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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+v,+m,+zvfbfmin -target-abi=ilp32d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+v,+m,+zvfbfmin -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
declare <2 x bfloat> @llvm.vp.select.v2bf16(<2 x i1>, <2 x bfloat>, <2 x bfloat>, i32)
define <2 x bfloat> @select_v2bf16(<2 x i1> %a, <2 x bfloat> %b, <2 x bfloat> %c, i32 zeroext %evl) {
; CHECK-LABEL: select_v2bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
; CHECK-NEXT: ret
%v = call <2 x bfloat> @llvm.vp.select.v2bf16(<2 x i1> %a, <2 x bfloat> %b, <2 x bfloat> %c, i32 %evl)
ret <2 x bfloat> %v
}
declare <4 x bfloat> @llvm.vp.select.v4bf16(<4 x i1>, <4 x bfloat>, <4 x bfloat>, i32)
define <4 x bfloat> @select_v4bf16(<4 x i1> %a, <4 x bfloat> %b, <4 x bfloat> %c, i32 zeroext %evl) {
; CHECK-LABEL: select_v4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, ta, ma
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
; CHECK-NEXT: ret
%v = call <4 x bfloat> @llvm.vp.select.v4bf16(<4 x i1> %a, <4 x bfloat> %b, <4 x bfloat> %c, i32 %evl)
ret <4 x bfloat> %v
}
declare <8 x bfloat> @llvm.vp.select.v8bf16(<8 x i1>, <8 x bfloat>, <8 x bfloat>, i32)
define <8 x bfloat> @select_v8bf16(<8 x i1> %a, <8 x bfloat> %b, <8 x bfloat> %c, i32 zeroext %evl) {
; CHECK-LABEL: select_v8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, m1, ta, ma
; CHECK-NEXT: vmerge.vvm v8, v9, v8, v0
; CHECK-NEXT: ret
%v = call <8 x bfloat> @llvm.vp.select.v8bf16(<8 x i1> %a, <8 x bfloat> %b, <8 x bfloat> %c, i32 %evl)
ret <8 x bfloat> %v
}
declare <16 x bfloat> @llvm.vp.select.v16bf16(<16 x i1>, <16 x bfloat>, <16 x bfloat>, i32)
define <16 x bfloat> @select_v16bf16(<16 x i1> %a, <16 x bfloat> %b, <16 x bfloat> %c, i32 zeroext %evl) {
; CHECK-LABEL: select_v16bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, m2, ta, ma
; CHECK-NEXT: vmerge.vvm v8, v10, v8, v0
; CHECK-NEXT: ret
%v = call <16 x bfloat> @llvm.vp.select.v16bf16(<16 x i1> %a, <16 x bfloat> %b, <16 x bfloat> %c, i32 %evl)
ret <16 x bfloat> %v
}
|
