#computeexpresslink — Public Fediverse posts

Nvidia Co-Founder: “Without Samsung and SK, There Would Be No AI Revolution”… Memory Evolves from ‘Storage’ to ‘Compute’

Chris Malachowsky, co-founder of Nvidia and known as the ‘father of the GPU,’ lavished praise on South Korea’s…
#EuropeSays #Korea #KR #SamsungElectronics #basedie #ChrisMalachowsky #ComputeExpressLink(CXL) #high-bandwidthmemory(HBM) #HotChips #NVIDIA #Processing-in-Memory(PIM) #Samsung #SKhynix #US-KoreaConference(UKC)
https://www.europesays.com/korea/113632/

Meta measures 43.7% of its servers as memory-capacity bound. They run out of RAM before they run out of cores, network, or storage.

CXL is the standard meant to fix that, and it is further along than most coverage suggests in one direction and further behind in another. Expansion runs in production today. Pooling works on real hardware.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure #tech

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Most CXL coverage collapses three separate things into one, which is why the technology reads as both imminent and permanently delayed.

Expansion gives a single host extra CXL-attached memory as a second tier. It is in production at hyperscale — 768 GB of local DDR5-6400 alongside 256 GB of reclaimed DDR4-2400 per node, at 0.13 the cost per gigabyte of local DRAM, because those DIMMs were already bought.

Pooling gives several hosts exclusive slices of a shared device, and does not require a switch: a multi-port device pools across whatever hosts plug into it. NSDI '26 measurements put multi-port paths at 260–300 ns against 490–600 ns switched.

Sharing — many hosts on one region, coherent in hardware — is defined in CXL 3.0 and absent from shipping devices.

The economics are the open question. Google researchers put switched break-even around 24 nodes. The same NSDI work finds sparse multi-port topologies save 3% to 5.4%. Topology decides.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Disaggregation #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Most CXL coverage collapses three separate things into one, which is why the technology reads as both imminent and permanently delayed.

Expansion gives a single host extra CXL-attached memory as a second tier. It is in production at hyperscale — 768 GB of local DDR5-6400 alongside 256 GB of reclaimed DDR4-2400 per node, at 0.13 the cost per gigabyte of local DRAM, because those DIMMs were already bought.

Pooling gives several hosts exclusive slices of a shared device, and does not require a switch: a multi-port device pools across whatever hosts plug into it. NSDI '26 measurements put multi-port paths at 260–300 ns against 490–600 ns switched.

Sharing — many hosts on one region, coherent in hardware — is defined in CXL 3.0 and absent from shipping devices.

The economics are the open question. Google researchers put switched break-even around 24 nodes. The same NSDI work finds sparse multi-port topologies save 3% to 5.4%. Topology decides.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Disaggregation #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Meta measures 43.7% of its servers as memory-capacity bound. They run out of RAM before they run out of cores, network, or storage.

CXL is the standard meant to fix that, and it is further along than most coverage suggests in one direction and further behind in another. Expansion runs in production today. Pooling works on real hardware.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure #tech

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Meta measures 43.7% of its servers as memory-capacity bound. They run out of RAM before they run out of cores, network, or storage.

CXL is the standard meant to fix that, and it is further along than most coverage suggests in one direction and further behind in another. Expansion runs in production today. Pooling works on real hardware.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure #tech

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Meta measures 43.7% of its servers as memory-capacity bound. They run out of RAM before they run out of cores, network, or storage.

CXL is the standard meant to fix that, and it is further along than most coverage suggests in one direction and further behind in another. Expansion runs in production today. Pooling works on real hardware.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure #tech

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Meta measures 43.7% of its servers as memory-capacity bound. They run out of RAM before they run out of cores, network, or storage.

CXL is the standard meant to fix that, and it is further along than most coverage suggests in one direction and further behind in another. Expansion runs in production today. Pooling works on real hardware.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure #tech

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Meta measures 43.7% of its servers as memory-capacity bound. They run out of RAM before they run out of cores, network, or storage.

CXL is the standard meant to fix that, and it is further along than most coverage suggests in one direction and further behind in another. Expansion runs in production today. Pooling works on real hardware.

#CXL #ComputeExpressLink #MemoryPooling #ServerMemory #DataCenter #Interconnect #DRAM #DDR4 #DDR5 #AIInfrastructure #tech

https://www.buysellram.com/blog/cxl-memory-explained-can-servers-finally-share-ram/

Samsung, SK Hynix advance new memory layer to tackle AI scaling limits

Samsung Electronics and SK hynix pushed to commercialize a new class of memory as artificial intelligence outgrew high-bandwidth…
#EuropeSays #Korea #KR #SKHynix #AImemory #ComputeExpressLink #CXL #DRAM #high-bandwidthmemory #memorycapacity #memorymanagementtools #Samsung #SamsungElectronics #SK #SKhynix
https://www.europesays.com/korea/92218/