1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -check-prefix=GFX942 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -O0 < %s | FileCheck -check-prefix=GFX90A %s
@G = addrspace(1) global <2 x i32> splat (i32 5)
define amdgpu_ps void @global_load_lds_dword_saddr(ptr addrspace(1) inreg nocapture %gptr, ptr addrspace(3) nocapture %lptr) {
; GFX942-LABEL: global_load_lds_dword_saddr:
; GFX942: ; %bb.0: ; %main_body
; GFX942-NEXT: v_readfirstlane_b32 s2, v0
; GFX942-NEXT: v_mov_b32_e32 v1, 0
; GFX942-NEXT: s_mov_b32 m0, s2
; GFX942-NEXT: s_nop 0
; GFX942-NEXT: global_load_lds_dword v1, s[0:1] offset:32 nt
; GFX942-NEXT: s_getpc_b64 s[0:1]
; GFX942-NEXT: s_add_u32 s0, s0, G@gotpcrel32@lo+4
; GFX942-NEXT: s_addc_u32 s1, s1, G@gotpcrel32@hi+12
; GFX942-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX942-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
; GFX942-NEXT: s_waitcnt lgkmcnt(0)
; GFX942-NEXT: s_mul_i32 s3, s3, 10
; GFX942-NEXT: s_mul_i32 s2, s2, 10
; GFX942-NEXT: v_mov_b32_e32 v2, s2
; GFX942-NEXT: v_mov_b32_e32 v3, s3
; GFX942-NEXT: global_store_dwordx2 v1, v[2:3], s[0:1]
; GFX942-NEXT: s_endpgm
;
; GFX90A-LABEL: global_load_lds_dword_saddr:
; GFX90A: ; %bb.0: ; %main_body
; GFX90A-NEXT: v_mov_b32_e32 v1, v0
; GFX90A-NEXT: s_mov_b32 s2, s0
; GFX90A-NEXT: ; kill: def $sgpr2 killed $sgpr2 def $sgpr2_sgpr3
; GFX90A-NEXT: s_mov_b32 s3, s1
; GFX90A-NEXT: ; kill: def $sgpr0_sgpr1 killed $sgpr2_sgpr3
; GFX90A-NEXT: s_getpc_b64 s[0:1]
; GFX90A-NEXT: s_add_u32 s0, s0, G@gotpcrel32@lo+4
; GFX90A-NEXT: s_addc_u32 s1, s1, G@gotpcrel32@hi+12
; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x0
; GFX90A-NEXT: v_mov_b32_e32 v0, 0
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: s_mov_b32 s4, s9
; GFX90A-NEXT: s_mov_b32 s6, 10
; GFX90A-NEXT: s_mul_i32 s4, s4, s6
; GFX90A-NEXT: s_mov_b32 s5, s8
; GFX90A-NEXT: s_mul_i32 s5, s5, s6
; GFX90A-NEXT: v_mov_b32_e32 v2, s5
; GFX90A-NEXT: v_mov_b32_e32 v4, s4
; GFX90A-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
; GFX90A-NEXT: v_mov_b32_e32 v3, v4
; GFX90A-NEXT: ; implicit-def: $sgpr4
; GFX90A-NEXT: v_readfirstlane_b32 s4, v1
; GFX90A-NEXT: s_mov_b32 m0, s4
; GFX90A-NEXT: s_nop 0
; GFX90A-NEXT: global_load_dword v0, s[2:3] offset:32 slc lds
; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
; GFX90A-NEXT: global_store_dwordx2 v0, v[2:3], s[0:1]
; GFX90A-NEXT: s_endpgm
main_body:
%LGV = load <2 x i32>, ptr addrspace(1) @G, align 8
%B = mul <2 x i32> %LGV, splat (i32 10)
call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) %gptr, ptr addrspace(3) %lptr, i32 4, i32 32, i32 2)
store <2 x i32> %B, ptr addrspace(1) @G, align 8
ret void
}
|
