; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck %s -check-prefix=GFX90A
; RUN: llc -global-isel -mtriple=amdgcn -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck %s -check-prefix=GFX940
declare double @llvm.amdgcn.struct.buffer.atomic.fadd.f64(double, <4 x i32>, i32, i32, i32, i32 immarg)
declare double @llvm.amdgcn.struct.ptr.buffer.atomic.fadd.f64(double, ptr addrspace(8), 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.raw.ptr.buffer.atomic.fadd.f64(double, ptr addrspace(8), 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.struct.ptr.buffer.atomic.fmin.f64(double, ptr addrspace(8), 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.raw.ptr.buffer.atomic.fmin.f64(double, ptr addrspace(8), 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.struct.ptr.buffer.atomic.fmax.f64(double, ptr addrspace(8), 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.raw.ptr.buffer.atomic.fmax.f64(double, ptr addrspace(8), i32, i32, i32 immarg)
declare double @llvm.amdgcn.global.atomic.fmin.f64.p1.f64(ptr addrspace(1) %ptr, double %data)
declare double @llvm.amdgcn.global.atomic.fmax.f64.p1.f64(ptr addrspace(1) %ptr, double %data)
declare double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %ptr, double %data)
declare double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %ptr, double %data)
define amdgpu_kernel void @raw_buffer_atomic_add_noret_f64(<4 x i32> %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_buffer_atomic_add_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 offen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: raw_buffer_atomic_add_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 offen
; GFX940-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
;
; GFX940-LABEL: raw_buffer_atomic_add_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 offen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-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, ptr undef
ret void
}
define amdgpu_kernel void @raw_buffer_atomic_add_rtn_f64_off4_slc(<4 x i32> %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: raw_buffer_atomic_add_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: raw_buffer_atomic_add_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 4 offen sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-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, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @raw_ptr_buffer_atomic_add_noret_f64(ptr addrspace(8) %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_ptr_buffer_atomic_add_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 offen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: raw_ptr_buffer_atomic_add_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 offen
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fadd.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0)
ret void
}
define amdgpu_ps void @raw_ptr_buffer_atomic_add_rtn_f64(ptr addrspace(8) inreg %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_ptr_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
;
; GFX940-LABEL: raw_ptr_buffer_atomic_add_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 offen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fadd.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0)
store double %ret, ptr undef
ret void
}
define amdgpu_kernel void @raw_ptr_buffer_atomic_add_rtn_f64_off4_slc(ptr addrspace(8) %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: raw_ptr_buffer_atomic_add_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: raw_ptr_buffer_atomic_add_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 4 offen sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fadd.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 4, i32 2)
store double %ret, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @struct_buffer_atomic_add_noret_f64(<4 x i32> %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_buffer_atomic_add_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: struct_buffer_atomic_add_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX940-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
;
; GFX940-LABEL: struct_buffer_atomic_add_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 idxen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-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, ptr undef
ret void
}
define amdgpu_kernel void @struct_buffer_atomic_add_rtn_f64_off4_slc(<4 x i32> %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: struct_buffer_atomic_add_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: struct_buffer_atomic_add_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-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, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @struct_ptr_buffer_atomic_add_noret_f64(ptr addrspace(8) %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_ptr_buffer_atomic_add_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: struct_ptr_buffer_atomic_add_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fadd.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
ret void
}
define amdgpu_ps void @struct_ptr_buffer_atomic_add_rtn_f64(ptr addrspace(8) inreg %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_ptr_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
;
; GFX940-LABEL: struct_ptr_buffer_atomic_add_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[0:3], 0 idxen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fadd.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
store double %ret, ptr undef
ret void
}
define amdgpu_kernel void @struct_ptr_buffer_atomic_add_rtn_f64_off4_slc(ptr addrspace(8) %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: struct_ptr_buffer_atomic_add_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: struct_ptr_buffer_atomic_add_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_add_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fadd.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 4, i32 0, i32 2)
store double %ret, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @raw_buffer_atomic_min_noret_f64(<4 x i32> %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_buffer_atomic_min_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 offen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: raw_buffer_atomic_min_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 offen
; GFX940-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
;
; GFX940-LABEL: raw_buffer_atomic_min_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[0:3], 0 offen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-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, ptr undef
ret void
}
define amdgpu_kernel void @raw_buffer_atomic_min_rtn_f64_off4_slc(<4 x i32> %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: raw_buffer_atomic_min_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: raw_buffer_atomic_min_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 4 offen sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-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, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @raw_ptr_buffer_atomic_min_noret_f64(ptr addrspace(8) %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_ptr_buffer_atomic_min_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 offen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: raw_ptr_buffer_atomic_min_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 offen
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmin.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0)
ret void
}
define amdgpu_ps void @raw_ptr_buffer_atomic_min_rtn_f64(ptr addrspace(8) inreg %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_ptr_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
;
; GFX940-LABEL: raw_ptr_buffer_atomic_min_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[0:3], 0 offen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmin.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0)
store double %ret, ptr undef
ret void
}
define amdgpu_kernel void @raw_ptr_buffer_atomic_min_rtn_f64_off4_slc(ptr addrspace(8) %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: raw_ptr_buffer_atomic_min_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: raw_ptr_buffer_atomic_min_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 4 offen sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmin.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 4, i32 2)
store double %ret, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @struct_buffer_atomic_min_noret_f64(<4 x i32> %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_buffer_atomic_min_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: struct_buffer_atomic_min_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX940-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
;
; GFX940-LABEL: struct_buffer_atomic_min_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[0:3], 0 idxen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-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, ptr undef
ret void
}
define amdgpu_kernel void @struct_buffer_atomic_min_rtn_f64_off4_slc(<4 x i32> %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: struct_buffer_atomic_min_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: struct_buffer_atomic_min_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-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, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @struct_ptr_buffer_atomic_min_noret_f64(ptr addrspace(8) %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_ptr_buffer_atomic_min_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: struct_ptr_buffer_atomic_min_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fmin.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
ret void
}
define amdgpu_ps void @struct_ptr_buffer_atomic_min_rtn_f64(ptr addrspace(8) inreg %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_ptr_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
;
; GFX940-LABEL: struct_ptr_buffer_atomic_min_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[0:3], 0 idxen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fmin.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
store double %ret, ptr undef
ret void
}
define amdgpu_kernel void @struct_ptr_buffer_atomic_min_rtn_f64_off4_slc(ptr addrspace(8) %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: struct_ptr_buffer_atomic_min_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: struct_ptr_buffer_atomic_min_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_min_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fmin.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 4, i32 0, i32 2)
store double %ret, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @raw_buffer_atomic_max_noret_f64(<4 x i32> %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_buffer_atomic_max_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 offen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: raw_buffer_atomic_max_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 offen
; GFX940-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
;
; GFX940-LABEL: raw_buffer_atomic_max_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[0:3], 0 offen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-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, ptr undef
ret void
}
define amdgpu_kernel void @raw_buffer_atomic_max_rtn_f64_off4_slc(<4 x i32> %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: raw_buffer_atomic_max_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: raw_buffer_atomic_max_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 4 offen sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-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, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @raw_ptr_buffer_atomic_max_noret_f64(ptr addrspace(8) %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_ptr_buffer_atomic_max_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 offen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: raw_ptr_buffer_atomic_max_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 offen
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmax.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0)
ret void
}
define amdgpu_ps void @raw_ptr_buffer_atomic_max_rtn_f64(ptr addrspace(8) inreg %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: raw_ptr_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
;
; GFX940-LABEL: raw_ptr_buffer_atomic_max_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[0:3], 0 offen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmax.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0)
store double %ret, ptr undef
ret void
}
define amdgpu_kernel void @raw_ptr_buffer_atomic_max_rtn_f64_off4_slc(ptr addrspace(8) %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: raw_ptr_buffer_atomic_max_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: raw_ptr_buffer_atomic_max_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 4 offen sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.raw.ptr.buffer.atomic.fmax.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 4, i32 2)
store double %ret, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @struct_buffer_atomic_max_noret_f64(<4 x i32> %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_buffer_atomic_max_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: struct_buffer_atomic_max_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX940-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
;
; GFX940-LABEL: struct_buffer_atomic_max_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[0:3], 0 idxen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-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, ptr undef
ret void
}
define amdgpu_kernel void @struct_buffer_atomic_max_rtn_f64_off4_slc(<4 x i32> %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: struct_buffer_atomic_max_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: struct_buffer_atomic_max_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-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, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @struct_ptr_buffer_atomic_max_noret_f64(ptr addrspace(8) %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_ptr_buffer_atomic_max_noret_f64:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 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_mov_b32_e32 v2, s8
; GFX90A-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: struct_ptr_buffer_atomic_max_noret_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s8, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s8
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fmax.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
ret void
}
define amdgpu_ps void @struct_ptr_buffer_atomic_max_rtn_f64(ptr addrspace(8) inreg %rsrc, double %data, i32 %vindex) {
; GFX90A-LABEL: struct_ptr_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
;
; GFX940-LABEL: struct_ptr_buffer_atomic_max_rtn_f64:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[0:3], 0 idxen sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: flat_store_dwordx2 v[0:1], v[0:1] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fmax.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 0, i32 0, i32 0)
store double %ret, ptr undef
ret void
}
define amdgpu_kernel void @struct_ptr_buffer_atomic_max_rtn_f64_off4_slc(ptr addrspace(8) %rsrc, double %data, i32 %vindex, ptr addrspace(1) %out) {
; GFX90A-LABEL: struct_ptr_buffer_atomic_max_rtn_f64_off4_slc:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX90A-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; 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_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
;
; GFX940-LABEL: struct_ptr_buffer_atomic_max_rtn_f64_off4_slc:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x34
; GFX940-NEXT: s_load_dword s10, s[2:3], 0x3c
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_load_dwordx2 s[8:9], s[2:3], 0x44
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: v_mov_b32_e32 v2, s10
; GFX940-NEXT: buffer_atomic_max_f64 v[0:1], v2, s[4:7], 0 idxen offset:4 sc0 nt
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: global_store_dwordx2 v2, v[0:1], s[8:9] sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.struct.ptr.buffer.atomic.fmax.f64(double %data, ptr addrspace(8) %rsrc, i32 %vindex, i32 4, i32 0, i32 2)
store double %ret, ptr addrspace(1) %out, align 8
ret void
}
define amdgpu_kernel void @global_atomic_fmin_f64_noret(ptr addrspace(1) %ptr, double %data) {
; GFX90A-LABEL: global_atomic_fmin_f64_noret:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[6:7], s[6:7] op_sel:[0,1]
; GFX90A-NEXT: global_atomic_min_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fmin_f64_noret:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[6:7]
; GFX940-NEXT: global_atomic_min_f64 v2, v[0:1], s[4:5]
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.global.atomic.fmin.f64.p1.f64(ptr addrspace(1) %ptr, double %data)
ret void
}
define amdgpu_kernel void @global_atomic_fmax_f64_noret(ptr addrspace(1) %ptr, double %data) {
; GFX90A-LABEL: global_atomic_fmax_f64_noret:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[6:7], s[6:7] op_sel:[0,1]
; GFX90A-NEXT: global_atomic_max_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fmax_f64_noret:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[6:7]
; GFX940-NEXT: global_atomic_max_f64 v2, v[0:1], s[4:5]
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.global.atomic.fmax.f64.p1.f64(ptr addrspace(1) %ptr, double %data)
ret void
}
define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat(ptr addrspace(1) %ptr) #1 {
; GFX90A-LABEL: global_atomic_fadd_f64_noret_pat:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB38_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: buffer_wbl2
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: .LBB38_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB38_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5] sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: .LBB38_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_agent(ptr addrspace(1) %ptr) #1 {
; GFX90A-LABEL: global_atomic_fadd_f64_noret_pat_agent:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB39_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: .LBB39_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_agent:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB39_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: .LBB39_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_system(ptr addrspace(1) %ptr) #1 {
; GFX90A-LABEL: global_atomic_fadd_f64_noret_pat_system:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB40_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: buffer_wbl2
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: .LBB40_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_system:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB40_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5] sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: .LBB40_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 syncscope("one-as") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_flush(ptr addrspace(1) %ptr) #0 {
; GFX90A-LABEL: global_atomic_fadd_f64_noret_pat_flush:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB41_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: .LBB41_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_flush:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB41_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: .LBB41_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define double @global_atomic_fadd_f64_rtn_pat(ptr addrspace(1) %ptr, double %data) #1 {
; GFX90A-LABEL: global_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: buffer_wbl2
; 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: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_setpc_b64 s[30:31]
;
; GFX940-LABEL: global_atomic_fadd_f64_rtn_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: global_atomic_add_f64 v[0:1], v[0:1], v[2:3], off sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret double %ret
}
define double @global_atomic_fadd_f64_rtn_pat_agent(ptr addrspace(1) %ptr, double %data) #1 {
; GFX90A-LABEL: global_atomic_fadd_f64_rtn_pat_agent:
; 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: global_atomic_add_f64 v[0:1], v[0:1], v[2:3], off glc
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_setpc_b64 s[30:31]
;
; GFX940-LABEL: global_atomic_fadd_f64_rtn_pat_agent:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: global_atomic_add_f64 v[0:1], v[0:1], v[2:3], off sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret double %ret
}
define double @global_atomic_fadd_f64_rtn_pat_system(ptr addrspace(1) %ptr, double %data) #1 {
; GFX90A-LABEL: global_atomic_fadd_f64_rtn_pat_system:
; 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: buffer_wbl2
; 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: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_setpc_b64 s[30:31]
;
; GFX940-LABEL: global_atomic_fadd_f64_rtn_pat_system:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: global_atomic_add_f64 v[0:1], v[0:1], v[2:3], off sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 syncscope("one-as") seq_cst, !amdgpu.no.fine.grained.memory !0
ret double %ret
}
define double @global_atomic_fmax_f64_rtn(ptr 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]
;
; GFX940-LABEL: global_atomic_fmax_f64_rtn:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_max_f64 v[0:1], v[0:1], v[2:3], off sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = call double @llvm.amdgcn.global.atomic.fmax.f64.p1.f64(ptr addrspace(1) %ptr, double %data)
ret double %ret
}
define double @global_atomic_fmin_f64_rtn(ptr 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]
;
; GFX940-LABEL: global_atomic_fmin_f64_rtn:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: global_atomic_min_f64 v[0:1], v[0:1], v[2:3], off sc0
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = call double @llvm.amdgcn.global.atomic.fmin.f64.p1.f64(ptr addrspace(1) %ptr, double %data)
ret double %ret
}
define amdgpu_kernel void @global_atomic_fadd_f64_noret_pat_agent_safe(ptr addrspace(1) %ptr) {
; GFX90A-LABEL: global_atomic_fadd_f64_noret_pat_agent_safe:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB47_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: .LBB47_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: global_atomic_fadd_f64_noret_pat_agent_safe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB47_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dwordx2 s[4:5], s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: v_mov_b32_e32 v2, 0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: global_atomic_add_f64 v2, v[0:1], s[4:5]
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: .LBB47_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(1) %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat(ptr %ptr) #1 {
; GFX90A-LABEL: flat_atomic_fadd_f64_noret_pat:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: v_mov_b32_e32 v3, 0x40100000
; 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: buffer_wbl2
; GFX90A-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX90A-NEXT: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3] sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat_agent(ptr %ptr) #1 {
; GFX90A-LABEL: flat_atomic_fadd_f64_noret_pat_agent:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: v_mov_b32_e32 v3, 0x40100000
; 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: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat_agent:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat_system(ptr %ptr) #1 {
; GFX90A-LABEL: flat_atomic_fadd_f64_noret_pat_system:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: v_mov_b32_e32 v3, 0x40100000
; 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: buffer_wbl2
; GFX90A-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat_system:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3] sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 syncscope("one-as") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define double @flat_atomic_fadd_f64_rtn_pat(ptr %ptr) #1 {
; GFX90A-LABEL: flat_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: buffer_wbl2
; 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: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_setpc_b64 s[30:31]
;
; GFX940-LABEL: flat_atomic_fadd_f64_rtn_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret double %ret
}
define double @flat_atomic_fadd_f64_rtn_pat_agent(ptr %ptr) #1 {
; GFX90A-LABEL: flat_atomic_fadd_f64_rtn_pat_agent:
; 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: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] glc
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_setpc_b64 s[30:31]
;
; GFX940-LABEL: flat_atomic_fadd_f64_rtn_pat_agent:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] sc0
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret double %ret
}
define double @flat_atomic_fadd_f64_rtn_pat_system(ptr %ptr) #1 {
; GFX90A-LABEL: flat_atomic_fadd_f64_rtn_pat_system:
; 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: buffer_wbl2
; GFX90A-NEXT: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] glc
; GFX90A-NEXT: s_waitcnt vmcnt(0)
; GFX90A-NEXT: buffer_invl2
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: s_setpc_b64 s[30:31]
;
; GFX940-LABEL: flat_atomic_fadd_f64_rtn_pat_system:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: buffer_wbl2 sc0 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] sc0 sc1
; GFX940-NEXT: s_waitcnt vmcnt(0)
; GFX940-NEXT: buffer_inv sc0 sc1
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 syncscope("one-as") seq_cst, !amdgpu.no.fine.grained.memory !0
ret double %ret
}
define amdgpu_kernel void @flat_atomic_fadd_f64_noret_pat_agent_safe(ptr %ptr) {
; GFX90A-LABEL: flat_atomic_fadd_f64_noret_pat_agent_safe:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX90A-NEXT: v_mov_b32_e32 v2, 0
; GFX90A-NEXT: v_mov_b32_e32 v3, 0x40100000
; 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: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX90A-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX90A-NEXT: buffer_wbinvl1_vol
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: flat_atomic_fadd_f64_noret_pat_agent_safe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx2 s[0:1], s[2:3], 0x24
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[0:1]
; GFX940-NEXT: buffer_wbl2 sc1
; GFX940-NEXT: flat_atomic_add_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: buffer_inv sc1
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr %ptr, double 4.0 syncscope("agent") seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @flat_atomic_fmin_f64_noret(ptr %ptr, double %data) {
; GFX90A-LABEL: flat_atomic_fmin_f64_noret:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[4:5], s[4:5] op_sel:[0,1]
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[6:7], s[6:7] op_sel:[0,1]
; GFX90A-NEXT: flat_atomic_min_f64 v[0:1], v[2:3]
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: flat_atomic_fmin_f64_noret:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[4:5]
; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[6:7]
; GFX940-NEXT: flat_atomic_min_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %ptr, double %data)
ret void
}
define double @flat_atomic_fmin_f64_rtn(ptr %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]
;
; GFX940-LABEL: flat_atomic_fmin_f64_rtn:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: flat_atomic_min_f64 v[0:1], v[0:1], v[2:3] sc0
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %ptr, double %data)
ret double %ret
}
define amdgpu_kernel void @flat_atomic_fmax_f64_noret(ptr %ptr, double %data) {
; GFX90A-LABEL: flat_atomic_fmax_f64_noret:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_pk_mov_b32 v[0:1], s[4:5], s[4:5] op_sel:[0,1]
; GFX90A-NEXT: v_pk_mov_b32 v[2:3], s[6:7], s[6:7] op_sel:[0,1]
; GFX90A-NEXT: flat_atomic_max_f64 v[0:1], v[2:3]
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: flat_atomic_fmax_f64_noret:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_load_dwordx4 s[4:7], s[2:3], 0x24
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[0:1], s[4:5]
; GFX940-NEXT: v_mov_b64_e32 v[2:3], s[6:7]
; GFX940-NEXT: flat_atomic_max_f64 v[0:1], v[2:3]
; GFX940-NEXT: s_endpgm
main_body:
%ret = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %ptr, double %data)
ret void
}
define double @flat_atomic_fmax_f64_rtn(ptr %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]
;
; GFX940-LABEL: flat_atomic_fmax_f64_rtn:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: flat_atomic_max_f64 v[0:1], v[0:1], v[2:3] sc0
; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %ptr, double %data)
ret double %ret
}
define amdgpu_kernel void @local_atomic_fadd_f64_noret_pat(ptr addrspace(3) %ptr) #1 {
; GFX90A-LABEL: local_atomic_fadd_f64_noret_pat:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB59_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dword s2, s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_mov_b32_e32 v2, s2
; GFX90A-NEXT: ds_add_f64 v2, v[0:1]
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: .LBB59_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: local_atomic_fadd_f64_noret_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB59_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dword s2, s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b32_e32 v2, s2
; GFX940-NEXT: ds_add_f64 v2, v[0:1]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: .LBB59_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(3) %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @local_atomic_fadd_f64_noret_pat_flush(ptr addrspace(3) %ptr) #0 {
; GFX90A-LABEL: local_atomic_fadd_f64_noret_pat_flush:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB60_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dword s2, s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_mov_b32_e32 v2, s2
; GFX90A-NEXT: ds_add_f64 v2, v[0:1]
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: .LBB60_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: local_atomic_fadd_f64_noret_pat_flush:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB60_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dword s2, s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b32_e32 v2, s2
; GFX940-NEXT: ds_add_f64 v2, v[0:1]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: .LBB60_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(3) %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define amdgpu_kernel void @local_atomic_fadd_f64_noret_pat_flush_safe(ptr addrspace(3) %ptr) #2 {
; GFX90A-LABEL: local_atomic_fadd_f64_noret_pat_flush_safe:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: s_mov_b64 s[0:1], exec
; GFX90A-NEXT: s_mov_b32 s4, s1
; GFX90A-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX90A-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX90A-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX90A-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX90A-NEXT: s_cbranch_execz .LBB61_2
; GFX90A-NEXT: ; %bb.1:
; GFX90A-NEXT: s_load_dword s2, s[2:3], 0x24
; GFX90A-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX90A-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX90A-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: v_mov_b32_e32 v2, s2
; GFX90A-NEXT: ds_add_f64 v2, v[0:1]
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: .LBB61_2:
; GFX90A-NEXT: s_endpgm
;
; GFX940-LABEL: local_atomic_fadd_f64_noret_pat_flush_safe:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_mov_b64 s[0:1], exec
; GFX940-NEXT: s_mov_b32 s4, s1
; GFX940-NEXT: v_mbcnt_lo_u32_b32 v0, s0, 0
; GFX940-NEXT: v_mbcnt_hi_u32_b32 v0, s4, v0
; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
; GFX940-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX940-NEXT: s_cbranch_execz .LBB61_2
; GFX940-NEXT: ; %bb.1:
; GFX940-NEXT: s_load_dword s2, s[2:3], 0x24
; GFX940-NEXT: s_bcnt1_i32_b64 s0, s[0:1]
; GFX940-NEXT: v_cvt_f64_u32_e32 v[0:1], s0
; GFX940-NEXT: v_mul_f64 v[0:1], v[0:1], 4.0
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: v_mov_b32_e32 v2, s2
; GFX940-NEXT: ds_add_f64 v2, v[0:1]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: .LBB61_2:
; GFX940-NEXT: s_endpgm
main_body:
%ret = atomicrmw fadd ptr addrspace(3) %ptr, double 4.0 seq_cst, !amdgpu.no.fine.grained.memory !0
ret void
}
define double @local_atomic_fadd_f64_rtn_pat(ptr addrspace(3) %ptr, double %data) #1 {
; 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: 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]
;
; GFX940-LABEL: local_atomic_fadd_f64_rtn_pat:
; GFX940: ; %bb.0: ; %main_body
; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX940-NEXT: v_mov_b64_e32 v[2:3], 4.0
; GFX940-NEXT: ds_add_rtn_f64 v[0:1], v0, v[2:3]
; GFX940-NEXT: s_waitcnt lgkmcnt(0)
; GFX940-NEXT: s_setpc_b64 s[30:31]
main_body:
%ret = atomicrmw fadd ptr addrspace(3) %ptr, double 4.0 seq_cst
ret double %ret
}
attributes #0 = { nounwind "denormal-fp-math"="preserve-sign,preserve-sign" }
attributes #1 = { nounwind }
attributes #2 = { nounwind "denormal-fp-math"="preserve-sign,preserve-sign" }
!0 = !{}
Codebase Browser
llvm