forked from OSchip/llvm-project
26 lines
1.1 KiB
LLVM
26 lines
1.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=GCN %s
|
|
|
|
define half @known_nnan_extract_vector_elt(float %a, float %b, i32 %idx, half %c) {
|
|
; GCN-LABEL: known_nnan_extract_vector_elt:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
|
|
; GCN-NEXT: v_cvt_pkrtz_f16_f32 v0, v0, v1
|
|
; GCN-NEXT: v_lshlrev_b32_e32 v1, 4, v2
|
|
; GCN-NEXT: v_lshrrev_b32_e32 v0, v1, v0
|
|
; GCN-NEXT: v_add_f16_e32 v1, 1.0, v3
|
|
; GCN-NEXT: v_cmp_lt_f16_e32 vcc, v0, v1
|
|
; GCN-NEXT: v_cndmask_b32_e32 v0, v1, v0, vcc
|
|
; GCN-NEXT: s_setpc_b64 s[30:31]
|
|
%cvt = call nnan <2 x half> @llvm.amdgcn.cvt.pkrtz(float %a, float %b)
|
|
%extract = extractelement <2 x half> %cvt, i32 %idx
|
|
%canon = call half @llvm.canonicalize.f16(half %extract)
|
|
%nnan.c = fadd nnan nsz half %c, 1.0
|
|
%cmp = fcmp olt half %extract, %nnan.c
|
|
%select = select i1 %cmp, half %extract, half %nnan.c
|
|
ret half %select
|
|
}
|
|
|
|
declare <2 x half> @llvm.amdgcn.cvt.pkrtz(float, float) #0
|
|
declare half @llvm.canonicalize.f16(half) #0
|