llvm-for-llvmta/test/CodeGen/AMDGPU/memory-legalizer-global-non...

303 lines
12 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx600 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX6 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX7 %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX10-WGP %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -mattr=+cumode -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX10-CU %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx700 -amdgcn-skip-cache-invalidations -verify-machineinstrs < %s | FileCheck --check-prefixes=SKIP-CACHE-INV %s
define amdgpu_kernel void @global_nontemporal_load_0(
; GFX6-LABEL: global_nontemporal_load_0:
; GFX6: ; %bb.0: ; %entry
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
; GFX6-NEXT: s_mov_b32 s6, -1
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX6-NEXT: s_mov_b32 s4, s2
; GFX6-NEXT: s_mov_b32 s5, s3
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: v_mov_b32_e32 v0, s0
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
; GFX6-NEXT: s_endpgm
;
; GFX7-LABEL: global_nontemporal_load_0:
; GFX7: ; %bb.0: ; %entry
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX7-NEXT: v_mov_b32_e32 v0, s2
; GFX7-NEXT: v_mov_b32_e32 v1, s3
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: v_mov_b32_e32 v2, s0
; GFX7-NEXT: flat_store_dword v[0:1], v2
; GFX7-NEXT: s_endpgm
;
; GFX10-WGP-LABEL: global_nontemporal_load_0:
; GFX10-WGP: ; %bb.0: ; %entry
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s0
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
; GFX10-WGP-NEXT: s_endpgm
;
; GFX10-CU-LABEL: global_nontemporal_load_0:
; GFX10-CU: ; %bb.0: ; %entry
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s0
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
; GFX10-CU-NEXT: s_endpgm
;
; SKIP-CACHE-INV-LABEL: global_nontemporal_load_0:
; SKIP-CACHE-INV: ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: s_load_dword s0, s[0:1], 0x0
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s0
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
; SKIP-CACHE-INV-NEXT: s_endpgm
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
entry:
%val = load i32, i32 addrspace(1)* %in, align 4, !nontemporal !0
store i32 %val, i32 addrspace(1)* %out
ret void
}
define amdgpu_kernel void @global_nontemporal_load_1(
; GFX6-LABEL: global_nontemporal_load_1:
; GFX6: ; %bb.0: ; %entry
; GFX6-NEXT: s_load_dwordx4 s[4:7], s[4:5], 0x0
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
; GFX6-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX6-NEXT: v_mov_b32_e32 v1, 0
; GFX6-NEXT: s_mov_b32 s2, -1
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: s_mov_b32 s0, s6
; GFX6-NEXT: s_mov_b32 s1, s7
; GFX6-NEXT: s_mov_b32 s6, 0
; GFX6-NEXT: s_mov_b32 s7, s3
; GFX6-NEXT: buffer_load_dword v0, v[0:1], s[4:7], 0 addr64 glc slc
; GFX6-NEXT: s_waitcnt vmcnt(0)
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
; GFX6-NEXT: s_endpgm
;
; GFX7-LABEL: global_nontemporal_load_1:
; GFX7: ; %bb.0: ; %entry
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX7-NEXT: v_lshlrev_b32_e32 v2, 2, v0
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: v_mov_b32_e32 v3, s1
; GFX7-NEXT: v_add_i32_e32 v2, vcc, s0, v2
; GFX7-NEXT: v_addc_u32_e32 v3, vcc, 0, v3, vcc
; GFX7-NEXT: flat_load_dword v2, v[2:3] glc slc
; GFX7-NEXT: v_mov_b32_e32 v0, s2
; GFX7-NEXT: v_mov_b32_e32 v1, s3
; GFX7-NEXT: s_waitcnt vmcnt(0)
; GFX7-NEXT: flat_store_dword v[0:1], v2
; GFX7-NEXT: s_endpgm
;
; GFX10-WGP-LABEL: global_nontemporal_load_1:
; GFX10-WGP: ; %bb.0: ; %entry
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-WGP-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, 0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: global_load_dword v0, v0, s[0:1] slc
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
; GFX10-WGP-NEXT: global_store_dword v1, v0, s[2:3]
; GFX10-WGP-NEXT: s_endpgm
;
; GFX10-CU-LABEL: global_nontemporal_load_1:
; GFX10-CU: ; %bb.0: ; %entry
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-CU-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX10-CU-NEXT: v_mov_b32_e32 v1, 0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: global_load_dword v0, v0, s[0:1] slc
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
; GFX10-CU-NEXT: global_store_dword v1, v0, s[2:3]
; GFX10-CU-NEXT: s_endpgm
;
; SKIP-CACHE-INV-LABEL: global_nontemporal_load_1:
; SKIP-CACHE-INV: ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[4:7], s[0:1], 0x9
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
; SKIP-CACHE-INV-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, 0
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: s_mov_b32 s0, s6
; SKIP-CACHE-INV-NEXT: s_mov_b32 s1, s7
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, 0
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, s3
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, v[0:1], s[4:7], 0 addr64 glc slc
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
; SKIP-CACHE-INV-NEXT: s_endpgm
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%val.gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 %tid
%val = load i32, i32 addrspace(1)* %val.gep, align 4, !nontemporal !0
store i32 %val, i32 addrspace(1)* %out
ret void
}
define amdgpu_kernel void @global_nontemporal_store_0(
; GFX6-LABEL: global_nontemporal_store_0:
; GFX6: ; %bb.0: ; %entry
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
; GFX6-NEXT: s_mov_b32 s6, -1
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX6-NEXT: s_mov_b32 s4, s2
; GFX6-NEXT: s_mov_b32 s5, s3
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: v_mov_b32_e32 v0, s0
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0 glc slc
; GFX6-NEXT: s_endpgm
;
; GFX7-LABEL: global_nontemporal_store_0:
; GFX7: ; %bb.0: ; %entry
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX7-NEXT: v_mov_b32_e32 v0, s2
; GFX7-NEXT: v_mov_b32_e32 v1, s3
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: v_mov_b32_e32 v2, s0
; GFX7-NEXT: flat_store_dword v[0:1], v2 glc slc
; GFX7-NEXT: s_endpgm
;
; GFX10-WGP-LABEL: global_nontemporal_store_0:
; GFX10-WGP: ; %bb.0: ; %entry
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s0
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3] slc
; GFX10-WGP-NEXT: s_endpgm
;
; GFX10-CU-LABEL: global_nontemporal_store_0:
; GFX10-CU: ; %bb.0: ; %entry
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s0
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3] slc
; GFX10-CU-NEXT: s_endpgm
;
; SKIP-CACHE-INV-LABEL: global_nontemporal_store_0:
; SKIP-CACHE-INV: ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: s_load_dword s0, s[0:1], 0x0
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s0
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0 glc slc
; SKIP-CACHE-INV-NEXT: s_endpgm
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
entry:
%val = load i32, i32 addrspace(1)* %in, align 4
store i32 %val, i32 addrspace(1)* %out, !nontemporal !0
ret void
}
define amdgpu_kernel void @global_nontemporal_store_1(
; GFX6-LABEL: global_nontemporal_store_1:
; GFX6: ; %bb.0: ; %entry
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
; GFX6-NEXT: s_mov_b32 s6, 0
; GFX6-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX6-NEXT: v_mov_b32_e32 v1, 0
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX6-NEXT: s_mov_b64 s[4:5], s[2:3]
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
; GFX6-NEXT: v_mov_b32_e32 v2, s0
; GFX6-NEXT: buffer_store_dword v2, v[0:1], s[4:7], 0 addr64 glc slc
; GFX6-NEXT: s_endpgm
;
; GFX7-LABEL: global_nontemporal_store_1:
; GFX7: ; %bb.0: ; %entry
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX7-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX7-NEXT: v_mov_b32_e32 v1, s3
; GFX7-NEXT: v_add_i32_e32 v0, vcc, s2, v0
; GFX7-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
; GFX7-NEXT: v_mov_b32_e32 v2, s0
; GFX7-NEXT: flat_store_dword v[0:1], v2 glc slc
; GFX7-NEXT: s_endpgm
;
; GFX10-WGP-LABEL: global_nontemporal_store_1:
; GFX10-WGP: ; %bb.0: ; %entry
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-WGP-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s0
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3] slc
; GFX10-WGP-NEXT: s_endpgm
;
; GFX10-CU-LABEL: global_nontemporal_store_1:
; GFX10-CU: ; %bb.0: ; %entry
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
; GFX10-CU-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: s_load_dword s0, s[0:1], 0x0
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s0
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3] slc
; GFX10-CU-NEXT: s_endpgm
;
; SKIP-CACHE-INV-LABEL: global_nontemporal_store_1:
; SKIP-CACHE-INV: ; %bb.0: ; %entry
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x9
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, 0
; SKIP-CACHE-INV-NEXT: v_lshlrev_b32_e32 v0, 2, v0
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, 0
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: s_load_dword s0, s[0:1], 0x0
; SKIP-CACHE-INV-NEXT: s_mov_b64 s[4:5], s[2:3]
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v2, s0
; SKIP-CACHE-INV-NEXT: buffer_store_dword v2, v[0:1], s[4:7], 0 addr64 glc slc
; SKIP-CACHE-INV-NEXT: s_endpgm
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%val = load i32, i32 addrspace(1)* %in, align 4
%out.gep = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 %tid
store i32 %val, i32 addrspace(1)* %out.gep, !nontemporal !0
ret void
}
!0 = !{i32 1}
declare i32 @llvm.amdgcn.workitem.id.x()