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
68
69
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+f16c < %s | FileCheck %s --check-prefix=ALL
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s --check-prefix=ALL
define zeroext i16 @test1_fast(double %d) #0 {
; ALL-LABEL: test1_fast:
; ALL: # %bb.0: # %entry
; ALL-NEXT: pushq %rax
; ALL-NEXT: callq __truncdfhf2@PLT
; ALL-NEXT: vpextrw $0, %xmm0, %eax
; ALL-NEXT: # kill: def $ax killed $ax killed $eax
; ALL-NEXT: popq %rcx
; ALL-NEXT: retq
entry:
%0 = tail call i16 @llvm.convert.to.fp16.f64(double %d)
ret i16 %0
}
define zeroext i16 @test2_fast(x86_fp80 %d) #0 {
; ALL-LABEL: test2_fast:
; ALL: # %bb.0: # %entry
; ALL-NEXT: subq $24, %rsp
; ALL-NEXT: fldt {{[0-9]+}}(%rsp)
; ALL-NEXT: fstpt (%rsp)
; ALL-NEXT: callq __truncxfhf2@PLT
; ALL-NEXT: vpextrw $0, %xmm0, %eax
; ALL-NEXT: # kill: def $ax killed $ax killed $eax
; ALL-NEXT: addq $24, %rsp
; ALL-NEXT: retq
entry:
%0 = tail call i16 @llvm.convert.to.fp16.f80(x86_fp80 %d)
ret i16 %0
}
define zeroext i16 @test1(double %d) #1 {
; ALL-LABEL: test1:
; ALL: # %bb.0: # %entry
; ALL-NEXT: pushq %rax
; ALL-NEXT: callq __truncdfhf2@PLT
; ALL-NEXT: vpextrw $0, %xmm0, %eax
; ALL-NEXT: # kill: def $ax killed $ax killed $eax
; ALL-NEXT: popq %rcx
; ALL-NEXT: retq
entry:
%0 = tail call i16 @llvm.convert.to.fp16.f64(double %d)
ret i16 %0
}
define zeroext i16 @test2(x86_fp80 %d) #1 {
; ALL-LABEL: test2:
; ALL: # %bb.0: # %entry
; ALL-NEXT: subq $24, %rsp
; ALL-NEXT: fldt {{[0-9]+}}(%rsp)
; ALL-NEXT: fstpt (%rsp)
; ALL-NEXT: callq __truncxfhf2@PLT
; ALL-NEXT: vpextrw $0, %xmm0, %eax
; ALL-NEXT: # kill: def $ax killed $ax killed $eax
; ALL-NEXT: addq $24, %rsp
; ALL-NEXT: retq
entry:
%0 = tail call i16 @llvm.convert.to.fp16.f80(x86_fp80 %d)
ret i16 %0
}
declare i16 @llvm.convert.to.fp16.f64(double)
declare i16 @llvm.convert.to.fp16.f80(x86_fp80)
attributes #0 = { nounwind readnone "unsafe-fp-math"="true" "use-soft-float"="false" }
attributes #1 = { nounwind readnone "unsafe-fp-math"="false" "use-soft-float"="false" }
|
