Discover and read the best of Twitter Threads about #TPU
Most recents (5)
@boblautenbach @Alan_L_Lovejoy @Ryu_Zoku Yes Chris Lattner is very interesting, been following his #LLVM and #SWIFT work.
1/
1/
@boblautenbach @Alan_L_Lovejoy @Ryu_Zoku Actually #ZokuTalk adopts the portion of SWIFT #EBNF for #Unicode as they seems have done good job on that, as well as parts of the EBNF for numerics such as "1_234.00" to expand privative data types entry.
\2
\2
@boblautenbach @Alan_L_Lovejoy @Ryu_Zoku Borrowing C & Assembly data types: 0b0011, 0xFF, keeping 16r0A, plus many others.
Actually the numeric formats are one of more complicated part of the #EBNF of #ZokuTalk and the only non-#MOBS (#Messages #Objects #Block #Syntax) part of the evolved syntax.
\3
Actually the numeric formats are one of more complicated part of the #EBNF of #ZokuTalk and the only non-#MOBS (#Messages #Objects #Block #Syntax) part of the evolved syntax.
\3
A short thread on accelerated computing. How $TSLA's #Dojo, $GOOG's #TPU #Cerebras's #WSE-2, #Graphcore's #IPU, and others compare to $NVDA 's #GPU. This is an extract of work we published a few weeks ago. 👇1/6
It is difficult to compare chips. Designing a chip is all about managing trade-offs between multiple dimensions. A chip has limited potential resources and the architect allocates them over these multiple dimensions. 2/6 
With this framework in mind, one sees alternatives to #GPU have fundamentally different architectures, favoring the flow of data across the chip vs. the flow of data between the memory and the chip. 3/6
(1) Possible buyout of #ARM by #NVIDIA does have an effect on the #Bioinformatics field: many applications now are deployable on CPU/GPUs with #ARM and/or #NVIDIA chips on them. Some recent examples are:
(a) the Oxford @nanopore MinION Mk1c device, which originally was specced at Jetson TX2 ARM+Pascal GPU accelerators (ARM processor 6 cores, 256 Core GPU), 8 GB RAM (may have changed since then.
I will be live tweeting @Tesla AI Day Here. Personally looking at the data flow, latency, low power and performance of #Dojo and how it compares to @Google #TPU version 4 and other HPC systems and how it directly relate to #AutonomousVehicles #FSDBeta
Well as usual, Tesla is fashionably late and we are almost 18 mins past the start time. And the beat goes on...
#AIDay starts with a demo of FSD with the driver griping the steering wheel with his left hand in what looks to be the streets of California. #DojovsTPU #Dojo @Tesla
Remember the #BachDoodle? We’re excited to release paper on Behind-the-Scenes design, #ML, scaling it up, and dataset of 21.6M melodies from around the world!
📜 arxiv.org/abs/1907.06637
w/ @fjord41 @ada_rob @notwaldorf @bengiswex Leon Hong @jaxcooo
📜 arxiv.org/abs/1907.06637
w/ @fjord41 @ada_rob @notwaldorf @bengiswex Leon Hong @jaxcooo
tl; dr
1/ In three days, people spent 350 years worth of time playing with the Bach Doodle, and the “harmonize” button was clicked more than 55 million times.
1/ In three days, people spent 350 years worth of time playing with the Bach Doodle, and the “harmonize” button was clicked more than 55 million times.
2/ The model Coconet 🥥 is an instance of OrderlessNADE and uses Gibbs sampling to generate the harmonizations through rewriting.
📜 Previous blogpost: g.co/magenta/coconet
📝 Paper from #ISMIR 2017: arxiv.org/abs/1903.07227
📜 Previous blogpost: g.co/magenta/coconet
📝 Paper from #ISMIR 2017: arxiv.org/abs/1903.07227
