Nvidia’s first cost disadvantage versus AMD in a decadeRead more
Nvidia Is Playing A Different Ball GameRead more
Broadcom Tomahawk 5, Cisco Silicon One, Nvidia Spectrum-4, Marvell Teralynx 9, Intel Tofino 4Read more
Intel Habana, Graphcore, Google TPU, and Nvidia A100 Compared In AI Training With MLPerfRead more
In depth breakdown of Nvidia’s Lovelace including architecture, die size, cost, and performance.Read more
Nvidia’s software expertise has propelled them to completely dominating the markets they operate in. Intel Network and Edge Group has a successful playbook to fight back. They have come to dominate many areas of hardware with this playbook. In this post we will discuss the playbook in detail.Read more
This article was originally published on March 23rd via the SemiAnalysis newsletter. A long-time supplier of Nvidia has seemingly beenRead more
They have numerous wins at Nvidia, Broadcom, Marvell, Cisco, Macom, Ayar Labs, Lightmatter, PsiQuantum, Ranovus, And Xanadu. In addition they are deeply integrated with the PDK and simulation toolchain with partnerships with Ansys, Cadence, and Synopsys.Read more
The hack contains sensitive info on future GPU configurations, source code for software, tester, simulation, and Verilog code.
This could be the most significant act of corporate espionage in a generation.
Advanced packaging exists on a continuum of cost and throughput vs performance and density. Even though the demand for advanced packaging is obvious, there is an incredible number of advanced packaging types and brand names from Intel (EMIB, Foveros, Foveros Omni, Foveros Direct), TSMC (InFO-OS, InFO-LSI, InFO-SOW, InFO-SoIS, CoWoS-S, CoWoS-R, CoWoS-L, SoIC), Samsung (FOSiP, X-Cube, I-Cube, HBM, DDR/LPDDR DRAM, CIS), ASE (FoCoS, FOEB), Sony (CIS), Micron (HBM), SKHynix (HBM), and YMTC (XStacking). These packaging types are used by all of our favorite companies from AMD, Nvidia, and many more. In Part 2, we will explain all these types of packaging and their uses.Read more