HPC Guru (Twitter)
.@AMD Hits the #ROCm Reset Switch with 5.0
With two #Exascale #supercomputers using its GPUs, AMD needs to keep investing in a software platform that scales - and think about #FPGA support post @XilinxInc acquisition
https://www.servethehome.com/amd-hits-the-rocm-reset-switch-with-5-0-get-excited/
#HPC #AI #GPU via @ServeTheHome
.@AMD Hits the #ROCm Reset Switch with 5.0
With two #Exascale #supercomputers using its GPUs, AMD needs to keep investing in a software platform that scales - and think about #FPGA support post @XilinxInc acquisition
https://www.servethehome.com/amd-hits-the-rocm-reset-switch-with-5-0-get-excited/
#HPC #AI #GPU via @ServeTheHome
ServeTheHome
AMD Hits the ROCm Reset Switch with 5.0 - Get Excited
AMD ROCm 5.0 has made some notable quality-of-life improvements for developers, and AMD now has a hint of FPGA in its ROCm definition
HPC Guru (Twitter)
👇Folks working on @AMDInstinct, please read the comments in response to the tweet below and do take the input from @eriklindahl and @never_released seriously
Having competitive #GPU hardware is of little use if the accompanying software ecosystem is lacking
#HPC #AI @AMD
-----------
@HPC_Guru:
.@AMD Hits the #ROCm Reset Switch with 5.0
With two #Exascale #supercomputers using its GPUs, AMD needs to keep investing in a software platform that scales - and think about #FPGA support post @XilinxInc acquisition
https://t.co/aGmIvrpbPK
#HPC #AI #GPU via @ServeTheHome
👇Folks working on @AMDInstinct, please read the comments in response to the tweet below and do take the input from @eriklindahl and @never_released seriously
Having competitive #GPU hardware is of little use if the accompanying software ecosystem is lacking
#HPC #AI @AMD
-----------
@HPC_Guru:
.@AMD Hits the #ROCm Reset Switch with 5.0
With two #Exascale #supercomputers using its GPUs, AMD needs to keep investing in a software platform that scales - and think about #FPGA support post @XilinxInc acquisition
https://t.co/aGmIvrpbPK
#HPC #AI #GPU via @ServeTheHome
Twitter
HPC Guru
.@AMD Hits the #ROCm Reset Switch with 5.0 With two #Exascale #supercomputers using its GPUs, AMD needs to keep investing in a software platform that scales - and think about #FPGA support post @XilinxInc acquisition servethehome.com/amd-hits-the-r… #HPC…
HPC Guru (Twitter)
👏👏 @AMD has #OpenSource #HPL and #HPCG implementations
#HPC #Exascale #GPU #ROCm via @nicholasmalaya
-----------
@nicholasmalaya:
Exascale software should be in the hands of the #hpc community! That's why we at AMD have open sourced HPL. This is AMD's software that contributed to the Exaflop runs on Frontier. https://t.co/hIOUymE2kT
👏👏 @AMD has #OpenSource #HPL and #HPCG implementations
#HPC #Exascale #GPU #ROCm via @nicholasmalaya
-----------
@nicholasmalaya:
Exascale software should be in the hands of the #hpc community! That's why we at AMD have open sourced HPL. This is AMD's software that contributed to the Exaflop runs on Frontier. https://t.co/hIOUymE2kT
HPC Guru (Twitter)
Having created a unified AI inferencing stack, @AMD has to create a unified #HPC & #AI training stack atop #ROCm
Then the hard work starts - getting applications ported
This is the only way to beat Nvidia and to keep Intel off balance
https://www.nextplatform.com/2022/07/08/now-comes-the-hard-part-amd-software/
@TheNextPlatform
Having created a unified AI inferencing stack, @AMD has to create a unified #HPC & #AI training stack atop #ROCm
Then the hard work starts - getting applications ported
This is the only way to beat Nvidia and to keep Intel off balance
https://www.nextplatform.com/2022/07/08/now-comes-the-hard-part-amd-software/
@TheNextPlatform
The Next Platform
Now Comes The Hard Part, AMD: Software
From the moment the first rumors surfaced that AMD was thinking about acquiring FPGA maker Xilinx, we thought this deal was as much about software as it
HPC Guru (Twitter)
RT @mindcrime: @HPC_Guru @AMD Software *is* a big weakness for @AMD right now. However much AMD is investing in the #ROCm team, they should triple it -tomorrow-. It's basically impossible for them to invest too much into their software stack. It's that or let #NVIDIA walk away with a trillion dollars...
RT @mindcrime: @HPC_Guru @AMD Software *is* a big weakness for @AMD right now. However much AMD is investing in the #ROCm team, they should triple it -tomorrow-. It's basically impossible for them to invest too much into their software stack. It's that or let #NVIDIA walk away with a trillion dollars...
HPC Guru (Twitter)
👇 @tekwendell on how Google seems to have lost a huge lead in #AI to Nvidia, and how AMD’s #GPU software (#ROCm) improvements are making it a viable contender for #ML
#AI #HPC via @wkmyrhang
👇 @tekwendell on how Google seems to have lost a huge lead in #AI to Nvidia, and how AMD’s #GPU software (#ROCm) improvements are making it a viable contender for #ML
#AI #HPC via @wkmyrhang
HPCwire (Twitter)
As AI continues to expand, the choice of software stacks like #CUDA, #ROCm, and #oneAPI becomes crucial for performance and productivity in #GPU-centric tasks. Our latest article delves into these software stacks and explores higher-level #HPC languages. ow.ly/7v5h50SpwYE
As AI continues to expand, the choice of software stacks like #CUDA, #ROCm, and #oneAPI becomes crucial for performance and productivity in #GPU-centric tasks. Our latest article delves into these software stacks and explores higher-level #HPC languages. ow.ly/7v5h50SpwYE
HPCwire (Twitter)
AMD Expands ROCm 6.3 with Optimized Libraries for AI and HPC Workflows
ow.ly/zEL650UgcxI #AMD #ROCm #HPC #TCIwire
AMD Expands ROCm 6.3 with Optimized Libraries for AI and HPC Workflows
ow.ly/zEL650UgcxI #AMD #ROCm #HPC #TCIwire
HPCwire
AMD Expands ROCm 6.3 with Optimized Libraries for AI and HPC Workflows
Nov. 26, 2024 — AMD has announced the release of ROCm 6.3 open-source platform, introducing advanced tools and optimizations to elevate AI, ML, and HPC workloads on AMD Instinct GPU […]
HPC Guru (Twitter)
RT @EmadBarsoumPi: Want to try R1 on MI300X? We are keeping improving the performance at fast pace, in two weeks we went from 1472 tok/sec to 5921 tok/sec!!! #AMD #ROCm #ML #AI #sglang #AIG https://twitter.com/AnushElangovan/status/1893377685721858375#m
RT @EmadBarsoumPi: Want to try R1 on MI300X? We are keeping improving the performance at fast pace, in two weeks we went from 1472 tok/sec to 5921 tok/sec!!! #AMD #ROCm #ML #AI #sglang #AIG https://twitter.com/AnushElangovan/status/1893377685721858375#m
X (formerly Twitter)
Emad Barsoum (@EmadBarsoumPi) on X
Want to try R1 on MI300X? We are keeping improving the performance at fast pace, in two weeks we went from 1472 tok/sec to 5921 tok/sec!!! #AMD #ROCm #ML #AI #sglang #AIG
HPCwire (Twitter)
AMD Advances Open AI Vision with New GPUs, Developer Cloud and Ecosystem Growth
ow.ly/UlUF50W8BlF #AMD #ROCm #MI350 #HPC
AMD Advances Open AI Vision with New GPUs, Developer Cloud and Ecosystem Growth
ow.ly/UlUF50W8BlF #AMD #ROCm #MI350 #HPC
HPCwire
AMD Advances Open AI Vision with New GPUs, Developer Cloud and Ecosystem Growth
SANTA CLARA, Calif., June 12, 2025 — AMD today delivered its comprehensive, end-to-end integrated AI platform vision and introduced its open, scalable rack-scale AI infrastructure built on industry standards at its […]