
|
|
%tid = call i32 @llvm.amdgcn.mbcnt.lo(i32 -1, i32 0) #0
|
|
%cmp = icmp eq i32 %tid, 0
|
|
br i1 %cmp, label %endif, label %if
|
|
|
|
if:
|
|
%fadd2 = call float @llvm.amdgcn.global.atomic.fadd.f32.p1f32.f32(float addrspace(1)* %in.gep, float 2.0)
|
|
%val = load volatile float, float addrspace(1)* undef
|
|
br label %endif
|
|
|
|
endif:
|
|
%x = phi float [ %val, %if ], [ 0.0, %entry ]
|
|
store float %x, float addrspace(1)* %out.gep
|
|
br label %done
|
|
|
|
done:
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #1
|
|
declare float @llvm.amdgcn.global.atomic.fadd.f32.p1f32.f32(float addrspace(1)* nocapture, float) #2
|
|
|
|
attributes #0 = { argmemonly nounwind }
|
|
attributes #1 = { nounwind readnone willreturn }
|
|
attributes #2 = { argmemonly nounwind willreturn }
|