1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
llvm-mirror/test/CodeGen/Thumb2/mve-intrinsics/vrintn.ll
Simon Tatham 2d913ae276 [ARM,MVE] Add intrinsics for FP rounding operations.
Summary:
This adds the unpredicated forms of six different MVE intrinsics which
all round a vector of floating-point numbers to integer values,
leaving them still in FP format, differing only in rounding mode and
exception settings.

Five of them map to existing target-independent intrinsics in LLVM IR,
such as @llvm.trunc and @llvm.rint. The sixth, mapping to the `vrintn`
instruction, is done by inventing a target-specific intrinsic.

(`vrintn` behaves the same as `vrintx` in terms of the output value:
the side effects on the FPSCR flags are the only difference between
the two. But ACLE specifies separate user-callable intrinsics for the
two, so the side effects matter enough to make sure we generate the
right one of the two instructions in each case.)

Reviewers: dmgreen, miyuki, MarkMurrayARM, ostannard

Reviewed By: miyuki

Subscribers: kristof.beyls, hiraditya, cfe-commits, llvm-commits

Tags: #clang, #llvm

Differential Revision: https://reviews.llvm.org/D74333
2020-02-18 09:34:50 +00:00

26 lines
880 B
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -verify-machineinstrs -o - %s | FileCheck %s
define arm_aapcs_vfpcc <8 x half> @test_vrndnq_f16(<8 x half> %a) {
; CHECK-LABEL: test_vrndnq_f16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vrintn.f16 q0, q0
; CHECK-NEXT: bx lr
entry:
%0 = tail call <8 x half> @llvm.arm.mve.vrintn.v8f16(<8 x half> %a)
ret <8 x half> %0
}
define arm_aapcs_vfpcc <4 x float> @test_vrndnq_f32(<4 x float> %a) {
; CHECK-LABEL: test_vrndnq_f32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vrintn.f32 q0, q0
; CHECK-NEXT: bx lr
entry:
%0 = tail call <4 x float> @llvm.arm.mve.vrintn.v4f32(<4 x float> %a)
ret <4 x float> %0
}
declare <8 x half> @llvm.arm.mve.vrintn.v8f16(<8 x half>)
declare <4 x float> @llvm.arm.mve.vrintn.v4f32(<4 x float>)