Anna Tikhonova

Software Engineering Manager, ML Platform & Technology, Apple. Previously Metal Performance Shaders, Metal, OpenCL. My tweets reflect my opinions, not Apple's.

[Anna Tikhonova @atikhonova]

@tonic888 I hope your son recovers soon. Wishing you all the best.

[Anna Tikhonova @atikhonova]

@kaiserd_ The fork is suitable for both Intel-based Macs and Macs with the M1 chip, running macOS 11.0+. This includes machines with AMD GPUs.

[Anna Tikhonova @atikhonova]

Please check out this blog post describing how we leverage #MLCompute to accelerate TensorFlow training on Macs: https://t.co/S4H6iOpqJ3

[Anna Tikhonova @atikhonova]

@Sumenia We accelerate the TensorFlow and TensorFlow Addons ops, supported by #MLCompute. More information on ML Compute can be found here: https://t.co/yFMeMhdkkc

[Anna Tikhonova @atikhonova]

Please try out this pre-release version of Mac-optimized TensorFlow and help us improve it. Your feedback is very welcome!

[TensorFlow @TensorFlow]

⚡️ Accelerating TensorFlow 2 performance on Mac

@Apple’s new Mac-optimized TensorFlow 2.4 fork lets you speed up training on Macs, resulting in up to 7x faster performance on platforms with the new M1 chip!

Learn how ↓ https://t.co/ggaQeduCWl

[Gokhan Avkarogullari @gavkar]

We have a new tech talk about the GPU on Apple M1 chip powering Apple Silicon Macs:

https://t.co/gyOvmMkH0w

[Anna Tikhonova @atikhonova]

Great talk describing how to take advantage of low-level GPU profiling information for fine-tuning your app's performance to create faster and more fluid apps and gaming experiences in macOS Big Sur and iOS 14 https://t.co/dx8YMzrOon

[Anna Tikhonova @atikhonova]

@tonic888 This is very sad... I love Big Basin...

[Scott Gardner @scotteg]

Super excited about the new ML Compute framework, which accelerates training and validation of #MachineLearning neural networks using the CPU and GPUs in #macOS11, #iOS14, and #tvOS14. 🤯🥳🤩💯🚀

https://t.co/E6VyYEwDyO #WWDC2020

[Matthijs Hollemans @mhollemans]

New blog post: What's new with Apple machine learning in 2020 https://t.co/8WaHxuS9X1

[Anna Tikhonova @atikhonova]

MLCompute, new in macOS BigSur and iOS 14, accelerates training of neural networks on CPU, GPU, and multiple GPUs (e.g., Radeon Pro Vega II Duo in a Mac Pro). It uses Accelerate framework’s high performance BNNS primitives for the CPU and Metal Performance Shaders for the GPU.

[Apple @Apple]

It’s almost here. Watch the #WWDC20 Apple Special Event on June 22 on YouTube Live at 10:00 a.m. PDT.

[Gokhan Avkarogullari @gavkar]

I’d like to give some details on what is new on the new A13 Bionic GPU and #MetalAPI besides the performance and power improvements (1/13)

[Jerremy Holland @jerremy]

BayLearn 2018 is open for abstract submissions. If you are working on cutting-edge machine learning research, please consider submitting an abstract before the August 13th deadline. https://t.co/OghENJFbWj

[Anna Tikhonova @atikhonova]

@elverils Could you be a bit more specific? Which minute in the video?

[Anna Tikhonova @atikhonova]

There are two #MetalPerformanceShaders sessions at #WWDC18 this year: "Metal for Ray Tracing Acceleration” and "Metal for Accelerating Machine Learning”.

[Anna Tikhonova @atikhonova]

@s1ddok I see the "Metal 2 on A11" videos here: https://t.co/OBvu6ecKJM. Which link is not working for you?

[Anna Tikhonova @atikhonova]

@jpgdallas Do you have a specific question about SceneKit?

[Anna Tikhonova @atikhonova]

Watch the "Metal for Accelerating Machine Learning” session to learn how to train convolutional and recurrent neural networks (CNNs and RNNs) on the GPU using #MetalPerformanceShaders #WWDC2018 https://t.co/Ir7aZkas7f

[Anna Tikhonova @atikhonova]

@RedQueenCoder Thank you, @RedQueenCoder! It was great to meet you and Delia as well.