Samsung Boosts 8GB HBM2 Production To Fuel Next Gen GPUs From AMD And NVIDIA
Samsung is currently the only memory chip maker that is producing 8-gigabyte (GB) HBM2 (second generation high bandwidth memory) chips. In order to keep up with demand from a growing field of customers and applications, Samsung is ramping up production of its 8GB HBM2 chips, which will find their way into systems tasked with artificial intelligence chores, HPC (high performance computing), advanced graphics, network systems, and enterprise servers.
Both AMD and NVIDIA use HBM2 chips in some of their high-end graphics card solutions as well. With NVIDIA, HBM2 can be found on its Quadro GP100 card for professionals, which wields 16GB of HBM2. And for AMD, its recently announced Radeon RX Vega Frontier Edition is also equipped with 16GB of HBM2.
"By increasing production of the industry’s only 8GB HBM2 solution now available, we are aiming to ensure that global IT system manufacturers have sufficient supply for timely development of new and upgraded systems," said Jaesoo Han, executive vice president, Memory Sales & Marketing team at Samsung Electronics."We will continue to deliver more advanced HBM2 line-ups, while closely cooperating with our global IT customers."
Samsung's 8GB HBM2 chips feature eight 8-gigabit (Gb) HBM2 dies and a buffer die at the bottom of the stack. These are all vertically connected by TSVs (Through Silicon Via), including spares, which Samsung says ensures high performance by enabling data paths to be switched to different TSVs when a delay in data transmission occurs. Samsung also has safeguards in place to prevent overheating.
HBM2 was introduced a little over a year ago. From a performance standpoint, it has a bandwidth of 256GB/s, which is more than eight times that of 32GB/s GDDR5 DRAM. There is also a need for more capacity, which is where Samsung's 8GB HBM2 chips come into play. Samsung reckons its volume production of 8GB HBM2 will cover more than half of its total HBM2 output by the first half of next year.
Both AMD and NVIDIA use HBM2 chips in some of their high-end graphics card solutions as well. With NVIDIA, HBM2 can be found on its Quadro GP100 card for professionals, which wields 16GB of HBM2. And for AMD, its recently announced Radeon RX Vega Frontier Edition is also equipped with 16GB of HBM2.
"By increasing production of the industry’s only 8GB HBM2 solution now available, we are aiming to ensure that global IT system manufacturers have sufficient supply for timely development of new and upgraded systems," said Jaesoo Han, executive vice president, Memory Sales & Marketing team at Samsung Electronics."We will continue to deliver more advanced HBM2 line-ups, while closely cooperating with our global IT customers."
Samsung's 8GB HBM2 chips feature eight 8-gigabit (Gb) HBM2 dies and a buffer die at the bottom of the stack. These are all vertically connected by TSVs (Through Silicon Via), including spares, which Samsung says ensures high performance by enabling data paths to be switched to different TSVs when a delay in data transmission occurs. Samsung also has safeguards in place to prevent overheating.
HBM2 was introduced a little over a year ago. From a performance standpoint, it has a bandwidth of 256GB/s, which is more than eight times that of 32GB/s GDDR5 DRAM. There is also a need for more capacity, which is where Samsung's 8GB HBM2 chips come into play. Samsung reckons its volume production of 8GB HBM2 will cover more than half of its total HBM2 output by the first half of next year.
