forked from OSchip/llvm-project
585 lines
26 KiB
LLVM
585 lines
26 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -global-isel < %s -march=amdgcn -mcpu=gfx90a -verify-machineinstrs | FileCheck %s -check-prefix=GFX90A
|
|
|
|
declare double @llvm.amdgcn.buffer.atomic.fadd.f64(double, <4 x i32>, i32, i32, i1)
|
|
declare double @llvm.amdgcn.struct.buffer.atomic.fadd.f64(double, <4 x i32>, i32, i32, i32, i32 immarg)
|
|
declare double @llvm.amdgcn.raw.buffer.atomic.fadd.f64(double, <4 x i32>, i32, i32, i32 immarg)
|
|
declare double @llvm.amdgcn.struct.buffer.atomic.fmin.f64(double, <4 x i32>, i32, i32, i32, i32 immarg)
|
|
declare double @llvm.amdgcn.raw.buffer.atomic.fmin.f64(double, <4 x i32>, i32, i32, i32 immarg)
|
|
declare double @llvm.amdgcn.struct.buffer.atomic.fmax.f64(double, <4 x i32>, i32, i32, i32, i32 immarg)
|
|
declare double @llvm.amdgcn.raw.buffer.atomic.fmax.f64(double, <4 x i32>, i32, i32, i32 immarg)
|
|
declare double @llvm.amdgcn.global.atomic.fadd.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
declare double @llvm.amdgcn.global.atomic.fmin.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
declare double @llvm.amdgcn.global.atomic.fmax.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
declare double @llvm.amdgcn.flat.atomic.fadd.f64.p0f64.f64(double* %ptr, double %data)
|
|
declare double @llvm.amdgcn.flat.atomic.fmin.f64.p0f64.f64(double* %ptr, double %data)
|
|
declare double @llvm.amdgcn.flat.atomic.fmax.f64.p0f64.f64(double* %ptr, double %data)
|
|
declare double @llvm.amdgcn.ds.fadd.f64(double addrspace(3)* nocapture, double, i32, i32, i1)
|
|
|
|
define amdgpu_kernel void @buffer_atomic_add_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: buffer_atomic_add_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 offen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i1 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @buffer_atomic_add_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: buffer_atomic_add_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 offen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i1 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @buffer_atomic_add_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: buffer_atomic_add_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 4 offen glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i1 1)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @raw_buffer_atomic_add_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_add_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 offen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @raw_buffer_atomic_add_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_add_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 offen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @raw_buffer_atomic_add_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_add_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 4 offen glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i32 2)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @struct_buffer_atomic_add_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_add_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @struct_buffer_atomic_add_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_add_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 idxen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @struct_buffer_atomic_add_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_add_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fadd.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i32 0, i32 2)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @raw_buffer_atomic_min_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_min_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 offen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fmin.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @raw_buffer_atomic_min_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_min_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[0:3], 0 offen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fmin.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @raw_buffer_atomic_min_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_min_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 4 offen glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fmin.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i32 2)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @struct_buffer_atomic_min_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_min_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fmin.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @struct_buffer_atomic_min_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_min_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[0:3], 0 idxen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fmin.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @struct_buffer_atomic_min_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_min_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fmin.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i32 0, i32 2)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @raw_buffer_atomic_max_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_max_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 offen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fmax.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @raw_buffer_atomic_max_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_max_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[0:3], 0 offen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fmax.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @raw_buffer_atomic_max_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: raw_buffer_atomic_max_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 4 offen glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.raw.buffer.atomic.fmax.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i32 2)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @struct_buffer_atomic_max_noret_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_max_noret_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s8, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s8
|
|
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fmax.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @struct_buffer_atomic_max_rtn_f64(<4 x i32> inreg %rsrc, double %data, i32 %vindex) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_max_rtn_f64:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[0:3], 0 idxen glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: flat_store_dwordx2 v[0:1], v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fmax.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
|
|
store double %ret, double* undef
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @struct_buffer_atomic_max_rtn_f64_off4_slc(<4 x i32> inreg %rsrc, double %data, i32 %vindex, double addrspace(1)* %out) {
|
|
; GFX90A-LABEL: struct_buffer_atomic_max_rtn_f64_off4_slc:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x34
|
|
; GFX90A-NEXT: s_load_dword s10, s[0:1], 0x3c
|
|
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x44
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s10
|
|
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 glc slc
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.struct.buffer.atomic.fmax.f64(double %data, <4 x i32> %rsrc, i32 %vindex, i32 4, i32 0, i32 2)
|
|
store double %ret, double addrspace(1)* %out, align 8
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_atomic_fadd_f64_noret(double addrspace(1)* %ptr, double %data) {
|
|
; GFX90A-LABEL: global_atomic_fadd_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: global_atomic_add_f64 v[0:1], v[0:1], v[2:3], off glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.global.atomic.fadd.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_atomic_fmin_f64_noret(double addrspace(1)* %ptr, double %data) {
|
|
; GFX90A-LABEL: global_atomic_fmin_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: global_atomic_min_f64 v[0:1], v[0:1], v[2:3], off glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.global.atomic.fmin.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_atomic_fmax_f64_noret(double addrspace(1)* %ptr, double %data) {
|
|
; GFX90A-LABEL: global_atomic_fmax_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: global_atomic_max_f64 v[0:1], v[0:1], v[2:3], off glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.global.atomic.fmax.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
ret void
|
|
}
|
|
|
|
define double @global_atomic_fadd_f64_rtn(double addrspace(1)* %ptr, double %data) {
|
|
; GFX90A-LABEL: global_atomic_fadd_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: global_atomic_add_f64 v[0:1], v[0:1], v[2:3], off glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.global.atomic.fadd.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
ret double %ret
|
|
}
|
|
|
|
define double @global_atomic_fmax_f64_rtn(double addrspace(1)* %ptr, double %data) {
|
|
; GFX90A-LABEL: global_atomic_fmax_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: global_atomic_max_f64 v[0:1], v[0:1], v[2:3], off glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.global.atomic.fmax.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
ret double %ret
|
|
}
|
|
|
|
define double @global_atomic_fmin_f64_rtn(double addrspace(1)* %ptr, double %data) {
|
|
; GFX90A-LABEL: global_atomic_fmin_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: global_atomic_min_f64 v[0:1], v[0:1], v[2:3], off glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.global.atomic.fmin.f64.p1f64.f64(double addrspace(1)* %ptr, double %data)
|
|
ret double %ret
|
|
}
|
|
|
|
define amdgpu_kernel void @flat_atomic_fadd_f64_noret(double* %ptr, double %data) {
|
|
; GFX90A-LABEL: flat_atomic_fadd_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0f64.f64(double* %ptr, double %data)
|
|
ret void
|
|
}
|
|
|
|
define double @flat_atomic_fadd_f64_rtn(double* %ptr, double %data) {
|
|
; GFX90A-LABEL: flat_atomic_fadd_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0f64.f64(double* %ptr, double %data)
|
|
ret double %ret
|
|
}
|
|
|
|
define amdgpu_kernel void @flat_atomic_fmin_f64_noret(double* %ptr, double %data) {
|
|
; GFX90A-LABEL: flat_atomic_fmin_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: flat_atomic_min_f64 v[0:1], v[0:1], v[2:3] glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0f64.f64(double* %ptr, double %data)
|
|
ret void
|
|
}
|
|
|
|
define double @flat_atomic_fmin_f64_rtn(double* %ptr, double %data) {
|
|
; GFX90A-LABEL: flat_atomic_fmin_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: flat_atomic_min_f64 v[0:1], v[0:1], v[2:3] glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0f64.f64(double* %ptr, double %data)
|
|
ret double %ret
|
|
}
|
|
|
|
define amdgpu_kernel void @flat_atomic_fmax_f64_noret(double* %ptr, double %data) {
|
|
; GFX90A-LABEL: flat_atomic_fmax_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x24
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: flat_atomic_max_f64 v[0:1], v[0:1], v[2:3] glc
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0f64.f64(double* %ptr, double %data)
|
|
ret void
|
|
}
|
|
|
|
define double @flat_atomic_fmax_f64_rtn(double* %ptr, double %data) {
|
|
; GFX90A-LABEL: flat_atomic_fmax_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: flat_atomic_max_f64 v[0:1], v[0:1], v[2:3] glc
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0f64.f64(double* %ptr, double %data)
|
|
ret double %ret
|
|
}
|
|
|
|
define amdgpu_kernel void @local_atomic_fadd_f64_noret(double addrspace(3)* %ptr, double %data) {
|
|
; GFX90A-LABEL: local_atomic_fadd_f64_noret:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dword s4, s[0:1], 0x24
|
|
; GFX90A-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x2c
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s4
|
|
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[2:3], s[2:3] op_sel:[0,1]
|
|
; GFX90A-NEXT: ds_add_rtn_f64 v[0:1], v2, v[0:1]
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.ds.fadd.f64(double addrspace(3)* %ptr, double %data, i32 0, i32 0, i1 0)
|
|
ret void
|
|
}
|
|
|
|
define double @local_atomic_fadd_f64_rtn(double addrspace(3)* %ptr, double %data) {
|
|
; GFX90A-LABEL: local_atomic_fadd_f64_rtn:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: v_mov_b32_e32 v4, v1
|
|
; GFX90A-NEXT: v_mov_b32_e32 v5, v2
|
|
; GFX90A-NEXT: ds_add_rtn_f64 v[0:1], v0, v[4:5]
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = call double @llvm.amdgcn.ds.fadd.f64(double addrspace(3)* %ptr, double %data, i32 0, i32 0, i1 0)
|
|
ret double %ret
|
|
}
|
|
|
|
define amdgpu_kernel void @local_atomic_fadd_f64_noret_pat(double addrspace(3)* %ptr) {
|
|
; GFX90A-LABEL: local_atomic_fadd_f64_noret_pat:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_load_dword s0, s[0:1], 0x24
|
|
; GFX90A-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NEXT: v_mov_b32_e32 v1, 0x40100000
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, s0
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: ds_add_rtn_f64 v[0:1], v2, v[0:1]
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: s_endpgm
|
|
main_body:
|
|
%ret = atomicrmw fadd double addrspace(3)* %ptr, double 4.0 seq_cst
|
|
ret void
|
|
}
|
|
|
|
define double @local_atomic_fadd_f64_rtn_pat(double addrspace(3)* %ptr, double %data) {
|
|
; GFX90A-LABEL: local_atomic_fadd_f64_rtn_pat:
|
|
; GFX90A: ; %bb.0: ; %main_body
|
|
; GFX90A-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NEXT: v_mov_b32_e32 v3, 0x40100000
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
|
|
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NEXT: s_setpc_b64 s[30:31]
|
|
main_body:
|
|
%ret = atomicrmw fadd double addrspace(3)* %ptr, double 4.0 seq_cst
|
|
ret double %ret
|
|
}
|