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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple amdgcn-amd-amdhsa -mcpu=gfx900 < %s | FileCheck --check-prefix=GCN %s
; RUN: llc -mtriple amdgcn-amd-amdhsa -mcpu=gfx900 -early-live-intervals -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
define weak_odr amdgpu_kernel void @test_mul24_knownbits_kernel(ptr addrspace(1) %p) #4 {
; GCN-LABEL: test_mul24_knownbits_kernel:
; GCN: ; %bb.0: ; %entry
; GCN-NEXT: v_and_b32_e32 v0, 3, v0
; GCN-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
; GCN-NEXT: v_mul_i32_i24_e32 v0, -5, v0
; GCN-NEXT: v_and_b32_e32 v0, 0xffffffe0, v0
; GCN-NEXT: v_ashrrev_i32_e32 v1, 31, v0
; GCN-NEXT: v_lshlrev_b64 v[0:1], 2, v[0:1]
; GCN-NEXT: s_waitcnt lgkmcnt(0)
; GCN-NEXT: v_mov_b32_e32 v2, s1
; GCN-NEXT: v_add_co_u32_e32 v0, vcc, s0, v0
; GCN-NEXT: v_addc_co_u32_e32 v1, vcc, v2, v1, vcc
; GCN-NEXT: v_mov_b32_e32 v2, 0
; GCN-NEXT: global_store_dword v[0:1], v2, off
; GCN-NEXT: s_endpgm
entry:
%0 = tail call i32 @llvm.amdgcn.workitem.id.x() #28, !range !4
%tid = and i32 %0, 3
%1 = mul nsw i32 %tid, -5
%v1 = and i32 %1, -32
%v2 = sext i32 %v1 to i64
%v3 = getelementptr inbounds float, ptr addrspace(1) %p, i64 %v2
store float 0.000, ptr addrspace(1) %v3, align 4
ret void
}
define i32 @f(i32 %x, i32 %y) {
; GCN-LABEL: f:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_or_b32_e32 v0, 0xffff80, v0
; GCN-NEXT: v_or_b32_e32 v1, 0xffff80, v1
; GCN-NEXT: v_mul_i32_i24_e32 v0, v0, v1
; GCN-NEXT: v_lshrrev_b32_e32 v0, 14, v0
; GCN-NEXT: s_setpc_b64 s[30:31]
%xx = or i32 %x, -128 ; 0xffffff80
%yy = or i32 %y, -128 ; 0xffffff80
%r = mul i32 %xx, %yy
%rr = lshr i32 %r, 14
ret i32 %rr
}
; Function Attrs: nounwind readnone speculatable
declare i32 @llvm.amdgcn.workitem.id.x() #20
!4 = !{i32 0, i32 1024}
|
