1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-01 05:01:59 +01:00
llvm-mirror/test/CodeGen/ARM/fp16-intrinsic-vector-2op.ll
Sjoerd Meijer 4c4a37be92 [ARM] Support for v4f16 and v8f16 vectors
This is the groundwork for adding the Armv8.2-A FP16 vector intrinsics, which
uses v4f16 and v8f16 vector operands and return values. All the moving parts
are tested with two intrinsics, a 1-operand v8f16 and a 2-operand v4f16
intrinsic. In a follow-up patch the rest of the intrinsics and tests will be
added.

Differential Revision: https://reviews.llvm.org/D44538

llvm-svn: 327839
2018-03-19 13:35:25 +00:00

22 lines
857 B
LLVM

; RUN: llc < %s -mtriple=arm-none-eabi -mattr=+v8.2a,+fullfp16,+neon -float-abi=hard | FileCheck %s --check-prefixes=CHECK,CHECK-HARD
; RUN: llc < %s -mtriple=arm-none-eabi -mattr=+v8.2a,+fullfp16,+neon | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP
declare <4 x half> @llvm.arm.neon.vpadd.v4f16(<4 x half>, <4 x half>)
define dso_local <4 x half> @t_vpadd_f16(<4 x half> %a, <4 x half> %b) {
; CHECK: t_vpadd_f16:
; CHECK-HARD: vpadd.f16 d0, d0, d1
; CHECK-HARD-NEXT: bx lr
; CHECK-SOFTFP: vmov [[D1:d[0-9]+]], r2, r3
; CHECK-SOFTFP: vmov [[D2:d[0-9]+]], r0, r1
; CHECK-SOFTFP: vpadd.f16 [[D3:d[0-9]+]], [[D2]], [[D1]]
; CHECK-SOFTFP: vmov r0, r1, [[D3]]
; CHECK-SOFTFP: bx lr
entry:
%vpadd_v2.i = tail call <4 x half> @llvm.arm.neon.vpadd.v4f16(<4 x half> %a, <4 x half> %b)
ret <4 x half> %vpadd_v2.i
}