Unboxing Tesla V100 (M) - Developer Preview after winning Deep Berlin NVIDIA
GIGABYTE Launches Two 4U NVIDIA Tesla GPU Servers: High Density for Deep Learning
GIGABYTE has announced a pair of new GPU-focused servers, rolling out the 8x SXM2 GPU G481-S80 and the 10x PCIe GPU G481-HA0, offering data centers some of the highest GPU density in this form factor available on the market. The new servers feature dual Intel Xeon Scalable processors with up to 28 core CPUs and the highest CPU TDP requirement of 205W for each socket. With deep learning-based systems becoming more visible in our daily lives (think image recognition, autonomous vehicles, and medical research), data centers need high-density machines to serve their client needs as well as save precious real estate.
Both server chassis are in a 4U form factor supporting the latest
with up to 28 cores per CPU and the ability to handle the 205W TDP supporting Intel’s Omni-Path connection technology to reduce CPU to network latency. The G481 series uses space optimization and hot-swappable dual fan walls for keeping the unit cool. The platform uses 6-channel RDIMM/LRDIMM DDR4 supporting up to 2666 Mhz and 1.5TB (CPU dependent) through 12 DIMMs per socket.
The G481-S80 is able to accommodate up to eight SXM2 form factor GPUs from the NVIDIA Volta V100 or Pascal P100 lines, with support for NVLink GPU to GPU interconnection which yields higher bandwidth, more links, with GIGABYTE saying these systems are designed to offer the highest GPU density available in this form factor available on the market. Pascal P100 Price , with GIGABYTE saying these systems are designed to offer the highest GPU density available in this form factor available on the market.
GPUs aside, the G481-S80 has four PCIe expansion slots to support advanced network connectivity such as InfiniBand for RDMA (Remote Direct Memory Access) for high-throughput, low latency GPU to network connectivity for each GPU pair. The HA0 adds the ability to install additional networking connection options in one of the PCIe expansion slots instead of a GPU. For example, a combination of 8x GPUs and two network cards such as InfiniBand or 10/25/50/100 Gb Ethernet for increased flexibility.
For storage, the G481-S80 has 10 2.5-inch hot-swap drive bays in the front able to support four NVMe drives through U.2 connection and six drives through SATA/SAS. The HA0 takes that further and offers 10 2.5-inch hot-swap drive bays able to house up to eight 2.5-inch NVMe drives and two 2.5-inch SATA/SAS drives. Below the 2.5-inch storage drive area are an additional 12 3.5-inch SATA/SAS hot swap drive bays. Both models also have a PCIe expansion slot in front above the storage area to attach a RAID card with a battery backup unit slot as well.
Powering these units are 80 Plus Platinum 2.2Kw power supply units. The S80 uses four, three for main system power and one back up for N+N redundancy while the HA0 uses three units for an N+1 configuration.
Neither pricing nor availability was mentioned; however, their product pages are on the website so we do expect to see these soon.
Dual Intel Xeon Scalable Processors (up to 205W TDP per socket)
Complete specifications for each server can be found at their webpage (
GIGABYTE's G190-G30: A 1U Server with four Volta and NVLink
GIGABYTE Server Launches Three New Density-Focused Servers: Skylake-SP, Choice of NIC
Pascal P100 Price
More EPYC Servers: Dell Launches 1P and 2P PowerEdge for HPC and Virtualization
Sizing UP Servers: Intel's Skylake-SP Xeon versus AMD's EPYC 7000 - The Sever CPU Battle of the Decade?
Intel to Update Xeon D in Early 2018, with Skylake-SP Cores
Intel Launches Xeon-W CPUs for Workstations: Skylake-SP & ECC for LGA2066
...how many sol/s in equihash? what's the sols/watt?
How does this handle PCIe lane switching? The HA0 has 10x x16 slots, but 2x sockets will only get you 96 lanes total. Seems like they'd be overcommitting GPUs to a certain extent.
They could have a PLX chip to increase the PCIe lane count available
It wouldn't increase lane count, only enable multiplexing to the existing 96 lanes right? So there would still be contention if all the GPUs were maxing out their x16's.
It wouldn't increase lane count to the CPU, no. I do however think it increases bandwidth *between* the GPUs, depending on their locations relative to the switch.
Pascal P100 Price
AMD's 7nm CPUs & GPUs To Be Fabbed by TSMC, on Track for 2018 - 2019
AMD: Jim Anderson Out, Saeid Moshkelani In as “Client Compute Group” General Manager
AMD Slashes Prices of First-Gen Ryzen Threadripper CPUs: Starting at $300
AMD Wins Patent Infringement Case Against Vizio & Others; Vizio Ordered To Cease Some TV Imports
Lite-On Demos Its First ‘Ruler’ EDSFF SSDs: CNEX Labs Controller, Up to 80 TB Capacity
Logitech Launches G Pro Wireless Gaming Mouse with 16,000 DPI Sensor
Turing Custom: A Quick Look At Upcoming GeForce RTX 2080 Ti & 2080 Cards
Dell Adds Per-Key LED Lighting to Alienware 15 and Alienware 17 Laptops
Alienware Installs NVIDIA’s GeForce RTX Cards In Aurora and Area-51 Desktops
Dell Launches Gaming 24 and Gaming 27 Displays: 1 ms Response, 144/155 Hz Refresh
it has develop… https://t.co/N82dL9swYm Pascal P100 Price , it has develop… https://t.co/N82dL9swYm
@anexanhume Yes. That is not a path GloFo wants to go down. Unless someone wants to do some jail time.
@gglawits @anandtech We do. Sometimes that editor (i.e. me) is in a hurry, as there were 3 different AMD announceme… https://t.co/XgcGG7bfPn
@dylan522p True. But those aren't high-end. Small chips have their own challenges in comparisons, including the siz… https://t.co/xL96d8nJes
@Krewell @jwangARK I always felt that a new fab in the Middle East was a bit too optimistic. But yeah, that dream i… https://t.co/6oXr5YRLRl
@carlosyusv You don't consider Intel bleeding edge? Put aside the fact that the name of the process means nothing
@eddychik @Techmeme NY fab at Malta stays at 14/12. They might sell the EUV machines, but that's it
@Mobile_Dom Back in Feb, one was 99 percent installed, the second was just in bits arriving from the factory. Chanc… https://t.co/36AgbzHrfz
@Mobile_Dom Yes. But they could just sell the EUV machines too
@Taiki__San @david_schor Nonsense reporting; actual quote: "Apple is of a view that it will no longer use the Group… https://t.co/TYXueeoqH0
@Taiki__San @david_schor Royalties on new designs, meaning >=A12. Thought that was understood.
Sometimes I wish I would review desktop parts instead of mobile. Ian automates everything; I can't automate anything.
@david_schor Good analysis. Obviously I base my assumption that the A12 is actually an new GPU based on the fact th… https://t.co/3oAf3b79f9
A12 GPU figures do look promising. Wonder what their custom GPU arch will bring.
@Bindibadgi Intel has already made public the perf loss in the SYSmark real world benchmarks for the L1TF patches.… https://t.co/E6hyvnlAz7
RT @Laughing_Man: @ganeshts Agreed, but I would also require that any fixed charger like this must be USB-IF certified and carry the Certif…
@FanlessTech I see many retailers here in the US giving prominent floor space to in-wall outlets with Type-A ports,… https://t.co/f3GgYGMmgq
For an in-wall USB-C charging outlet, it would be nice to have support the higher wattage power-delivery specificat… https://t.co/jpBMeLk6oe
@FPiednoel I believe a USB dongle with the same functionality and Windows support has been available for a number o… https://t.co/TbnMVo8lav
0 Reviews:
Post Your Review