home.social

#a6000 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #a6000, aggregated by home.social.

  1. Apollo-Team: Sale of additional A6000 announced

    ...I am glad to announce that we will be able to offer another batch of 40 units for on-line sale and 20 units to be sold "live" on Amiga40 event....

    Full press release:

    amiga-news.de/en/news/AN-2025-

  2. Apollo-Team: Sale of additional A6000 announced

    ...I am glad to announce that we will be able to offer another batch of 40 units for on-line sale and 20 units to be sold "live" on Amiga40 event....

    Full press release:

    amiga-news.de/en/news/AN-2025-

    #Amiga #retrocomputing #ApolloVampire #A6000

  3. Apollo-Team: Sale of additional A6000 announced

    ...I am glad to announce that we will be able to offer another batch of 40 units for on-line sale and 20 units to be sold "live" on Amiga40 event....

    Full press release:

    amiga-news.de/en/news/AN-2025-

    #Amiga #retrocomputing #ApolloVampire #A6000

  4. Apollo-Team: Sale of additional A6000 announced

    ...I am glad to announce that we will be able to offer another batch of 40 units for on-line sale and 20 units to be sold "live" on Amiga40 event....

    Full press release:

    amiga-news.de/en/news/AN-2025-

    #Amiga #retrocomputing #ApolloVampire #A6000

  5. Apollo-Team: Sale of additional A6000 announced

    ...I am glad to announce that we will be able to offer another batch of 40 units for on-line sale and 20 units to be sold "live" on Amiga40 event....

    Full press release:

    amiga-news.de/en/news/AN-2025-

    #Amiga #retrocomputing #ApolloVampire #A6000

  6. The new keyboard computer "Apollo A6000" already sold out. But if you want to inform yourself:

    amiga-news.de/en/news/AN-2025-

    PS: on Friday 26-9-2025 Apollo team will post the Apollo A6000 roadmap for the next batch(es) including details on timeline and options.

  7. The new keyboard computer "Apollo A6000" already sold out. But if you want to inform yourself:

    amiga-news.de/en/news/AN-2025-

    PS: on Friday 26-9-2025 Apollo team will post the Apollo A6000 roadmap for the next batch(es) including details on timeline and options.

    #retrocomputing #A6000

  8. The new keyboard computer "Apollo A6000" already sold out. But if you want to inform yourself:

    amiga-news.de/en/news/AN-2025-

    PS: on Friday 26-9-2025 Apollo team will post the Apollo A6000 roadmap for the next batch(es) including details on timeline and options.

    #retrocomputing #A6000

  9. The new keyboard computer "Apollo A6000" already sold out. But if you want to inform yourself:

    amiga-news.de/en/news/AN-2025-

    PS: on Friday 26-9-2025 Apollo team will post the Apollo A6000 roadmap for the next batch(es) including details on timeline and options.

    #retrocomputing #A6000

  10. The new keyboard computer "Apollo A6000" already sold out. But if you want to inform yourself:

    amiga-news.de/en/news/AN-2025-

    PS: on Friday 26-9-2025 Apollo team will post the Apollo A6000 roadmap for the next batch(es) including details on timeline and options.

    #retrocomputing #A6000

  11. #GPUHammer is the first attack to show #Rowhammer bit flips on #GPU memories, specifically on a GDDR6 memory in an #NVIDIA A6000 GPU. Our attacks induce bit flips across all tested DRAM banks, despite in-DRAM defenses like TRR, using user-level #CUDA #code. These bit flips allow a malicious GPU user to tamper with another user’s data on the GPU in shared, time-sliced environments. In a proof-of-concept, we use these bit flips to tamper with a victim’s DNN models and degrade model accuracy from 80% to 0.1%, using a single bit flip. Enabling Error Correction Codes (ECC) can mitigate this risk, but ECC can introduce up to a 10% slowdown for #ML #inference workloads on an #A6000 GPU.

    gpuhammer.com/

  12. #GPUHammer is the first attack to show #Rowhammer bit flips on #GPU memories, specifically on a GDDR6 memory in an #NVIDIA A6000 GPU. Our attacks induce bit flips across all tested DRAM banks, despite in-DRAM defenses like TRR, using user-level #CUDA #code. These bit flips allow a malicious GPU user to tamper with another user’s data on the GPU in shared, time-sliced environments. In a proof-of-concept, we use these bit flips to tamper with a victim’s DNN models and degrade model accuracy from 80% to 0.1%, using a single bit flip. Enabling Error Correction Codes (ECC) can mitigate this risk, but ECC can introduce up to a 10% slowdown for #ML #inference workloads on an #A6000 GPU.

    gpuhammer.com/

  13. #GPUHammer is the first attack to show #Rowhammer bit flips on #GPU memories, specifically on a GDDR6 memory in an #NVIDIA A6000 GPU. Our attacks induce bit flips across all tested DRAM banks, despite in-DRAM defenses like TRR, using user-level #CUDA #code. These bit flips allow a malicious GPU user to tamper with another user’s data on the GPU in shared, time-sliced environments. In a proof-of-concept, we use these bit flips to tamper with a victim’s DNN models and degrade model accuracy from 80% to 0.1%, using a single bit flip. Enabling Error Correction Codes (ECC) can mitigate this risk, but ECC can introduce up to a 10% slowdown for #ML #inference workloads on an #A6000 GPU.

    gpuhammer.com/

  14. #GPUHammer is the first attack to show #Rowhammer bit flips on #GPU memories, specifically on a GDDR6 memory in an #NVIDIA A6000 GPU. Our attacks induce bit flips across all tested DRAM banks, despite in-DRAM defenses like TRR, using user-level #CUDA #code. These bit flips allow a malicious GPU user to tamper with another user’s data on the GPU in shared, time-sliced environments. In a proof-of-concept, we use these bit flips to tamper with a victim’s DNN models and degrade model accuracy from 80% to 0.1%, using a single bit flip. Enabling Error Correction Codes (ECC) can mitigate this risk, but ECC can introduce up to a 10% slowdown for #ML #inference workloads on an #A6000 GPU.

    gpuhammer.com/

  15. #GPUHammer is the first attack to show #Rowhammer bit flips on #GPU memories, specifically on a GDDR6 memory in an #NVIDIA A6000 GPU. Our attacks induce bit flips across all tested DRAM banks, despite in-DRAM defenses like TRR, using user-level #CUDA #code. These bit flips allow a malicious GPU user to tamper with another user’s data on the GPU in shared, time-sliced environments. In a proof-of-concept, we use these bit flips to tamper with a victim’s DNN models and degrade model accuracy from 80% to 0.1%, using a single bit flip. Enabling Error Correction Codes (ECC) can mitigate this risk, but ECC can introduce up to a 10% slowdown for #ML #inference workloads on an #A6000 GPU.

    gpuhammer.com/

  16. Widescreen Wonder: #LasVegasSphere
    54,000 m2 (~3.67 acre) interior LED display (16x16K) and an exterior LED display (‘Exosphere’) consisting out of 1.23 million LED ‘pucks’. Driving all these pixels are around 150 #NVidia RTX #A6000 #GPU, installed in computer systems which are networked using NVidia #BlueField data processing units (#DPU) and NVidia #ConnectX6 NICs (up to 400 Gb/s), with visual content transferred from Sphere Studios in Cali. All this hardware uses 45kW.
    blogs.nvidia.com/blog/sphere-l

  17. Widescreen Wonder: #LasVegasSphere
    54,000 m2 (~3.67 acre) interior LED display (16x16K) and an exterior LED display (‘Exosphere’) consisting out of 1.23 million LED ‘pucks’. Driving all these pixels are around 150 #NVidia RTX #A6000 #GPU, installed in computer systems which are networked using NVidia #BlueField data processing units (#DPU) and NVidia #ConnectX6 NICs (up to 400 Gb/s), with visual content transferred from Sphere Studios in Cali. All this hardware uses 45kW.
    blogs.nvidia.com/blog/sphere-l

  18. Widescreen Wonder:
    54,000 m2 (~3.67 acre) interior LED display (16x16K) and an exterior LED display (‘Exosphere’) consisting out of 1.23 million LED ‘pucks’. Driving all these pixels are around 150 RTX , installed in computer systems which are networked using NVidia data processing units () and NVidia NICs (up to 400 Gb/s), with visual content transferred from Sphere Studios in Cali. All this hardware uses 45kW.
    blogs.nvidia.com/blog/sphere-l

  19. Widescreen Wonder: #LasVegasSphere
    54,000 m2 (~3.67 acre) interior LED display (16x16K) and an exterior LED display (‘Exosphere’) consisting out of 1.23 million LED ‘pucks’. Driving all these pixels are around 150 #NVidia RTX #A6000 #GPU, installed in computer systems which are networked using NVidia #BlueField data processing units (#DPU) and NVidia #ConnectX6 NICs (up to 400 Gb/s), with visual content transferred from Sphere Studios in Cali. All this hardware uses 45kW.
    blogs.nvidia.com/blog/sphere-l

  20. Widescreen Wonder: #LasVegasSphere
    54,000 m2 (~3.67 acre) interior LED display (16x16K) and an exterior LED display (‘Exosphere’) consisting out of 1.23 million LED ‘pucks’. Driving all these pixels are around 150 #NVidia RTX #A6000 #GPU, installed in computer systems which are networked using NVidia #BlueField data processing units (#DPU) and NVidia #ConnectX6 NICs (up to 400 Gb/s), with visual content transferred from Sphere Studios in Cali. All this hardware uses 45kW.
    blogs.nvidia.com/blog/sphere-l

  21. May - My favourite month in my favourite season. Carpets of Bluebells @ Middleton Woods, #Ilkley. Taken with #Sony #a6000

    #woodland #bluebells #yorkshire #europe