DeepLearningKit - an Open Source Deep Learning

Framework for Apple’s iOS, OS X and tvOS

developed in Metal and Swift

Amund Tveit

∗

Memkite

Torbjørn Morland*

Memkite

Thomas Brox Røst*

Atbrox

Abstract

In this paper we present DeepLearningKit - an open source framework that sup-

ports using pre- trained deep learning models (convolutional neural networks) for

iOS, OS X and tvOS. DeepLearningKit is developed in Metal in order to utilize the

GPU efﬁciently and Swift for integration with applications, e.g. iOS-based mobile

apps on iPhone/iPad, tvOS-based apps for the big screen, or OS X desktop appli-

cations. The goal is to support using deep learning models trained with popular

frameworks such as Caffe, Torch, TensorFlow, Theano, Pylearn, Deeplearning4J

and Mocha. Given the massive GPU resources and time required to train Deep

Learning models we suggest an App Store like model to distribute and download

pretrained and reusable Deep Learning models.

1 Introduction

The Metal programming language is the recommended and most the efﬁcient way of utilizing the

GPU on Apple’s iOS since 2014 [1, 2, 3, 4], and tvOS and OSX since 2015 [5, 6, 7]. This paper

gives an overview of a Metal and Swift based Deep Learning library named DeepLearningKit,

in particular parts of Metal convolutional neural network operators for the GPU. DeepLearningKit

supports on-device Deep Learning on Apple’s iOS, OS X and tvOS.

DeepLearningKit currently has shader functions for convolutional neural networks implemented in

Metal and parallelized for the GPU - operators include: convolution, pooling, rectiﬁer and softmax.

In terms of deep learning model supported it has support for Min Lin’s Caffe-trained Network In

Network[8] (NIN - trained on CIFAR-10, CIFAR-100 and ImageNet data sets). We also have pre-

liminary support running Theano[9] trained LeNet (trained on MNIST digit classiﬁcation dataset).

The reason we have chosen NIN is that the network is small compared to other deep convolutional

neural networks, but at the same time provide very high classiﬁcation accuracy on images, e.g.

better than AlexNet. GoogleLeNet (winner of Imagenet 2014) uses a similar approach as NIN[?].

NIN can perhaps also be used in non-image domains, e.g speech recognition[10] or natural lan-

guage processing[11]. In particular one could attempt to adapt Zhang and Lecun’s encoding and 1D

convolutional operators in “Text Understanding from Scratch”[12] and use it with NIN.

2 DeepLearningKit

This section gives describes how DeepLearningKit was built and with early empirical results using

it.

∗

https://DeepLearningKit.org

1

Figure 1: DeepLearningKit

2.1 Metal GPU Compute API in a Nutshell

All of the conﬁguration of Metal happens in Swift (or Objective-C), and Metal itself is where to

write the computational functions (shaders)

Metal has a threading model similar to Vulkan (SPIR-V) as shown in ﬁgure 2 (source: [13]), with one

or several command queues (MTLCommandQueue) that each store and run a sequence of command

buffers (MTLCommandBuffer) that processes data on the GPU (MTLBuffer). Figure 3 shows a

(partial) comparison between Metal/Swift API and C++/OpenCL (OpenCL can be used to generate

Vulkan/SPIR-V code).

Each MTLCommandBuffer has a compute command encoder (MTLComputeCommandEncoder)

that speciﬁes how the command buffer should be executed on the GPU, e.g. number of threadgroups

and threads per threadgroup (speciﬁed with MTLSize and dispatchThreadGroups()) as well as the

Metal shader function to perform (MTLFunction) that is loaded from the Metal (source or binary)

Library (MTLLibrary). The Metal shader function, e.g. convolution() or rectiﬁer() is wrapped

inside a compute pipeline descriptor (MTLComputePipeLineDescriptor) before it is inserted into

the MTLCommandBuffer.

Since Convolutional Neural Networks is a set of layers (typically with matrix or vector calculations

per layer), we represented each layer as a MTLCommandBuffer (with the approriate Metal shader)

and inserted all of those into a MTLCommandQueue. Data (both on Swift and Metal side) was

pre-allocated (e.g. MTLBuffer) before the calculation was started on the GPU.

2.2 GPU algorithms used in DeepLearningKit

Calculating convolution layers are the most computationally expensive part of deep convolutional

neural networks, since it involves matrix multiplication - typically with the GEneral Matrix to Matrix

Multiplication (GEMM) function parallelized for the GPU.

The approach for GPU based GEMM used in DeepLearningKit is similar to that of Nvidia’s cuDNN

CUDA based Deep Learning library, i.e. using an im2col() transformation followed by convolution()

function, see Shaders.metal on github.com/deeplearningkit/deeplearningkit for implementation.

2

Figure 2: Metal - similar setup as Vulkan (SPIR-V)

Figure 3: Metal/Swift compared to C++/OpenCL

2.3 Experiences with PowerVR G6430/GT7600 on iPhone 5S/6S

The performance of DeepLearningKit from iPhone 5S (with PowerVR G6430 according to The

iPhone 5S Review (AnandTech)) to iPhone 6S (with PowerVR GT7600 according to Apple iPhone

6S Plus vs. Samsung Galaxy S6 Edge+) we got 1 order of magnitude in improved performance.

Calculation time to run through a 20 layer deep convolutional neural network model for image

recognition went from approximately 2 seconds to less than 100 milliseconds. The network we

used was NIN network trained on CIFAR-10. Based on XCode proﬁling we suspect that the Metal

compute drivers for the GPU weren’t ﬁne tuned, so with lower level tools (e.g. for OpenCL/Vulkan

SPIR-V) for tuning for the GPU we could probably improve performance quite a bit.

(Note that 100 milliseconds or in other words 0.1 seconds is what Jacob Nielsen stated is one of 3

important response times that a user feels a system reacts instantenously)

Based on XCode proﬁling with Instruments (ﬁgure 4) we suspect that our Metal/Swift code and

perhaps the underlying Metal compute drivers still have potential to be improved (the time required

to run through the network in a forward pass is about 93 milliseconds (ref lower right in ﬁgure ),

but Xcode instruments shows that the total duration for the GPU compute steps are about 0.5 mil-

liseconds (537.62 microseconds, ref blue line at the bottom of ﬁgure 3), i.e. i.e. only approximately

1/200th of the total forward pass time (note: the entire forward pass does more than computation

3

on the GPU, the most likely time cost is memory allocation/copying and synchronization between

GPU and CPU)

Figure 4: DeepLearningKit run - XCode Instruments Output - GPU Hardware

2.4 Effort needed to port from Metal/Swift to OpenCL/Vulkan Compute SPIR-V

Code needed to set up and run deep learning on the GPU, load/save data, and setup the deep learning

pipeline (convolutional neural network)is done is done in Swift (for easy app integration on iOS, OS

X and tvOS), but can be moved to a language of selection (e.g. Java on Android or C++/C on other

devices). The Swift API for setting up Metal resembles the corresponding OpenCL C API as shown

in Figure 3.

The Deep Learning GPU code (e.g. shader functions with calculations of convolution etc) is written

in Metal, a language that is a subset C++11 and also has its own (relatively few) additions compared

to C++11. Porting the Metal code GPU code to OpenCL should be relatively straight forward since

OpenCL is also a subset of C++, as an example see ﬁgures 5 and 6 for a rectiﬁer function written in

both Metal and OpenCL. Going from OpenCL to Vulkan SPIR-V can be done with compiler (ﬁgure

??) for further proﬁling and optimization.

Figure 5: Rectiﬁer Function in Metal

Figure 6: Rectiﬁer Function in OpenCL

Threading model in Vulkan is close to 1-1 with Metal (ﬁgure 2), so that should not be an issue for

porting

4

2.5 Roadmap for DeepLearningKit

Here follows a brief overview of things we are working on or is on our roadmap.

1. use FFT-based convolution - with precalculated convolution ﬁlters [14, 15]

2. use lower resolution on ﬂoating point - in order to increase performance and support larger

models (for now it uses 32 bit ﬂoat or complex numbers - i.e. 2x32 bit per complex number

to prepare for FFT-based convolution) [16, 17]

3. avoid copying memory between CPU and GPU more than needed [18]

4. add support for other types of pre-trained networks than deep convolutional neural net-

works, e.g. recurring neural networks[19, 20]

5. look into more in-place calculations to save memory, i.e. supporting larger models

6. try to exploit larger parts of Metal API wrt memory layout, threadgroups to increase per-

formance (this relates to 1.) [21, 22, 23, 24, 25]

7. Look into teacher-student deep networks or other compressed models for even smaller but

still high quality models (recent research have shown AlexNet models being compressed

from 240MB to 6.9MB), see the paper [A Deep Neural Network Compression Pipeline]

8. Look into algorithms for approximate matrix multiplication (i.e. convolution step speedup)

to further increase speed (and reduce energy usage), interesting techniques include a) [Ap-

proximating matrix multiplication and low-rank approximation], [Fast Approximate Matrix

Multiplication by Solving Linear Systems] and [Fast Monte-Carlo Algorithms for Approx-

imate Matrix Multiplications].

9. Look into a broad set of Deep Learning applications, e.g. categories in ﬁgures 7 from the

research bibliography at [http://Deeplearning.University]. It might be application speciﬁc

optimizations that can be done, e.g. in the case of natural language processing with convo-

lutional neural networks one uses 1D convolution instead of 2D (as in image classiﬁcation).

3 App Store for Deep Learning Models

Given the immense asymmetry in time taken to train a Deep Learning Model versus time needed to

use it (e.g. to do image recognition), it makes perfect sense to build a large repository of pre-trained

models that can be (re)used several times. Since there are several popular tools used to train Deep

Learning models (e.g. Caffe, Torch, Theano, DeepLearning4J, PyLearn and Nervana) were working

on supporting importing pre-trained models in those tools into an app store for deep learning models

(currently weve been primarily been working with Caffe CNN models).

The tweet in Figure 8 illustrates how much energy is required to train a Deep Network (per night),

some Deep Learning Models can take weeks of training on GPUs like the Nvidia TitanX, or in other

words piles of wood of energy. Using a model is quite different since it requires less energy than

lighting match. See ﬁgures 9 and 10 for an illustration of this.

Deep Learning Models also typically have a (low) limit in the number of classes they can predict per

model (e.g. in the ImageNet competition there are 1000 classes, CIFAR-100 100 classes and CIFAR-

10 10 classes). This means that in order to create real-life applications one need to intelligently (and

very rapid load them from SSD into GPU accessible RAM) switch between several Deep Learning

Models, or if there is enough capacity one can run several models in parallel on the same GPU.

Selecting an approriate Deep Learning model (i.e. which is the most likely to work well in a given

context) is to our knowledge not a well-studied ﬁeld of research, and in some ways it resembles the

meta or universal search problem found in web search (e.g. cross-model ranking), but latency plays

an even bigger part in the mobile on-device case (dont have time to run many models). We have

some ideas for a meta model for selecting a model to use, which can use input like location, time of

day, and camera history to predict which models might be most relevant.

With state-of-the-art compression techniques for Convolutional Neural Network the (groundbreak-

ing) AlexNet model from 2012 can be compressed from 240MB to 6.9MB. This means that one

could theoretically ﬁt more than eighteen thousand AlexNet models on a 128 GB mobile device like

the iPhone 6!

5