Samsung Introduces HBM2E Memory, Packing a 33% Bandwidth Boost

Samsung Introduces HBM2E Memory, Packing a 33% Bandwidth Boost

Samsung Introduces HBM2E Memory, Packing a 33% Bandwidth Boost

At Nvidia’s GPU Technology Conference, GTC, Samsung has revealed their latest HBM memory innovation, showcasing HBM2E “Flashbolt” memory, which offers a 33% increase in speed over the company’s older HBM2 chips. 

When compared to Samsung’s already fast Aquabolt HBM2 offerings, which can deliver u to 2.4Gbps speeds, Flashbolt can offer 3.2Gbps transfer rates, a 33% increase over what was previously possible. 

Each of the die used in Samsung’s Flashpoint HBM2 memory is 16Gb in size, which when stacked create 16GB memory chips, each of which packs 410GB/s of memory bandwidth. For context, AMD’s Radeon RX Vega 56 offers 410GB/s of memory bandwidth over two HBM2 memory chips. Yes, Samsung’s Flashbolt HBM2 memory offers a 2x boost in speed over the memory used in the RX Vega 56. 

Below is a comment from Samsung’s Jinman Han, the company’s senior vice president of Memory Product Planning and Application Engineering Team at Samsung Electronics.

      Flashbolt’s industry-leading performance will enable enhanced solutions for next-generation data centers, artificial intelligence, machine learning, and graphics applications,

We will continue to expand our premium DRAM offering, and improve our ‘high-performance, high capacity, and low power’ memory segment to meet market demand

Samsung Introduces HBM2E Memory, Packing a 33% Bandwidth Boost 

At this time it is unknown when Samsung’s Flashbolt HBM2 memory will become readily available, but at a minimum, these high-speed HBM2E chips will help inject new life into the HBM memory standard. If this memory was used to build AMD’s Radeon VII, the graphics card would offer 1,640GB/s of memory bandwidth, which would be a staggering increase over the 1,024GB/s that the card currently offers. 

You can join the discussion on Samsung’s HBM2E Flashbolt memory on the OC3D Forums.Â