File: med3-no-simplify.ll

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-12
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,496,180 kB
  • sloc: cpp: 5,593,972; ansic: 986,872; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,538; xml: 953; cs: 573; fortran: 567
file content (48 lines) | stat: -rw-r--r-- 2,053 bytes parent folder | download | duplicates (7)
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
; RUN: llc -march=amdgcn -verify-machineinstrs -amdgpu-scalar-ir-passes=false < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs -amdgpu-scalar-ir-passes=false < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs -amdgpu-scalar-ir-passes=false < %s | FileCheck -check-prefix=GCN %s

; These tests are split out from umed3.ll and smed3.ll and use the
; -amdgpu-scalar-ir-passes=false flag, because InstSimplify would constant
; fold these functions otherwise.

declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone

; GCN-LABEL: {{^}}v_test_umed3_r_i_i_constant_order_i32:
; GCN: v_max_u32_e32 v{{[0-9]+}}, 17, v{{[0-9]+}}
; GCN: v_min_u32_e32 v{{[0-9]+}}, 12, v{{[0-9]+}}
define amdgpu_kernel void @v_test_umed3_r_i_i_constant_order_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #1 {
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
  %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
  %a = load i32, i32 addrspace(1)* %gep0

  %icmp0 = icmp ugt i32 %a, 17
  %i0 = select i1 %icmp0, i32 %a, i32 17

  %icmp1 = icmp ult i32 %i0, 12
  %i1 = select i1 %icmp1, i32 %i0, i32 12

  store i32 %i1, i32 addrspace(1)* %outgep
  ret void
}

; GCN-LABEL: {{^}}v_test_smed3_r_i_i_constant_order_i32:
; GCN: v_max_i32_e32 v{{[0-9]+}}, 17, v{{[0-9]+}}
; GCN: v_min_i32_e32 v{{[0-9]+}}, 12, v{{[0-9]+}}
define amdgpu_kernel void @v_test_smed3_r_i_i_constant_order_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #1 {
  %tid = call i32 @llvm.amdgcn.workitem.id.x()
  %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid
  %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid
  %a = load i32, i32 addrspace(1)* %gep0

  %icmp0 = icmp sgt i32 %a, 17
  %i0 = select i1 %icmp0, i32 %a, i32 17

  %icmp1 = icmp slt i32 %i0, 12
  %i1 = select i1 %icmp1, i32 %i0, i32 12

  store i32 %i1, i32 addrspace(1)* %outgep
  ret void
}