HPC Guru (Twitter)
From #desktops to #supercomputers, from the #datacenter to the #cloud, #ARM poses the greatest threat to #x86 dominance in over a decade
#HPC #AI @Arm @intel @AMD @awscloud @Azure @nvidia
-----------
@suhaibkhan:
Apple’s gamble, with the M1, is that its custom CPU performance is now so high, at such low power consumption, that the choice of chip inside the system has become irrelevant within a given product generation.
https://t.co/TVYR3lPgZb #ARM #x86
From #desktops to #supercomputers, from the #datacenter to the #cloud, #ARM poses the greatest threat to #x86 dominance in over a decade
#HPC #AI @Arm @intel @AMD @awscloud @Azure @nvidia
-----------
@suhaibkhan:
Apple’s gamble, with the M1, is that its custom CPU performance is now so high, at such low power consumption, that the choice of chip inside the system has become irrelevant within a given product generation.
https://t.co/TVYR3lPgZb #ARM #x86
Twitter
Suhaib Khan
Apple’s gamble, with the M1, is that its custom CPU performance is now so high, at such low power consumption, that the choice of chip inside the system has become irrelevant within a given product generation. extremetech.com/computing/3221… #ARM #x86
HPC Guru (Twitter)
RT @hpcnotes: It’s fun to speculate about future CPUs for #HPC - so time to predict the future …
In 2030, which processor architecture will be the strongest challenger (ie 2nd place) to the dominant architecture of that time?
Will the challenger be #ARM, #RISCV, #x86, or something else?
RT @hpcnotes: It’s fun to speculate about future CPUs for #HPC - so time to predict the future …
In 2030, which processor architecture will be the strongest challenger (ie 2nd place) to the dominant architecture of that time?
Will the challenger be #ARM, #RISCV, #x86, or something else?
HPC Guru (Twitter)
Don’t miss this interesting and wide ranging interview of Jim Keller by @IanCutress in @anandtech
“I think we've barely scratched the surface on what's possible. “
https://www.anandtech.com/show/16762/an-anandtech-interview-with-jim-keller-laziest-person-at-tesla
#HPC #AI #CPU #GPU #x86 #ARM #RISCV #MooresLaw #AMD #Intel #Tesla
Don’t miss this interesting and wide ranging interview of Jim Keller by @IanCutress in @anandtech
“I think we've barely scratched the surface on what's possible. “
https://www.anandtech.com/show/16762/an-anandtech-interview-with-jim-keller-laziest-person-at-tesla
#HPC #AI #CPU #GPU #x86 #ARM #RISCV #MooresLaw #AMD #Intel #Tesla
HPC Guru (Twitter)
RT @HatemLtaief: Support for Hardware #heterogeneity: the question is not when… but how? Slides from production manager Tsutomu Takeda @NEC_corp during #ISC21 webinar. Interesting system integration: #vector #x86 #GPU #storage #Infiniband. Help! :-) https://twitter.com/HatemLtaief/status/1410156221181665281/photo/1
RT @HatemLtaief: Support for Hardware #heterogeneity: the question is not when… but how? Slides from production manager Tsutomu Takeda @NEC_corp during #ISC21 webinar. Interesting system integration: #vector #x86 #GPU #storage #Infiniband. Help! :-) https://twitter.com/HatemLtaief/status/1410156221181665281/photo/1
HPC Guru (Twitter)
EPYC is EPIC!
👇 Thread by @HatemLtaief on accelerating RT calculations for giant telescopes
@AMD Rome leads the pack (including HBM based CPUs) in terms of sustained bandwidth for their code by fitting into LLC
#HPC #SC21
-----------
@HatemLtaief:
The return of #x86… Compress algebraically the operator, fit into LLC, and run at cache bandwidth speed. This turns out to nicely work on #AMD #Epyc processors, making #HBM based hardware jealous :-) #SC21 #HPC #astronomy https://t.co/ALhDWoTzVw
EPYC is EPIC!
👇 Thread by @HatemLtaief on accelerating RT calculations for giant telescopes
@AMD Rome leads the pack (including HBM based CPUs) in terms of sustained bandwidth for their code by fitting into LLC
#HPC #SC21
-----------
@HatemLtaief:
The return of #x86… Compress algebraically the operator, fit into LLC, and run at cache bandwidth speed. This turns out to nicely work on #AMD #Epyc processors, making #HBM based hardware jealous :-) #SC21 #HPC #astronomy https://t.co/ALhDWoTzVw
HPC Guru (Twitter)
Intel Launches $1B Fund to Build a Foundry Innovation Ecosystem
New fund will strengthen @Intel’s foundry business & support design approaches that leverage multiple instruction set architectures (ISAs), spanning #x86, #ARM and #RISCV
https://www.intel.com/content/www/us/en/newsroom/news/intel-launches-1-billion-fund-build-foundry-innovation-ecosystem.html
#HPC #AI
Intel Launches $1B Fund to Build a Foundry Innovation Ecosystem
New fund will strengthen @Intel’s foundry business & support design approaches that leverage multiple instruction set architectures (ISAs), spanning #x86, #ARM and #RISCV
https://www.intel.com/content/www/us/en/newsroom/news/intel-launches-1-billion-fund-build-foundry-innovation-ecosystem.html
#HPC #AI
HPC Guru (Twitter)
"That's the first time in Intel's history we'll license x86 soft cores and hard cores to customers who would like to develop chips"
@Intel's plan to license #x86 cores for chips with Arm, RISC-V and more inside
https://www.theregister.com/2022/02/14/intel_x86_licensing/
#HPC #AI via @TheRegister
"That's the first time in Intel's history we'll license x86 soft cores and hard cores to customers who would like to develop chips"
@Intel's plan to license #x86 cores for chips with Arm, RISC-V and more inside
https://www.theregister.com/2022/02/14/intel_x86_licensing/
#HPC #AI via @TheRegister
The Register
Intel's plan to license x86 cores for chips with Arm, RISC-V and more inside
If you've wanted to create your own specialized Xeon, now's your chance
HPC Guru (Twitter)
First Experiences in Performance #Benchmarking with the New #SPEChpc 2021 Suites
Evaluate portability and basic performance characteristics on various #HPC architectures, including #x86 CPU, @NVIDIA #GPU, and @AMD #GPU
https://arxiv.org/pdf/2203.06751.pdf
via @sunitachandra29
First Experiences in Performance #Benchmarking with the New #SPEChpc 2021 Suites
Evaluate portability and basic performance characteristics on various #HPC architectures, including #x86 CPU, @NVIDIA #GPU, and @AMD #GPU
https://arxiv.org/pdf/2203.06751.pdf
via @sunitachandra29
HPC Guru (Twitter)
Nvidia’s #Grace CPU Superchip is expected in 2023, so the only comparisons that will matter would be with other CPUs expected around then - not with previous generations from Intel & AMD
https://www.tomshardware.com/news/nvidia-claims-arm-grace-cpu-superchip-2x-faster-23x-more-efficient-than-intel-ice-lake
#HPC #AI #ARM #x86
Nvidia’s #Grace CPU Superchip is expected in 2023, so the only comparisons that will matter would be with other CPUs expected around then - not with previous generations from Intel & AMD
https://www.tomshardware.com/news/nvidia-claims-arm-grace-cpu-superchip-2x-faster-23x-more-efficient-than-intel-ice-lake
#HPC #AI #ARM #x86
HPC Guru (Twitter)
👇🧵 by @HatemLtaief on redesigning algorithms to utilize large L3 cache of AMD Milan-X to get a significant performance boost
Poster on temporal blocking using multicore #wavefront diamond (MWD) tiling technique
accepted at #SC22
#HPC
-----------
@HatemLtaief:
🚨 Latest results of #stencil computations using temporal blocking on @AMD #Epyc #MilanX 🚨
Expected but still wow! 🤩
Joint work w/ @LongQU and D. Keyes @KAUST_ECRC
#HPC #x86 #KAUSTResearch https://t.co/AwYG43VO5w
👇🧵 by @HatemLtaief on redesigning algorithms to utilize large L3 cache of AMD Milan-X to get a significant performance boost
Poster on temporal blocking using multicore #wavefront diamond (MWD) tiling technique
accepted at #SC22
#HPC
-----------
@HatemLtaief:
🚨 Latest results of #stencil computations using temporal blocking on @AMD #Epyc #MilanX 🚨
Expected but still wow! 🤩
Joint work w/ @LongQU and D. Keyes @KAUST_ECRC
#HPC #x86 #KAUSTResearch https://t.co/AwYG43VO5w
HPC Guru (Twitter)
RT @FelixCLC_: Hi everyone!
Was chatting with a few students and enthusiasts about the how CPUs got so fast. Covers SIMD, multi ALUs & Out of Order Execution
Added some practical examples that should be approachable to anyone who's written a loop
https://gist.github.com/FCLC/8322c7e0fd8746d256178c329e9d0de4
#CPU #HPC #x86 #arm #C
RT @FelixCLC_: Hi everyone!
Was chatting with a few students and enthusiasts about the how CPUs got so fast. Covers SIMD, multi ALUs & Out of Order Execution
Added some practical examples that should be approachable to anyone who's written a loop
https://gist.github.com/FCLC/8322c7e0fd8746d256178c329e9d0de4
#CPU #HPC #x86 #arm #C
Gist
An approachable introduction to how modern CPUs got fast, beyond throwing more GHz at the problem
An approachable introduction to how modern CPUs got fast, beyond throwing more GHz at the problem - Understanding how modern processors got fast: SIMD, multiple pipes and Out of Order execution.md
HPC Guru (Twitter)
ParaS is an implementation of the SYCL 2020 specification, developed for architectural and vendor neutral programming
The current version enables seamless execution across CPUs of #x86 (Intel and AMD) and #ARM as well as #CUDA enabled NVIDIA GPUs
#HPC #AI via @cdacindia https://twitter.com/cdacindia/status/1840063621981700424#m
ParaS is an implementation of the SYCL 2020 specification, developed for architectural and vendor neutral programming
The current version enables seamless execution across CPUs of #x86 (Intel and AMD) and #ARM as well as #CUDA enabled NVIDIA GPUs
#HPC #AI via @cdacindia https://twitter.com/cdacindia/status/1840063621981700424#m
HPC Guru (Twitter)
ARMed and dangerous? @AMD and @intel unite against a common threat
Or are they worried about a RISCVy future?
Should have done this much earlier
Would love to hear your thoughts
#x86 via @Patrick1Kennedy https://twitter.com/ServeTheHome/status/1846238721127178356#m
ARMed and dangerous? @AMD and @intel unite against a common threat
Or are they worried about a RISCVy future?
Should have done this much earlier
Would love to hear your thoughts
#x86 via @Patrick1Kennedy https://twitter.com/ServeTheHome/status/1846238721127178356#m
HPC Guru (Twitter)
ICYMI: @HPCwire looks back at some colorful moments in the #x86 history between @intel and @AMD
o AMD almost gave up on x86 in servers after major product flops
o Looking at Intel now, it is hard to imagine that it used to be the big bully
https://www.hpcwire.com/2024/10/21/celebrating-intel-amd-unity-looking-back-at-x86-flubs/
#HPC #AI
ICYMI: @HPCwire looks back at some colorful moments in the #x86 history between @intel and @AMD
o AMD almost gave up on x86 in servers after major product flops
o Looking at Intel now, it is hard to imagine that it used to be the big bully
https://www.hpcwire.com/2024/10/21/celebrating-intel-amd-unity-looking-back-at-x86-flubs/
#HPC #AI