News Posts matching "SoC"

Return to Keyword Browsing

AMD Doubles L3 Cache Per CCX with Zen 2 "Rome"

A SiSoft SANDRA results database entry for a 2P AMD "Rome" EPYC machine sheds light on the lower cache hierarchy. Each 64-core EPYC "Rome" processor is made up of eight 7 nm 8-core "Zen 2" CPU chiplets, which converge at a 14 nm I/O controller die, which handles memory and PCIe connectivity of the processor. The result mentions cache hierarchy, with 512 KB dedicated L2 cache per core, and "16 x 16 MB L3." Like CPU-Z, SANDRA has the ability to see L3 cache by arrangement. For the Ryzen 7 2700X, it reads the L3 cache as "2 x 8 MB L3," corresponding to the per-CCX L3 cache amount of 8 MB.

For each 64-core "Rome" processor, there are a total of 8 chiplets. With SANDRA detecting "16 x 16 MB L3" for 64-core "Rome," it becomes highly likely that each of the 8-core chiplets features two 16 MB L3 cache slices, and that its 8 cores are split into two quad-core CCX units with 16 MB L3 cache, each. This doubling in L3 cache per CCX could help the processors cushion data transfers between the chiplet and the I/O die better. This becomes particularly important since the I/O die controls memory with its monolithic 8-channel DDR4 memory controller.

GIGABYTE Intros B450M Gaming Socket AM4 Motherboard

GIGABYTE today introduced the B450M Gaming, a low-cost socket AM4 motherboard based on AMD B450 chipset, designed to be priced under $100. Built in the compact micro-ATX form-factor (205 mm x 244 mm), the board draws power from a combination of 24-pin ATX and 8-pin EPS, and uses a 4+3 phase VRM to power the AM4 SoC. A large VRM heatsink dominates the main MOSFET block, which also covers up a portion of the rear I/O area. The AM4 socket is wired to two DDR4 DIMM slots, supporting up to 32 GB of dual-channel memory, the board's sole M.2-2280 slot, and the PCI-Express 3.0 x16 slot with metal reinforcement. Two PCI-Express 2.0 x1 slots wired to the B450 chipset make for the rest of the expansion area.

Storage connectivity includes one M.2-2280 slot with PCI-Express 3.0 x4 and SATA 6 Gbps wiring, and four SATA 6 Gbps ports. USB connectivity includes four USB 3.1 gen 1 type-A ports on the rear panel, and two USB 3.1 gen 1 ports via header. Networking, interestingly, is a 1 GbE interface driven by Realtek Dragon 8118AS controller, which was originally launched as Realtek's competitor to the i219-V (comes with various performance enhancements). Audio is a basic 6-channel fare driven by Realtek ALC887, somewhat improved with ground-layer isolation and electrolytic capacitors.

The Subor Z+ Console/PC Hybrid with AMD Fenghuang SoC Benchmarked

Last August Chinese pC maker Zhongshan Subor announced a mysterious new console/PC hybrid called Subor Z+ with an interesting spec sheet. The most intriguing part of that machine was none other than a new AMD SoC custom with the code name 'Fenghuang/FireFlight'. Based on the Zen architecture instead of the Jaguar used in consoles such as the Xbox One X or PS4 Pro, this SoC has a CPU with 4 cores and 8 threads at 3.0 GHz a Vega-based GPU with 24 CUs at 1300 MHz, 8 GB GDDR5, 128 GB SSD and 1 TB HDD.

The preliminary tests that we could see thanks to DigitalFoundry have now been completed with a new series of benchmarks from a Chinese YouTube user in which we can see the Subor Z+ running different Windows games at more than 60 fps in some of them. The graphics power sits between a RX 570 and a GTX 1060 according to the content producer, and among the results we have different scores showing how far this can go. For example, Fire Strike Extreme (486 points), Time Spy (3288), Tomb Raider (74.81 fps without clarifying graphic config), Cinebench (110/581) or PUBG, which was running at around 50-55 fps at 1080p and with low level of detail.

Intel to Outsource Entry-level CPU and Chipset Fabrication to TSMC

Intel is facing a manufacturing crisis, in which demand has far outstripped supply, and the company is firing up all its silicon fabrication facilities to manufacture 14 nm products, mainly processors under the Core and Xeon brands. We've been hearing reports since early-September of Intel seeking out third-party foundries such as TSMC to manufacture its chipsets. We now get confirmation that TSMC will also manufacture entry-level Intel processors under brands such as Atom, Celeron, and Pentium Silver SoCs, leaving the company's socketed processors to Intel's fabs. DigiTimes does not name the third-party foundry as TSMC, but mentions that the only company that meets Intel's requirements at the moment is TSMC.

Intel Acquires NetSpeed Systems for Chip Design and Interconnect Fabric IP

Intel today announced the acquisition of NetSpeed Systems, a San Jose, California-based provider of system-on-chip (SoC) design tools and interconnect fabric intellectual property (IP). Deal terms were not disclosed. NetSpeed's highly configurable and synthesizable offerings will help Intel more quickly and cost-effectively design, develop and test new SoCs with an ever-increasing set of IP. The NetSpeed team is joining Intel's Silicon Engineering Group (SEG) led by Jim Keller. NetSpeed co-founder and CEO, Sundari Mitra, will continue to lead her team as an Intel vice president reporting to Keller.
Intel is designing more products with more specialized features than ever before, which is incredibly exciting for Intel architects and for our customers. The challenge is synthesizing a broader set of IP blocks for optimal performance while reining in design time and cost. NetSpeed's proven network-on-chip technology addresses this challenge, and we're excited to now have their IP and expertise in-house.

Jim Keller, senior vice president and general manager of the Silicon Engineering Group at Intel

UL Benchmarks Kicks Huawei Devices from its Database over Cheating

UL Benchmarks de-listed several popular Huawei devices from its database over proof of cheating in its benchmarks. Over the month, it was found that several of Huawei's devices, such as P20 Pro, Nova 3, and Play; overclocked their SoCs while ignoring all power and thermal limits, to achieve high benchmark scores, when it detected that a popular benchmark such as 3DMark, was being run. To bust this, UL Benchmarks tested the three devices with "cloaked" benchmarks, or "private benchmarks" as they call it. These apps are identical in almost every way to 3DMark, but lack the identification or branding that lets Huawei devices know when to overclock themselves to cheat the test.

The results were startling. When the devices have no clue that a popular benchmark is being run (or if has no way of telling that 3DMark is being run), it chugs along at its "normal" speed, which is 35% to 36% lower. The rules that bind device manufacturers from advertising UL's 3DMark scores explicitly state that the device must not detect the app and optimize its hardware on the fly to ace the test. Huawei responded to UL by stating that it will unlock a new "performance mode" to users that lets them elevate their SoCs to the same high clocks for any application.

Intel "Whiskey Lake-U" Core Processor Lineup Detailed

Intel is giving final touches to its 9th generation Core "Whiskey Lake-U" processors for Ultrabooks and other ULV platforms. Successors to 8th Gen "Kaby Lake Refresh" chips, these 15-Watt SoCs may not pack a newer microarchitecture in terms of IPC increases, but Intel is building them on the latest iteration of its 14 nm node, along with tweaks made to their Turbo Boost algorithm, which combined with higher boost clocks, should offer better performance than the previous generation.

The lineup begins with the Core i3-8145U, successor to the i3-8130U. This 2-core/4-thread chip is has a lower nominal clock at 2.10 GHz (vs. 2.20 GHz of its predecessor), but significantly higher boost clocks of 3.90 GHz (vs. 3.40 GHz of the i3-8130U). The Core i5-8265U and top-end i7-8565U are both 4-core/8-thread chips with a nominal clocks of 1.60 GHz and 1.80 GHz, respectively. The i5-8265U has a boost clock of 4.10 GHz and 6 MB of L3 cache; while the i7-8565U tops that with 4.70 GHz boost clocks, and 8 MB of L3 cache. All three chips have 15W TDP, configurable to 25W by applying the "high performance" power scheme.

Intel "Crimson Canyon" NUCs with Discrete GPUs Up for Pre-order

One of the first Intel NUC (next unit of computing) mini PCs to feature completely discrete GPUs (and not MCMs of CPUs and GPUs), the "Crimson Canyon" NUC8i3CYSM and NUC8i3CYSN, are up for pre-order. The former is priced at USD $529, while the latter goes for $574. The two combine Intel's 10 nm Core i3-8121U "Cannon Lake" SoC with AMD Radeon 540 discrete GPU. Unlike the "Hades Canyon" NUC, which features an MCM with a powerful AMD Radeon Vega M GPU die and a quad-core "Kaby Lake" CPU die; the "Crimson Canyon" features its processor and GPU on separate packages. The Radeon 540 packs 512 stream processors, 32 TMUs, and 16 ROPs; with 2 GB of GDDR5 memory.

All that's differentiating the NUC8i3CYSM from the NUC8i3CYSN is memory. You get 4 GB of LPDDR4 memory with the former, and 8 GB of it with the latter. Both units come with a 2.5-inch 1 TB HDD pre-installed. You also get an M.2-2280 slot with PCIe 3.0 x4 wiring, and support for Optane caching. Intel Wireless-AC 9560 WLAN card handles wireless networking, while an i219-V handles wired. Connectivity includes four USB 3.0 type-A ports, one of which has high current; an SDXC card reader, CIR, two HDMI 2.0 outputs, and 7.1-channel HD audio. The NUC has certainly grown in size over the years. This one measures 117 mm x 112 mm x 52 mm (WxDxH). An external 90W power-brick adds to the bulk.

Samsung Foundry and Arm Expand Collaboration to Drive High-Performance Computing Solutions

Samsung Electronics, a world leader in advanced semiconductor technology, today announced that its strategic foundry collaboration with Arm will be expanded to 7/5-nanometer (nm) FinFET process technology to remain a step ahead in the era of high-performance computing. Based on Samsung Foundry's 7LPP (7nm Low Power Plus) and 5LPE (5nm Low Power Early) process technologies, the Arm Artisan physical IP platform will enable 3GHz+ computing performance for Arm's Cortex -A76 processor.

Samsung's 7LPP process technology will be ready for its initial production in the second half of 2018. The first extreme ultra violet (EUV) lithography process technology, and its key IPs, are in development and expected to be completed by the first half of 2019. Samsung's 5LPE technology will allow greater area scaling and ultra-low power benefits due to the latest innovations in 7LPP process technology.

ASUS Intros Tinker Fanless Aluminum Case

ASUS rolled out the Tinker Fanless Aluminium case, a custom-design case for the Tinker Board and Tinker Board S hobby-kits by ASUS that rival Raspberry Pi. The case is built from a block of aluminium with brushed-metal finish; which opens from one side (rear), held together by a single thumb-screw. It has cutouts for all of the Tinker Board's ports and connectors - four USB, an HDMI output, Ethernet, DC-in, two card slots, and slots for the optional WLAN module. The case has enough room to let you mount the SoC heatsink that's included with Tinker Boards. The case measures 90 mm x 67 mm x 36 mm (WxDxH).

Compulab MintBox mini 2 Up for Pre-order

Compulab put up the MintBox mini 2, a compact, passively cooled desktop powered by Linux Mint, up for pre-order at US $299 for the base variant with 4 GB RAM and 64 GB storage; and $349 for 8 GB RAM and 120 GB storage (better value). The two can be ordered from Compulab's Amazon web-store, and will start shipping from August. The two feature the latest stable version of Linux Mint 19 "Tara," and 5 percent of your monies spent buying these are donated to the Linux Mint project.

The super-compact MintBox mini 2 is powered by Intel Celeron J3455 SoCs, mated to either 4 GB or 8 GB of RAM; and either 64 GB or 120 GB of SSD storage. You get two each of USB 3.0 and USB 2.0 ports, a microSDXC slot, two 1 GbE interfaces, 802.11 b/g/n + Bluetooth 4.1 WLAN, serial COM (through a unique connector, with an optional dongle that converts it to RS232), and display outputs that include HDMI and mini-DisplayPort.

AMD "Vega" Outsells "Previous Generation" by Over 10 Times

At its Computex presser, leading up to its 7 nm Radeon Vega series unveil, AMD touched upon the massive proliferation of the Vega graphics architecture, which is found not only in discrete GPUs, but also APUs, and semi-custom SoCs of the latest generation 4K-capable game consoles. One such slide that created quite some flutter reads that "Vega" shipments are over 10 times greater than those of the "previous generation."

Normally you'd assume the previous-generation of "Vega" to be "Polaris," since we're talking about the architecture, and not an implementation of it (eg: "Vega 10" or "Raven Ridge," etc.). AMD later, at its post event round-table, clarified that it was referring to "Fiji," or the chip that went into building the Radeon R9 Fury X, R9 Nano, etc., and comparing its sales with that of products based on the "Vega 10" silicon. Growth in shipments of "Vega" based graphics cards is triggered by the crypto-mining industry, and for all intents and purposes, AMD considers the "Vega 10" silicon to be a commercial success.

Samsung to Power Future High-Performance Computing and Connected Devices

Samsung Electronics, a world leader in advanced semiconductor technology solutions, today unveiled a series of new silicon innovations at the heart of future high-performance computing and connected devices. With comprehensive process technology roadmap updates down to 3-nanometer (nm) at the annual 'Samsung Foundry Forum (SFF) 2018 USA', Samsung Foundry is focused on providing customers with the tools necessary to design and manufacture powerful, yet energy-efficient system-on-chips (SoC) for a wide range of applications.

"The trend toward a smarter, connected world has the industry demanding more from silicon providers," said Charlie Bae, executive vice president and head of the Foundry Sales & Marketing Team at Samsung Electronics. "To meet that demand, Samsung Foundry is powering innovation at the silicon level that will ultimately give people access to data, analysis, and insight in new and previously unthought-of ways to make human lives better. It is imperative for us to accomplish the first-time silicon success for our customers' next-generation chip designs."

TSMC to Bring 3D Stacked Wafers to Complex Silicon Designs, Such as GPUs

TSMC is close to adapt 3D stacked silicon wafers to complex silicon designs, such as graphics processors, using its new proprietary Wafer-on-Wafer (WoW) Advanced Packaging technology, which will be introduced with its 7 nm+ and 5 nm nodes. 3D stacked silicon fabrication is currently only implemented on "less complex" silicon designs, such as NAND flash, which don't run anywhere near as hot as complex designs ASIC designs, such as GPUs or CPUs. In its current form, TSMC achieved 2-layer stacks, in which two silicon layers that are "mirror images" of each other (for perfect alignment), sandwich bonding layers, through which pins for the upper layer pass through.

The bonding of the two layers is where the bulk of TSMC's innovations and "secret sauces" lie. For 3D NAND flash, multiple pancaked dies are wired out through their edges. You don't need as many pins to talk to a NAND flash die, as say a GPU die. For complex dies, designers have to pass thousands of pins through the "bottom layer," the connecting substrate, and eventually to the "top layer." The bottom layer hence is bumped out on both ends, one side interfacing with the package substrate for both dies, and the top side serving as a sort of substrate for the top die. This innovation is what TSMC calls "thru-silicon-vias" or TSVs.

MSI Intros Cubi N 8 GL Series Mini-PCs with Intel "Gemini Lake" SoCs

MSI introduced the Cubi N 8 GL line of compact mini-PCs powered by Intel "Gemini Lake" Celeron and Pentium Silver SoCs. These include variants with Celeron J4005 and Pentium Silver J5005. Despite "Gemini Lake" chips featuring dual-channel memory support, the Cubi N 8 GL only features one DDR4 SO-DIMM slot, which supports up to 8 GB of DDR4-2400 memory. Storage options include either an M.2-2280 slot with both SATA 6 Gbps and PCIe 2.0 x2 wiring, or a 2.5-inch drive bay with SATA 6 Gbps. An interesting inclusion here is the Intel Dual Band Wireless-AC 9461 WLAN card, which gives you 802.11ac (up to 433 Mbps), but Bluetooth 5.0. Other connectivity includes four USB 3.0 ports, HDMI 2.0 and D-Sub display outputs, and gigabit Ethernet. The company didn't reveal pricing.

Intel Could Develop its own big.LITTLE x86 Adaptation

big.LITTLE is an innovation by ARM, which seeks to minimize power-draw on mobile devices. It is a sort of heterogeneous multi-core CPU design, in which a few "big" high-performance CPU cores work alongside a few extremely low-power "little" CPU cores. The idea here is that the low-power cores consume much lesser power at max load, than the high-performance cores at their minimum power-state, so the high-performance cores can be power-gated when the system doesn't need them (i.e. most of the time).

Intel finds itself with two distinct x86 implementations at any given time. It has low-power CPU micro-architectures such as "Silvermont," "Goldmont," and "Goldmont Plus," etc., implemented on low-power product lines such as the Pentium Silver series; and it has high-performance micro-architectures, such as "Haswell," "Skylake," and "Coffee Lake." The company wants to take a swing at its own heterogeneous multi-core CPU, according to tech stock analyst Ashraf Eassa, with the Motley Fool.

Apple to End the x86 Mac Era in 2020

One of the biggest tech stories of the 2000s was Apple's transition from the PowerPC machine architecture to Intel x86, which brought the Mac closer to being the PC it so loathed. The transition wasn't smooth, as besides the operating system, practically every third-party software developer (eg: Adobe), had to rewrite their software for the new architecture, with new APIs, and new runtime environments. Apple could be bringing about a similar change before the turn of the decade.

Apple already builds its own application processors for iOS devices, and some of the newer chips such as the A11 Bionic and A10 Fusion have already reached the performance levels of entry-level x86 desktop processors. It's only a matter of time before Apple can build its own SoCs for Macs (that's not just iMac desktops, but also Mac Pro workstations, MacBook, MacBook Air, and MacBook Pro). That timeline is expected to be around 2020. Since these chips are based on the ARM machine architecture, they will mandate a major transformation of the entire software ecosystem Apple built over the past decade and a half. Intel shares dropped by as much as 9.2 at the first reports of this move.

Intel's "Bitcoin Mining Hardware Accelerator" Patent Filling Published

A filed patent by Intel has shed some light on the company's idea to somewhere, along the fuzzy lines of the future, introduce a Bitcoin mining hardware "accelerator" to the market. The application itself, for a "Bitcoin Mining Hardware Accelerator With Optimized Message Digest and Message Scheduler Datapath" was originally submitted in September 2016, so it's not exactly a novel idea. However, the fact that it has just now been published doesn't really mean there hasn't been work behind closed doors at Intel towards development of working silicon of this technology.

In the filing, it appears it's Intel's intent to create a chip that could augment the existing Bitcoin mining process by increasing energy efficiency. As they themselves put it, "Because the software and hardware utilized in Bitcoin mining uses brute force to repeatedly and endlessly perform SHA-256 functions, the process of Bitcoin mining can be very power-intensive and utilize large amounts of hardware space. The embodiments described herein optimize Bitcoin mining operations by reducing the space utilized and power consumed by Bitcoin mining hardware."

GIGABYTE Intros Brix S Powered by Pentium Silver J5005 SoC

GIGABYTE today rolled out a variant of its Brix S mini-PC barebone powered by Pentium Silver J5005 SoC (model: GB-BLPD-5005). This chip packs a quad-core "Goldmont Plus" CPU, and faster UHD Graphics 605 iGPU than the one which Celeron J4005 comes with. You add your own DDR4 SO-DIMM memory (up to 8 GB of dual-channel memory over two slots); and storage. Storage options include an M.2-2280 slot with PCIe gen 2.0 x2 wiring, and a 2.5-inch drive bay with SATA 6 Gbps interface (up to 9.5 mm-thick drives supported).

An included Intel Dual Band Wireless-AC 3168 card sitting in its own M.2 slot (other than the vacant M.2-2280 slot) provides dual-band 802.11 ac and Bluetooth 4.2. Wired networking is care of a Realtek RTL8111HS controller, putting out a GbE interface. The Realtek ALC255 HD audio codec puts out stereo audio with around 89 dBA SNR. USB connectivity includes four USB 3.0 ports (two on the rear panel, two up front, including a type-C port). Display outputs include one each of mini-DisplayPort 1.2a and HDMI 2.0a. Measuring 46.8 mm x 112.6 mm x 119.4 mm (HxWxD), it supports VESA mounting. The company didn't reveal pricing.

Xilinx Unveils Their Revolutionary Adaptive Compute Acceleration Platform

Xilinx, Inc., the leader in adaptive and intelligent computing, today announced a new breakthrough product category called adaptive compute acceleration platform (ACAP) that goes far beyond the capabilities of an FPGA. An ACAP is a highly integrated multi-core heterogeneous compute platform that can be changed at the hardware level to adapt to the needs of a wide range of applications and workloads. An ACAP's adaptability, which can be done dynamically during operation, delivers levels of performance and performance per-watt that is unmatched by CPUs or GPUs.

An ACAP is ideally suited to accelerate a broad set of applications in the emerging era of big data and artificial intelligence. These include: video transcoding, database, data compression, search, AI inference, genomics, machine vision, computational storage and network acceleration. Software and hardware developers will be able to design ACAP-based products for end point, edge and cloud applications. The first ACAP product family, codenamed "Everest," will be developed in TSMC 7nm process technology and will tape out later this year.

Supermicro Launches New Embedded Solutions Based on the Intel Xeon D-2100 SoC

Super Micro Computer, Inc. (NASDAQ: SMCI), a global leader in enterprise computing, storage, networking solutions and green computing technology, today announced several new additions to its edge computing and network appliance portfolio based on the new Intel Xeon D-2100 SoC (System-on-a-Chip) processor.

Leveraging its deep expertise in server technology, Supermicro is bringing customers some of the first Intel Xeon D-2100 System-on-a-Chip (SoC) processor-based solutions. The company's X11SDV series motherboards offer infrastructure optimization by combining the performance and advanced intelligence of Intel Xeon processors into a dense, lower-power system-on-a-chip. Supermicro is introducing a wide range of new systems to the market including compact embedded systems, rackmount embedded systems, as well as multi-node MicroCloud and SuperBlade systems.

Qualcomm to Build Snapdragon 5G SoCs on Samsung 7nm LPP EUV Process

Samsung Electronics, a world leader in advanced semiconductor technology, and Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, today announced the intention to expand their decade-long foundry relationship into EUV (extreme ultra violet) lithography process technology, including the manufacture of future Qualcomm Snapdragon 5G mobile chipsets using Samsung's 7-nanometer (nm) LPP (Low Power Plus) EUV process technology.

Using 7LPP EUV process technology, Snapdragon 5G mobile chipsets will offer a smaller chip footprint, giving OEMs more usable space inside upcoming products to support larger batteries or slimmer designs. Process improvements, combined with a more advanced chip design, are expected to bring significant improvements in battery life.

HDPlex H3 V2 Fanless Chassis Pictured

Here are some of the first pictures of HDPlex H3 V2 fan-less HTPC chassis. The H3 sits between the tiny H1 and deck-sized H5. It has the height of the H5 and the width of the H1. The case measures 270 mm x 264 mm x 93 mm (WxDxH), weighing in at 5.5 kg. Its main chamber can house mini-ITX motherboards, and a half-height add-on card that's no more than 1-slot thick. As with most fan-less cases, the chunky, ridged aluminium body of the H3 V2 doubles up as heatsink for the CPU/SoC, and can handle thermal loads of up to 80W. The CPU block uses eight 6 mm-thick copper heat pipes to transport heat to the body. The case also has room for up to four 7 mm-thick 2.5-inch drives. Available now, it is priced at USD $240.

Intel Launches Their Xeon D-2100 Series SoCs

Intel today introduced the new Intel Xeon D-2100 processor, a system-on-chip (SoC) processor architected to address the needs of edge applications and other data center or network applications constrained by space and power. The Intel Xeon D-2100 processor extends the record-breaking performance and innovation of the Intel Xeon Scalable platform from the heart of the data center to the network edge and web tier, where network operators and cloud service providers face the need to continuously grow performance and capacity without increasing power consumption.

"To seize 5G and new cloud and network opportunities, service providers need to optimize their data center and edge infrastructures to meet the growing demands of bandwidth-hungry end users and their smart and connected devices," said Sandra Rivera, senior vice president and general manager of the Network Platforms Group at Intel. "The Intel Xeon D-2100 processor allows service providers and enterprises to deliver the maximum amount of compute intelligence at the edge or web tier while expending the least power."

Samsung Enters Volume Production of a Killer Crypto-mining ASIC

One of the world's largest SoC, DRAM, and NAND flash makers, with its own semiconductor fabs, Samsung, is eyeing itself a large slice of the crypto-currency mining craze. The company reportedly entered volume production of a highly efficient crypto-currency mining ASIC, for an unnamed client from China. The client has placed a gargantuan order for crypto-coin mining ASICs contract-manufactured by Samsung, which appears to be targeted at Bitcoin, for now.

China's largest mining ASIC solutions providers, Bitman and Cannan, have similarly contracted TSMC to manufacture mining ASICs. An ASIC (from a mining context) is a single-chip solution that combines a CPU, a SIMD parallel-processing component tailored for mining, memory, and storage. It has infinitesimally smaller PCB, power, and thermal footprints compared to PCs with GPUs, and can be deployed in extremely large numbers for mining on an industrial-scale.
Return to Keyword Browsing