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
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
; FIXME: This should go in existing select.ll test, except the current testcase there is broken on GCN
; GCN-LABEL: {{^}}select_i1:
; GCN: v_cndmask_b32
; GCN-NOT: v_cndmask_b32
define amdgpu_kernel void @select_i1(i1 addrspace(1)* %out, i32 %cond, i1 %a, i1 %b) nounwind {
%cmp = icmp ugt i32 %cond, 5
%sel = select i1 %cmp, i1 %a, i1 %b
store i1 %sel, i1 addrspace(1)* %out, align 4
ret void
}
; GCN-LABEL: {{^}}s_minmax_i1:
; GCN: s_load_dword [[LOAD:s[0-9]+]],
; GCN: s_bitcmp1_b32 [[LOAD]], 0
; GCN: s_cselect_b64 vcc, -1, 0
; GCN-DAG: s_lshr_b32 [[A:s[0-9]+]], [[LOAD]], 8
; GCN-DAG: s_lshr_b32 [[B:s[0-9]+]], [[LOAD]], 16
; GCN: v_mov_b32_e32 [[V_B:v[0-9]+]], [[B]]
; GCN: v_mov_b32_e32 [[V_A:v[0-9]+]], [[A]]
; GCN: v_cndmask_b32_e32 [[SEL:v[0-9]+]], [[V_B]], [[V_A]]
; GCN: v_and_b32_e32 v{{[0-9]+}}, 1, [[SEL]]
define amdgpu_kernel void @s_minmax_i1(i1 addrspace(1)* %out, [8 x i32], i1 zeroext %cond, i1 zeroext %a, i1 zeroext %b) nounwind {
%cmp = icmp slt i1 %cond, false
%sel = select i1 %cmp, i1 %a, i1 %b
store i1 %sel, i1 addrspace(1)* %out, align 4
ret void
}
|
