HPC Guru @HPC_Guru Twitter profile

Pinned Tweet

HPC Guru

2 years

To pay tribute to #Frontier , the fastest publicized #supercomputer in the world today and the first official #Exascale system, I have changed my Twitter header to a picture of @ORNL It used to be a picture of Mount Fuji (for Fugaku) before #HPC #AI

1

19

115

Last Seen Profiles

@stw_pdg

@userisdowner

@RJ_Abeytia

@DiViNiUMMUSiC

@Havas

@smakids

@_heartarchive

@voleybolplus

@MaritimeTartan

@Neithgguk_

@hommedurif2

@katar1nabluu00

@CritterHoller

@ios_978

@mintmeal

@spidereno

@thillybilly

@MarziaPie

@LesDevalideuses

@_grsk_

@AFRODES_USA

@SStaffsPolice

@WeUp_exchange

@gans_rantau

@Epoha_portal

@RepJenKiggans

@hiraa_says

@chcscenter

@nezumipoo

@RADIOUTCH

@haroonuafghani

@pwettyplis

@JoinMaxcoin

@MuppetSilas

@Manuel_Ibarra

@sailor_yun

HPC Guru

@HPC_Guru

2 years

Finally, we broke the #Exascale barrier officially! Congratulations, @ORNL , @AMD , @HPE_Cray & everyone involved! #HPC #AI #Top500 #ISC22

11

119

360

HPC Guru

@HPC_Guru

3 years

Congratulations, @LisaSu , @AMD CEO, on being voted the Readers Choice for "Outstanding Leadership in #HPC " in @HPCwire 2021 Readers’ and Editors’ Choice Awards During #SC21

4

43

337

HPC Guru

@HPC_Guru

1 year

DGX GH200: Nvidia ties 256 Grace-Hopper Superchips by 36 NVLink Switches to provide >1 EF FP8 (or ~9PF of FP64) o 144TB unified memory o 900 GB/s GPU-to-GPU bandwidth o 128 TB/s bisection bandwidth o End-of-year availability #HPC #AI via @HPCwire

5

70

249

HPC Guru

@HPC_Guru

4 years

Great loss, especially for the #HPC community The “guy in the red hat“,Rich Brueckner, passed away last Wednesday Rich owned @insideHPC & @insideBigData

59

75

196

HPC Guru

@HPC_Guru

17 days

Robert Dennard, the inventor of DRAM, and famous for Dennard scaling, died on April 23 at the age of 91 #HPC via @dylan522p

9

51

190

HPC Guru

@HPC_Guru

4 years

#Top500 : Congratulations to #Fugaku team on being the new #1 on the @top500supercomp #HPC #AI #ISC20 #ARM

3

189

176

HPC Guru

@HPC_Guru

6 months

This graph of #datacenter revenue over the last 10 quarters does an excellent job of illustrating: o @Nvidia 's surge on the back of #GenAI o Continuing @Intel decline o @AMD is still relatively small in revenue Thanks to @DC__64 for sharing this #HPC #AI

10

46

167

HPC Guru

@HPC_Guru

8 months

How did @nvidia get here? Huang's Law The company’s chief scientist, Bill Dally, managed to sum it all up in a single slide during his keynote address to the IEEE’s #HotChips2023 #HPC #AI #GPU via @IEEESpectrum

7

41

160

HPC Guru

@HPC_Guru

2 years

How Much #Latency Does #CXL #Memory Introduce? #HPC #AI #HC34 via @ServeTheHome

1

43

157

HPC Guru

@HPC_Guru

6 months

One Giant Superchip for LLMs, Recommenders, and GNNs: Introducing NVIDIA #GH200 NVL32 Rack-scale solution within @NVIDIA DGX Cloud or an @awscloud instance, boasts a 32-GPU NVIDIA NVLink domain and a massive 19.5 TB of unified memory #AI #HPC #GenAI

6

43

160

HPC Guru

@HPC_Guru

2 months

#Blackwell : While @Nvidia has a clear lead at lower precision, it may have come at the expense of double precision performance, an area where @AMD has won multiple high-profile #supercomputer bids #GTC24 #HPC #AI via @Tobias_Writes @TheRegister

18

47

157

HPC Guru

@HPC_Guru

2 months

. @NVIDIA Flagship Accelerator Specification Comparison #B200 vs. #H100 vs. #A100 #AI #HPC #GPU #GTC24 via @anandtech

2

51

154

HPC Guru

@HPC_Guru

4 years

Congratulations to @AMDServer Rome on being voted the #HPC Processor of the Year 2020! And to @FujitsuHPC A64FX on coming in a strong 2nd. Thanks to all 363 of you who voted.

8

21

132

HPC Guru

@HPC_Guru

5 months

Intel CEO laments @Nvidia 's 'extraordinarily lucky' #AI dominance, claims it coulda-woulda-shoulda have been @Intel Things would be completely different if only Intel hadn't cancelled the #Larrabee #GPU

Intel CEO laments Nvidia's 'extraordinarily lucky' AI dominance, claims it coulda-woulda-shoulda...

Things would be completely different if only Intel hadn't cancelled the Larrabee GPU.

www.pcgamer.com

29

20

130

HPC Guru

@HPC_Guru

2 years

When I created this Twitter account 13 years, 2 months and 9 days ago, I never imagined I would have even a 1000 followers So reaching 20,000 followers is a pleasant surprise! Thanks to all who patiently bear my idiosyncrasies, lots of tweets about #HPC , and a few on mangoes🥭

11

9

136

HPC Guru

@HPC_Guru

1 year

New @AMDInstinct #MI300 Details Emerge, Debuts in 2 EF #ElCapitan #Supercomputer @Livermore_Lab 24-core Zen 4 CPU, CDNA 3 GPU, and 128GB of HBM3 all in one package, what's not to like? #ISC23 #HPC #AI #APU via @tomshardware

7

31

128

HPC Guru

@HPC_Guru

4 years

Fujitsu Begins Shipping #Supercomputer Fugaku #HPC #ARM #SVE #HBM via @ProfMatsuoka

0

81

126

HPC Guru

@HPC_Guru

8 months

Nvidia 1000x in 10 years: o Better Number Representation: 16x o Complex Instructions: 12.5x o Moore’s Law: 2.5x (Hint: 2.5 x over 10 years should tell us something!) o Sparsity: 2x o Model Efficiency #HPC #AI #GPU #HotChips2023

7

38

130

HPC Guru

@HPC_Guru

6 months

Singapore isn’t just rich, it’s #GPU -rich About 15% or $2.7 billion of @Nvidia 's revenue for the quarter ended October came from Singapore #AI #HPC

12

31

129

HPC Guru

@HPC_Guru

1 year

Intel Publishes Blazing Fast AVX-512 Sorting Library The code has been merged to Numpy and is providing some 10~17x speed-ups On an Intel Tigerlake system this sped-up 16-bit int sorting by 17x #HPC #AI via @HPCZorf @phoronix

Intel Publishes Blazing Fast AVX-512 Sorting Library, Numpy Switching To It For 10~17x Faster Sorts

Intel recently published an open-source C++ header file library for high performance SIMD-based sorting, which initially is focused on providing a lightning fast AVX-512 quicksort implementation

www.phoronix.com

5

31

126

HPC Guru

@HPC_Guru

5 months

TSMC plans chips with 200 billion transistors on a single piece of silicon on course to delivering chip packages with one trillion transistors 1nm-class #A10 fabrication processes by 2030 #HPC #AI via @tomshardware

2

37

127

HPC Guru

@HPC_Guru

9 years

"Prof. Mandelbrot? It's Dr. Schrödinger. I seem to have a problem." http://t.co/fC5YaJ7tRY #weekendhumor via @kfury @insideHPC

5

143

121

HPC Guru

@HPC_Guru

10 days

63rd #Top500 is out! o #Frontier @ORNL remains #1 o #Aurora @argonne becomes the 2nd official #Exascale #supercomputer o Only new #Top10 system is #Alps @cscsch #HPC #AI #ISC24

1

58

126

HPC Guru

@HPC_Guru

6 months

Farewell, #SC23 ! See you in Atlanta, and hoping you don't see me :-) #IamHPC #IamHPCGuru

4

6

124

HPC Guru

@HPC_Guru

1 year

“Our ( @nvidia ) entire data center family of products — #H100 , Grace CPU, Grace Hopper Superchip, NVLink, Quantum 400 InfiniBand and BlueField-3 DPU — is in production We are significantly increasing our supply to meet surging demand for them” #HPC #AI

4

25

124

HPC Guru

@HPC_Guru

5 months

Nvidia: At a recent launch event, @AMD talked about the inference performance of the #H100 #GPU compared to that of its #MI300X The results shared did not use optimized software, and the H100, if benchmarked properly, is 2x faster #LLM #GenAI

8

30

122

HPC Guru

@HPC_Guru

6 months

. @AMD is going to take @Nvidia directly on in the generative AI market, and it is absolutely and unequivocally going to sell as many #MI300A and #MI300X #GPU accelerators as it can make - @TDaytonPM #AI #GenAI #HPC

3

29

120

HPC Guru

@HPC_Guru

2 years

Federica Pisani has passed away. She was well known in the #supercomputing community and active on #HPC Twitter. @fedepisani had worked at Cray Inc. as Marketing Manager for Europe. #SC22 via @tdih_hpc

28

12

119

HPC Guru

@HPC_Guru

8 months

65 years later, #Fortran is still used in #HPC

MIT CSAIL

@MIT_CSAIL

8 months

Over 65 years ago this month, researchers ran the first FORTRAN program, considered the beginning of general-purpose programming: Image v/ @NASA

8

155

509

3

28

120

HPC Guru

@HPC_Guru

3 years

Samsung is advocating that performing computation in the memory die is faster and more efficient than taking the data back to a CPU, GPU, or accelerator Samsung HBM2-PIM and Aquabolt-XL at #Hotchips2021 #AI #HPC via @ServeTheHome

3

37

116

HPC Guru

@HPC_Guru

1 year

Gordon Moore, Intel Co-Founder, Dies at 94 He famously forecast in 1965 that the number of transistors on an integrated circuit would double every year – a prediction that later came to be known as Moore’s Law #HPC

3

63

118

HPC Guru

@HPC_Guru

6 months

62nd #Top500 list: #Frontier @ORNL remains #1 and is still the only #exascale #supercomputer on the list #Aurora @argonne submitted with HPL on half of the system is the new #2 at 585PF #HPC #AI #SC23

7

40

118

HPC Guru

@HPC_Guru

2 years

1/ Deep dive into #Graviton3 reveals it is a 7 die chiplet design Supports DDR5 & PCIe Gen5 #HPC #cloud #AWS via @ircolle

5

36

110

HPC Guru

@HPC_Guru

8 years

The power of math: 17 Equations That Changed the World, chosen by Ian Stewart #HPC via @paulcoxon

2

84

111

HPC Guru

@HPC_Guru

24 days

I’m back after a month long break from Twitter #HPC

13

6

110

HPC Guru

@HPC_Guru

3 months

#India plans 10,000- #GPU sovereign #AI #supercomputer Puts $1.2 billion on the table for #AI skills and local #LLMs #HPC #GenAI via @TheRegister @EvanKirstel

India plans 10,000-GPU sovereign AI supercomputer

Puts $1.2 billion on the table for AI skills and local LLMs, tells private enterprise it expects help

www.theregister.com

4

32

106

HPC Guru

@HPC_Guru

7 months

. @Intel Scores a Huge #Gaudi2 Win in NVIDIA #MLPerf Training v3.1 NVIDIA’s marketing slide shows Intel is up to 4x better performance per dollar versus NVIDIA (~8x the performance for ~32x the cost) #AI #ML via @ServeTheHome

5

21

107

HPC Guru

@HPC_Guru

2 years

U.S. officials order @Nvidia to halt sales of top #AI chips to #China The ban affects its #A100 and #H100 chips designed to speed up #MachineLearning tasks Nvidia shares fell 6.6% after hours #HPC #GPU

U.S. officials order Nvidia to halt sales of top AI chips to China

Chip designer Nvidia Corp said on Wednesday that U.S. officials told it to stop exporting two top computing chips for artificial intelligence work to China, a move that could cripple Chinese firms'...

www.reuters.com

8

47

103

HPC Guru

@HPC_Guru

6 months

. @Meta is skipping the ubiquitous #GPU and building #AI #inference and a #training chip on RISC-V #HPC @risc_v via @NicoleHemsoth

6

28

107

HPC Guru

@HPC_Guru

11 months

Matching Nvidia Performance With 0 Code Changes With MosaicML With the latest @PyTorch 2.0, @MosaicML Composer, and Foundry releases, @AMD hardware is now just as easy to use as @Nvidia hardware #AI #GenerativeAI #HPC #GPU via @dylan522p

3

34

105

HPC Guru

@HPC_Guru

5 years

Friday, March 9, will mark 10 years of @HPC_Guru on Twitter. After more than 33000 tweets, mainly on #HPC , I wonder if it is time to call it a day. Also need to decide whether I should reveal my identity or keep it a mystery.

44

9

106

HPC Guru

@HPC_Guru

1 year

Looking for NVIDIA alternatives given the long lead times for A100/H100 GPUs? Rumor: @Intel is trying to build demand for #Gaudi2 by placing a large (>1000 nodes) cluster in the Intel Developer Cloud #AI #HPC via @ServeTheHome

2

27

104

HPC Guru

@HPC_Guru

3 months

. @HPC_Guru came into existence 15 years ago today #HPC #MyTwitterAnniversary

10

6

103

HPC Guru

@HPC_Guru

1 year

At #GTC23 , @nvidia showed the Grace CPU Superchip for the first time to the public Claims of 1.2x performance and 1.7x energy efficiency improvements over latest x86 CPUs At iso-power, Grace CPU Superchip gives CSPs 2x the growth opportunity #HPC #AI #ARM

3

16

103

HPC Guru

@HPC_Guru

2 years

The 60th #Top500 list is officially released at #SC22 @ORNL ’s Exaflop machine #Frontier keeps top spot, new competitor Leonardo breaks the Top10 #HPC #AI

1

38

102

HPC Guru

@HPC_Guru

1 year

Largest US #semiconductor companies by market cap: 1. Nvidia 2. Broadcom 3. AMD 4. TI 5. Intel #HPC #AI via @matteastwood

7

37

100

HPC Guru

@HPC_Guru

1 year

I’m back after a long break, on a date which is the same in both formats (2/2/2023) What did I miss in the world of #HPC ?

24

6

100

HPC Guru

@HPC_Guru

2 years

Crusher is an early-access testbed for @ORNL 's upcoming #Frontier #supercomputer with identical hardware o @AMDServer EPYC 'Trento' CPU o @AMDInstinct MI250X 'Aldebaran' #GPU #HPC #AI #Exascale via @hms1193 @ProfMatsuoka

8

26

100

HPC Guru

@HPC_Guru

1 year

Can #Fortran survive another 15 years? Researchers @LosAlamosNatLab released an April 18 report evaluating the long-term risks of relying on Fortran for mission-critical code supporting nuclear security #HPC @GCNtech @fortranlang

15

38

99

HPC Guru

@HPC_Guru

4 years

This is Fran Allen, the first woman to receive the ACM Turing award. Her first assignment @IBM was to teach research scientists within IBM how to use #Fortran . She went on to work on compilers, including those for parallel systems. #HPC

Association for Computing Machinery

@TheOfficialACM

4 years

0

6

24

3

27

98

HPC Guru

@HPC_Guru

1 year

. @AMD is a bit more conservative than @intel about the time frame for #Zettascale @LisaSu at #ISSCC2023 : o #Supercomputers 2x perf every 1.2 years o Extrapolation implies Zetta by 2034 o Systems aren't small, systems aren't cheap! #HPC #AI via @IanCutress

7

28

98

HPC Guru

@HPC_Guru

2 months

👇Intel PVC Max 1550 outperformed NVIDIA and AMD offerings on the depleted fuel problems that were tested o 2.3x faster than the A100 o 1.2x faster than the GH200 o 1.8x faster than the AMD MI250X However no one clamoring for a Ponte Vecchio #HPC via @Underfox3

Underfox

@Underfox3

2 months

In this paper is presented the first performance evaluation of a scientific simulation application at scale on a supercomputer featuring Intel Max series (Ponte Vecchio) GPUs.

3

21

82

4

22

96

HPC Guru

@HPC_Guru

2 years

Frontier poster #HPC #ISC22 #Exacale

2

20

94

HPC Guru

@HPC_Guru

4 years

To pay tribute to #Fugaku , the fastest publicized #supercomputer in the world today, I have changed my Twitter header to a picture of Mount Fuji. #HPC #AI

3

14

96

HPC Guru

@HPC_Guru

3 years

ICYMI: Partial differential equations are kind of magical - and notoriously hard to solve. Researchers @Caltech introduced a new #DeepLearning technique for solving PDEs that is dramatically more accurate #AI #HPC via @techreview

2

19

91

HPC Guru

@HPC_Guru

5 months

👇 #H100 vs #MI300X : @AMD response to @Nvidia Even using TensorRT-LLM, #MI300X is comparable or better Should we wait for the Nvidia rebuttal? #AI #HPC via @nicholasmalaya

Nicholas Malaya

@nicholasmalaya

5 months

"MI300X using vLLM vs H100 using Nvidia's optimized TensorRT-LLM. Even when using TensorRT-LLM for H100 as our competitor outlined, and vLLM for MI300X, we still show a 1.3x improvement in latency." @HPC_Guru 👀

5

25

128

12

11

98

HPC Guru

@HPC_Guru

6 months

CuPBoP-AMD: Extending #CUDA to @AMD Platforms CuPBoPAMD is a CUDA translator that translates CUDA programs at NVVM IR level to HIP-compatible IR that can run on @AMDInstinct #GPUs #HPC #AI #SC23 via @hgpu

2

35

94

HPC Guru

@HPC_Guru

2 years

Hello, #SC22 ! It is terrific to be here in person. Jack Dongarra is on stage to give his Turing Award Lecture #HPC

3

9

94

HPC Guru

@HPC_Guru

2 years

Congratulations, @thoefler ! @ComputerSociety honors @ETH_en professor, Torsten Hoefler with the Sidney Fernbach Memorial Award for his pioneering contributions to large-scale parallel processing systems and #supercomputers #HPC #AI #SC22

Torsten Hoefler receives the Sidney Fernbach Award

ethz.ch

3

18

95

HPC Guru

@HPC_Guru

2 years

#Top500 : It’s an @AMD rout! Beyond the top ranked and first official #Exascale system, Frontier 5 of the Top10 and 10 of the Top20 #supercomputers are powered by @AMDServer EPYC All 3 new TOP10 machines are powered by AMD EPYC and @AMDInstinct #HPC #ISC22

0

27

92

HPC Guru

@HPC_Guru

3 years

122 years of #MooresLaw which was predicted by Gordon Moore in 1965 🤔 The number of people who incorrectly interpret Moore’s Law doubles every 18 months #HPC #AI

Steve Jurvetson

@FutureJurvetson

3 years

Tesla now holds the mantle of Moore’s Law. Just as NVIDIA took leadership from Intel a decade ago. While the substrate has shifted several times, humanity's capacity to compute has compounded for 122 years as if on rails. It's surreal. Log scale details:

150

896

6K

8

18

92

HPC Guru

@HPC_Guru

1 year

. @AMD 's Zen 5 could be integer performance champ, according to @tenstorrent CEO Jim Keller @jimkxa predicts that AMD's Zen 5 will be 30% faster than the current-gen Zen 4 in integer workloads #HPC #AI via @tomshardware

6

12

89

HPC Guru

@HPC_Guru

1 year

Intel Admits #GPU Mistakes, Reveals New #Supercomputing Chip Roadmap Falcon Shores, originally to be an XPU (unified CPU and GPU), is now a 2025 #GPU -only product for scientific and #AI computing #HPC #ISC23 via @HPCwire

5

26

92

HPC Guru

@HPC_Guru

6 months

Hype: Zettascale (FP64) by 2027 (Intel at #SC21 ) Reality: Unlikely to achieve 10 Exascale by end of the decade (Dongarra at #SC23 ) #SC23 #HPC #AI #Top500

7

16

92

HPC Guru

@HPC_Guru

6 months

Everything you wanted to know about #MI300A #APU programming but were afraid to ask Presented at ESPM2 at #SC23 #HPC #AI via @nicholasmalaya

0

28

89

HPC Guru

@HPC_Guru

5 months

This is really impressive - an Apple M3 Max with 16-core CPU, a 40-core GPU has a thermal design power (TDP) of 78 watts Delivers 774 GF DGEMM We have come a long way! Congratulations @Arm , @Apple ! #HPC via @FelixCLC_ @GabrielBaraldi3

fclc

@FelixCLC_

5 months

Folks, the *cut down* M3 Max (with 300GB/s!!) MBP is getting darn near 800 GFLOPS of DGEMM. let me repeat: a laptop *CPU* is getting nearly 800 GIGA Double Precision Floating point Operations Per Second.

3

14

82

3

18

92

HPC Guru

@HPC_Guru

2 years

After CUDA, there’s QODA NVIDIA Quantum-Optimized Device Architecture (QODA) is a platform for hybrid quantum-classical computers, enabling integration and programming of quantum processing units (QPUs), GPUs, & CPUs in one system #HPC #QuantumComputing

1

29

89

HPC Guru

@HPC_Guru

9 months

. @NVIDIA on the energy efficient design of the Grace-Hopper Superchip at #ATPESC23 Low power data movement and computation NVLink C2C: 1.3 pJ/bit #HPC #AI #ARM via @ogawa_tter

5

23

88

HPC Guru

@HPC_Guru

2 months

. @Meta shares details of the hardware, network, storage, design, performance, and software that make up its two new 24,576 #H100 #GPU clusters that the company is using to train its Llama 3 #LLM #AI #GenAI via @EvanKirstel @dcdnews

Meta reveals details of two new 24k GPU AI clusters

Have been built to support AI research and development

www.datacenterdynamics.com

3

20

86

HPC Guru

@HPC_Guru

2 years

Terry Quinn revealed that @AMD ’s forthcoming #MI300 #APU would be the computational bedrock of El Capitan, an #Exascale #supercomputer which is slated for installation @Livermore_Lab in late 2023 #HPC #AI #GPU via @TiffanyTrader

1

17

86

HPC Guru

@HPC_Guru

6 months

Steve Scott, previously at Cray and Microsoft, is now Corporate Fellow for Network and Systems Architecture @AMD Congratulations, Steve and AMD! #HPC #AI via @tdih_hpc

2

18

90

HPC Guru

@HPC_Guru

4 months

According to Citi's price projections for @AMD 's #MI300 #AI accelerators, @Nvidia currently charges up to four times more for its competing #H100 GPUs AMD's chips cost $10 to $15K apiece Nvidia's H100 has peaked beyond $40K #HPC #GPU via @tomshardware

Nvidia's H100 AI GPUs cost up to four times more than AMD's competing MI300X — AMD's chips cost $10...

AMD on track to generate billions on its Instinct MI300 GPUs this year, says Citi.

www.tomshardware.com

10

16

85

HPC Guru

@HPC_Guru

2 months

Jensen Huang before the black leather jacket! @WIRED prediction 20+ years ago #GTC2024 #AI #HPC via @rodolfor

Rodolfo Rosini ✨☕️

@rodolfor

2 months

Wired, 2002: “THE NEXT INTEL”

8

31

172

2

26

88

HPC Guru

@HPC_Guru

4 months

"There is no such thing as #AGI !" Years/decades to get to human-level #AI Recommended watching for this weekend: @ylecun delivers the Lytle Lecture @UW on Jan 24, 2024 "Objective-Driven AI: Towards Machines that can Learn, Reason, and Plan"

3

15

85

HPC Guru

@HPC_Guru

9 months

#MPI Application Binary Interface Standardization MPI is the most widely used interface for #HPC workloads A new level of MPI compatibility: a standard #ABI is proposed in this paper via @science_dot

3

18

85

HPC Guru

@HPC_Guru

5 months

. @LightmatterCo 's Passage is a silicon photonics interposer designed to support high speed chip-to-chip and node-to-node communications Claim: “all of the GPUs that are designed for #AI training and inference or #HPC are going to be built on Passage,”

4

21

84

HPC Guru

@HPC_Guru

1 year

Was Rialto a Bridge too far? Big Friday announcement from @Intel : Forget the #GPU , the future is #XPU Intel’s next-gen HPC part Falcon Shores (2025) will have CPU, GPU, and memory co-packaged #HPC #AI via @Patrick1Kennedy @ServeTheHome

4

13

84

HPC Guru

@HPC_Guru

10 months

RISC-V has now been promoted to an official Debian CPU architecture #RISCV @risc_v #HPC #AI

RISC-V Is Now An Official Debian Architecture

Debian 13 'Trixie' has been aiming for official RISC-V support and indeed it will happen: RISC-V has now been promoted to an official Debian CPU architecture.

www.phoronix.com

3

28

84

HPC Guru

@HPC_Guru

2 years

“Breaking the exaflop barrier was important, but doing so while achieving No. 1 on the Green500 list is remarkable“ The Beating Heart of the World’s First #Exascale #Supercomputer #HPC #AI via @IEEESpectrum

3

21

80

HPC Guru

@HPC_Guru

1 year

#Bergamo , @AMD ’s upcoming 128-core #cloud native server part sets new heights in x86 CPU performance Zen 4c delivers identical functionality of Zen 4 at about half of the core area #Hyperscale #HPC #AI via @dylan522p

Zen 4c: AMD’s Response to Hyperscale ARM & Intel Atom

Bergamo Volumes, ASP, Performance, Hyperscale Order Shift, Die Shot, Floorplan, Physical Design, and Future Use of Dense Core Variants

www.semianalysis.com

3

20

79

HPC Guru

@HPC_Guru

6 months

. @SKhynix & @Nvidia working on a #GPU redesign that 3D-stacks #HBM4 directly on top of the processing cores, eliminating interposers This resembles AMD's 3D V-Cache, which is placed directly on CPU dies, but HBM will be bigger capacity & cheaper #HPC

SK Hynix and Nvidia reportedly working on a radical GPU redesign that 3D-stacks HBM memory directly...

SK Hynix is working with Nvidia, other logic designers on HBM4 integration.

www.tomshardware.com

3

11

80

HPC Guru

@HPC_Guru

3 years

Congratulations @sunitachandra29 ! @exascaleproject Selects Sunita Chandrasekaran @brookhavenlab as Principal Investigator of the #SOLLVE Project #HPC #AI #Exascale #OpenMP #GPU via @HPCwire

5

9

82

HPC Guru

@HPC_Guru

6 months

. @AMD slaps together a silicon sandwich with #MI300 -series APUs, GPUs to challenge @Nvidia ’s #AI empire Chips boast 1.3x lead in #AI , 1.8x in #HPC over Nv's #H100 via @TheRegister

1

20

80

HPC Guru

@HPC_Guru

1 year

“My belief is in the next 5 to 10 years, RISC-V will take over all the data centers” Jim Keller interview with @sallywf @eetimes Jim added that this is especially true for scientific computing and #HPC He said #supercomputing could dominate even faster @risc_v #AI

EE Times | Electronic Engineering Times

@eetimes

1 year

The legendary CPU architect Jim Keller discusses Tenstorrent’s strategy, RISC-V and the future of #AI in an exclusive interview with EE Times. #RISCV

5

24

86

7

26

81

HPC Guru

@HPC_Guru

5 years

"Peak FLOPS is the best way to rank a #supercomputer or any other #HPC system"

Kate Hackett

@HackettKate

5 years

You've been kidnapped. Your kidnappers allow you to keep tweeting to pretend everything is alright. What would you tweet that would alarm your followers without the kidnappers knowing you're asking for help? "And then I put in the exact amount of garlic the recipe called for."

6K

1K

16K

5

7

82

HPC Guru

@HPC_Guru

3 years

Killer Instinct: @AMD ’s Multi-Chip MI200 #GPU Readies for a Major Global Debut o Frontier @ORNL o @LUMIhpc o Setonix @PawseyCentre #HPC #AI via @HPCwire

6

23

78

HPC Guru

@HPC_Guru

5 months

. @Nvidia ensures supply of #GH200 , #H200 products in 2024 by pre-purchasing more than $1 billion in HBM3E from @MicronTech and @SKhynix #HPC #AI via @tomshardware

Nvidia reportedly races to secure memory supply for next-gen H200 AI GPUs — pre-purchases $1.54...

Nvidia ensures supply of GH200, H200 products by pre-purchasing HBM3E.

www.tomshardware.com

5

16

80

HPC Guru

@HPC_Guru

1 year

Steadily chipping away Intel’s lead in the Data Center CPU market Analysts from research firm BRAID suggest @AMD is on the path of achieving up to 30% market share by the end of 2023 and will eventually get close to 40% by the end of 2025 #HPC #AI

2

14

82

HPC Guru

@HPC_Guru

2 years

Polaris, the newest #supercomputer at DOE’s Argonne National Laboratory, is now open to the research community Polaris is a 560 node @HPE_HPC system, each node has 1x @AMD Milan CPU + 4x @nvidia A100 #GPU #HPC #AI via @argonne_lcf @FelixCLeClair

3

13

80

HPC Guru

@HPC_Guru

5 years

#SC19 Stats: Number if attendees is 13,757 Representing 118 countries @Supercomputing is becoming like an #HPC United Nations 😊 #HPCIsNow via @david_schor

2

30

81

HPC Guru

@HPC_Guru

11 months

. @Intel has announced that all of #Aurora ’s 10,624 compute blades have been installed @argonne and it is expected to debut on the Nov #Top500 @CodeNative : “the largest #GPU cluster in the world” #HPC #AI @intelhpc via @HPCwire

6

14

81

HPC Guru

@HPC_Guru

1 year

How long will it take to train #GPT : #Fugaku vs. @OpenAI From presentation by @rioyokota "Distributed parallel learning of large-scale language models using Fugaku" #HPC #AI #LLM via @yutakashino @ProfMatsuoka

4

24

80

HPC Guru

@HPC_Guru

3 years

Big #HPC news via @NicoleHemsoth in @TheNextPlatform confirming what many suspected #China has already broken the (true/LINPACK) #exascale barrier in 2021—on more than one machine It seems they decided NOT to submit to #Top500 due to political issues

China Has Already Reached Exascale – On Two Separate Systems

More analysis "Why Did China Keep Its Exascale Supercomputers Quiet?" Native CPU and accelerator architectures that have been in play on China's previous

www.nextplatform.com

5

28

78

HPC Guru

@HPC_Guru

1 year

The Alps #supercomputer @cscsch will contain ~5,000 Grace Hopper modules, with four modules per node, use Slingshot networking @Nvidia says that Alps will be the first system to deploy the Grace Hopper Superchip #HPC #AI via @HPCwire

2

23

79

HPC Guru

@HPC_Guru

2 years

When transistors can’t get any smaller, the only direction is up @intel researchers on "3D-Stacked CMOS Takes Moore’s Law to New Heights" #HPC #AI via @IEEESpectrum

2

26

78

HPC Guru

@HPC_Guru

3 years

Welcome back Fortran: This dinosaur is back in the top 20 after more than 10 years #Fortran was the first commercial programming language ever, and is gaining popularity thanks to the massive need for (scientific) number crunching #HPC via @fortranlang

This old programming language is suddenly getting more popular again

Apple's Objective-C finally exits the top 20 list of popular programming languages tracked by Tiobe, but a 'dinosaur' language has had an unexpected boost.

www.zdnet.com

4

26

79

HPC Guru

@HPC_Guru

7 months

Apple #M3 Family of CPUs Launched with Some Shaky Performance Claims Does @Apple think it can just say up to x% faster without giving any details? @Patrick1Kennedy says FTC needs to get involved in Apple’s performance claims #ARM via @ServeTheHome

4

20

79

HPC Guru

@HPC_Guru

11 months

The #memory & #storage subsystems of #Aurora are incredible! 👇Capacity & (Peak bandwidth) numbers o 10.9 PB DDR5 (5.95 PB/s) o 1.36 PB CPU HBM (30.5 PB/s) o 8.16 PB GPU HBM (208.9 PB/s) o Storage: 230PB #DAOS (31 TB/s) #HPC #AI #Exascale

6

18

77

HPC Guru

@HPC_Guru

11 months

Somewhere along the way, @AMD ’s #APU dreams met @Livermore_Lab ’s needs and we have the #MI300A #MI300X (153B transistors across 12 chiplets) is the most complex compute engine that AMD has ever created The third time charm of @AMDInstinct #GPU #HPC #AI

3

10

77