252
|
1 ; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
|
|
2 ; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
|
|
3 ; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
|
|
4 ; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
|
|
5 ; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1032 %s
|
|
6 ; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
|
|
7 ; RUN: llc -global-isel=0 -march=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
|
|
8 ; RUN: llc -global-isel=1 -march=amdgcn -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,GFX1064 %s
|
150
|
9
|
|
10 ; GCN-LABEL: {{^}}test_init_exec:
|
|
11 ; GFX1032: s_mov_b32 exec_lo, 0x12345
|
|
12 ; GFX1064: s_mov_b64 exec, 0x12345
|
|
13 ; GCN: v_add_f32_e32 v0,
|
|
14 define amdgpu_ps float @test_init_exec(float %a, float %b) {
|
|
15 main_body:
|
|
16 %s = fadd float %a, %b
|
|
17 call void @llvm.amdgcn.init.exec(i64 74565)
|
|
18 ret float %s
|
|
19 }
|
|
20
|
|
21 ; GCN-LABEL: {{^}}test_init_exec_from_input:
|
|
22 ; GCN: s_bfe_u32 s0, s3, 0x70008
|
|
23 ; GFX1032: s_bfm_b32 exec_lo, s0, 0
|
|
24 ; GFX1032: s_cmp_eq_u32 s0, 32
|
|
25 ; GFX1032: s_cmov_b32 exec_lo, -1
|
|
26 ; GFX1064: s_bfm_b64 exec, s0, 0
|
|
27 ; GFX1064: s_cmp_eq_u32 s0, 64
|
|
28 ; GFX1064: s_cmov_b64 exec, -1
|
|
29 ; GCN: v_add_f32_e32 v0,
|
|
30 define amdgpu_ps float @test_init_exec_from_input(i32 inreg, i32 inreg, i32 inreg, i32 inreg %count, float %a, float %b) {
|
|
31 main_body:
|
|
32 %s = fadd float %a, %b
|
|
33 call void @llvm.amdgcn.init.exec.from.input(i32 %count, i32 8)
|
|
34 ret float %s
|
|
35 }
|
|
36
|
|
37 declare void @llvm.amdgcn.init.exec(i64)
|
|
38 declare void @llvm.amdgcn.init.exec.from.input(i32, i32)
|