VeriSilicon Expands DSP Portfolio with Silicon-Proven ZSP5000 Vision Core Series for Edge Intelligence
SHANGHAI — VeriSilicon (688521.SH) today released the ZSP5000 Digital Signal Processing (DSP) series IPs, which are based on its fifth-generation silicon-proven DSP architecture. This product line adopts a highly scalable and energy-efficient design, and has been deeply optimized for compute-intensive workloads such as computer vision and embedded AI. Combined with the configurable nature of the architecture, this series of IP can provide excellent solutions with both energy and computing efficiency for various edge devices.
Article content
The ZSP5000 series IPs include ZSP5000, ZSP5000UL, ZSP5000L, and ZSP5000H, delivering scalable vector processing performance ranging from 32 to 256 8-bit Multiply-Accumulate (MAC) operations per cycle. For even higher performance, VeriSilicon's multi-core ZSP5400H can combine multiple ZSP5000H cores in a multi-cluster architecture to further scale computing capability.
Article content
The ZSP5000 series features a rich and intuitive instruction set optimized for ease of programming and efficient performance tuning, while its dedicated instructions accelerate common imaging and signal processing tasks such as vector-scalar arithmetic, horizontal reductions, permutations, shifts, table lookups, clamping, and averaging. It integrates the ZTurbo coprocessor interface, allowing customers to easily add custom instructions and hardware accelerators within the same pipeline, and is compatible with the OpenCV Application Programming Interface (API), ensuring seamless integration with the mainstream computer vision frameworks. Additionally, the ZSP5000 series is equipped with a full-featured memory subsystem, a multi-channel 3D DMA engine, and a scalable multicore configuration, supporting flexible deployment for a broad spectrum of applications.
Article content
The ZSP5000 series IPs are backward compatible with VeriSilicon's scalar ZSPNano series, efficiently handling mixed MCU and DSP workloads. VeriSilicon also offers comprehensive ZView development tools, including an Eclipse-based Integrated Development Environment (IDE), cycle-accurate simulator, optimizing compiler, debugger, and profiling tools, streamlining software development and system integration.
Article content
'With the growing adoption of OpenCV and the increasing demand for computer vision workloads alongside NPUs in edge intelligence computing, we are introducing the ZSP5000—our next-generation DSP IP series. It supports the industry-standard OpenCV API, enables streamlined interfacing with NPUs via our FLEXA interface, and integrates built-in audio processing capabilities for multi-modal applications,' said Weijin Dai, Chief Strategy Officer, Executive Vice President, and General Manager of the IP Division at VeriSilicon. 'Energy efficiency is key at the edge, and the ZSP5000 series IPs feature an optimized memory access architecture to minimize processor power consumption. It also features ZTurbo, a custom instruction extension mechanism designed for targeted applications, which enables further power and performance optimization through seamless integration of hardware accelerators. Our leading customers are already leveraging these capabilities to achieve significant advancements in power and performance.'
Article content
Article content
Article content
Article content
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Globe and Mail
3 hours ago
- Globe and Mail
2 Artificial Intelligence (AI) Stocks the U.S. Government Is Actively Backing in 2025
Key Points Defense Secretary Pete Hegseth outlined a vision for the U.S. government to leverage more software across its operations. So far this year, data analytics platforms Palantir Technologies and have been notable beneficiaries in the public sector. Both companies' software is deployed across numerous government agencies, but I see one of these high-flying AI stocks as the clear winner. 10 stocks we like better than Palantir Technologies › When it comes to artificial intelligence (AI) stocks, chances are investors' thoughts may turn to semiconductors, massive data centers, or cloud computing infrastructure. This is great news for chip powerhouses and hyperscalers like Nvidia, Advanced Micro Devices, Broadcom, Taiwan Semiconductor Manufacturing, Microsoft, Amazon, or Alphabet, but investors could be overlooking emerging opportunities beyond the usual suspects. Enterprise-grade software will become an increasingly vital layer atop the hardware stack. The commercial angle is to market AI-powered software to large corporations with complex needs spanning data analytics, logistics, human resources, cybersecurity, and more. Where to invest $1,000 right now? Our analyst team just revealed what they believe are the 10 best stocks to buy right now. Learn More » But there is another opportunity outside of the private sector: how AI is redefining one of the largest and most sophisticated enterprises of all, the U.S. government. Earlier this year, Defense Secretary Pete Hegseth announced a plan to allocate more spending toward the Software Acquisition Pathway (SWP), a strategy first deployed in 2020. Its stated aim is to "provide for the efficient and effective acquisition, development, integration, and timely delivery of secure software." Let's explore how Palantir Technologies (NASDAQ: PLTR) and (NYSE: BBAI) are capitalizing on AI's shift from hardware to software and how each company is approaching the opportunity with SWP. 1. Palantir Technologies: The AI darling of the U.S. government Palantir has been at the center of several notable deals with the federal government throughout 2025. In late May, it deepened its relationship with the Department of Defense (DOD) through a $795 million extension featuring its Maven Smart System (MSS). This brought the total value of the MSS program to $1.28 billion, making it a long-term revenue driver. More recently, the company won a deal with the Army reportedly worth up to $10 billion over the next 10 years. Palantir's wins extend beyond the U.S. military as well. The company is building the Immigration Lifecycle Operating System -- often referred to as ImmigrationOS -- for Immigration and Customs Enforcement (ICE). Signing multiyear billion-dollar deals provides Palantir with high revenue visibility, keeps its customer base sticky, and opens the door to upsell or cross-sell added services down the road. The ability to parlay its defense expertise into other government functions also expands Palantir's public sector footprint and reinforces the breadth of its capabilities -- solidifying its role as a ubiquitous AI backbone for the U.S. government. 2. A niche player helping the public sector Another AI software developer that has signed deals with the U.S. government this year is In February, it won a contract with the DOD to design a system to assist national security decision-making by analyzing trends and patterns in foreign media. Shortly thereafter, the company won a $13.2 million deal spread over three and a half years to support the Joint Chiefs of Staff's force management and data analytics capabilities. In May, the company partnered with Hardy Dynamics to advance the Army's use of machine learning and AI for autonomous drones. Lastly, has a deal with U.S. Customs and Border Protection to deploy its biometric AI infrastructure system, called Pangiam, at a dozen major airports across North America to help streamline arrivals and improve security protocols. Which is the better stock: Palantir or Between the two stocks, I see Palantir as the clear choice. has proved it can win meaningful government contracts, but its work is more niche-focused and smaller in scale compared to Palantir's multibillion-dollar deals across multiple platforms. In my view, popularity is largely with retail investors who are hoping that it becomes the "next Palantir." Smart investors know that hope is not a real strategy. Prudent valuation analysis -- and not speculation -- is required to know which stock is truly worth buying. While some on Wall Street may argue that Palantir stock is cheap based on software-specific metrics such as the Rule of 40, I'm not entirely bought into such a narrative. PLTR PS Ratio data by YCharts. Traditional approaches to valuation, such as the price-to-sales ratio (P/S), show that Palantir is the priciest software-as-a-service stock among the businesses in the chart above -- and its valuation expansion means that shares are becoming even more expensive as the stock continues to rally. Palantir is an impressive company that has proved it can deliver on crucial applications, but the stock is historically expensive. I think that investors are better off waiting for a more reasonable entry point and paying a more appropriate price down the road. Should you invest $1,000 in Palantir Technologies right now? Before you buy stock in Palantir Technologies, consider this: The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Palantir Technologies wasn't one of them. The 10 stocks that made the cut could produce monster returns in the coming years. Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you'd have $668,155!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you'd have $1,106,071!* Now, it's worth noting Stock Advisor's total average return is 1,070% — a market-crushing outperformance compared to 184% for the S&P 500. Don't miss out on the latest top 10 list, available when you join Stock Advisor. See the 10 stocks » *Stock Advisor returns as of August 13, 2025 Adam Spatacco has positions in Alphabet, Amazon, Microsoft, Nvidia, and Palantir Technologies. The Motley Fool has positions in and recommends Advanced Micro Devices, Alphabet, Amazon, Datadog, Microsoft, MongoDB, Nvidia, Palantir Technologies, ServiceNow, Snowflake, and Taiwan Semiconductor Manufacturing. The Motley Fool recommends Broadcom and recommends the following options: long January 2026 $395 calls on Microsoft and short January 2026 $405 calls on Microsoft. The Motley Fool has a disclosure policy.
Globe and Mail
8 hours ago
- Globe and Mail
5 Artificial Intelligence (AI) Stocks to Buy and Hold for the Next Decade
Key Points Nvidia and Taiwan Semiconductor are slated to profit from the huge AI computing power buildout. Meta Platforms and Alphabet are using AI to improve advertising. Amazon's cloud computing division is seeing strong AI demand. 10 stocks we like better than Nvidia › The best investing strategies involve buying great companies and holding them over long periods to let them be, which has yielded impressive returns if you picked the right businesses. Among the top performers over the past decade have been Nvidia (NASDAQ: NVDA), Taiwan Semiconductor Manufacturing (NYSE: TSM), Amazon (NASDAQ: AMZN), Meta Platforms (NASDAQ: META), and Alphabet (NASDAQ: GOOG)(NASDAQ: GOOGL). I removed Nvidia from the chart below because it's up over 30,000% in the past decade, which skews the graph, but the other four have also done phenomenally well. TSM data by YCharts. The "worst" performer of the remaining four has been Alphabet, with its stock rising nearly five times in value. These five stocks have had a strong run over the past decade, but I still believe they are excellent picks for the next decade, mainly due to the proliferation of artificial intelligence (AI). They are at the top of my list right now, and I think buying shares with the mindset of holding for the next decade is a wise investment strategy. Nvidia and Taiwan Semiconductor are providing AI computing power All five of these stocks are benefiting in various ways from the AI race. Nvidia makes graphics processing units (GPUs), which are currently the most popular computing hardware for running and training AI models. It owns this market, and its dominance has allowed it to become the world's largest company. There's still a huge AI computing demand that hasn't been met, which bodes well for Nvidia's future. Because of this, it remains one of the best stocks to buy and hold over the next decade. Taiwan Semiconductor (TSMC for short) is a manufacturer that produces chips for many of the major players in AI, including Nvidia. These companies don't have chip production capabilities, so they farm that work out to TSMC, which has earned its reputation for being the best foundry in the world through continuous innovation and impressive yields. There are few challengers to its supremacy, and this position will help it continue to be a market-crushing stock for the foreseeable future. Nvidia and Taiwan Semiconductor are seeing huge growth right now because they're providing the computing power necessary for AI. The next three are also benefiting and will likely see even more success over the next decade. More AI applications will rise over the next few years At first glance, Amazon doesn't seem like much of an AI company. However, it has large exposure through its cloud computing wing, Amazon Web Services (AWS), which is the largest cloud computing provider. It's seeing strong demand for increased computing capacity for AI workloads. With this demand expected to rapidly increase over the next decade, this bodes well for AWS, which makes up the majority of Amazon's profits, helping drive the stock to new heights. Meta Platforms is developing its own in-house generative AI model, Llama. It has several uses for it, but the biggest is maintaining its role at the top of the social media world. Meta owns two of the biggest social media platforms, Facebook and Instagram, which generate most of their money through ad revenue. The company has integrated AI tools into its ad services and has already seen an uptick in interaction and conversion rates. This effect will become even greater as generative AI technologies improve, making Meta a strong stock pick for the next decade. Lastly is Alphabet. Many think Alphabet will be displaced by AI because it gets the majority of its revenue through Google Search, which is seen as a target for AI disruption. However, that hasn't happened yet, and Google Search continues to get larger, with revenue rising 12% in the second quarter. Part of its success can be attributed to the rise of its Search Overviews, which are a hybrid between a traditional search engine and generative AI. This feature has become popular and could be enough to keep Google on top in search, allowing it to achieve new heights over the next decade. Should you invest $1,000 in Nvidia right now? Before you buy stock in Nvidia, consider this: The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Nvidia wasn't one of them. The 10 stocks that made the cut could produce monster returns in the coming years. Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you'd have $668,155!* Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you'd have $1,106,071!* Now, it's worth noting Stock Advisor's total average return is 1,070% — a market-crushing outperformance compared to 184% for the S&P 500. Don't miss out on the latest top 10 list, available when you join Stock Advisor. See the 10 stocks » *Stock Advisor returns as of August 13, 2025 Keithen Drury has positions in Alphabet, Amazon, Meta Platforms, Nvidia, and Taiwan Semiconductor Manufacturing. The Motley Fool has positions in and recommends Alphabet, Amazon, Meta Platforms, Nvidia, and Taiwan Semiconductor Manufacturing. The Motley Fool has a disclosure policy.
Globe and Mail
10 hours ago
- Globe and Mail
TSMC (TSM): New Buy Recommendation for This Technology Giant
Bernstein analyst Mark Li reiterated a Buy rating on TSMC today and set a price target of $249.00. The company's shares closed today at $238.88. Elevate Your Investing Strategy: Take advantage of TipRanks Premium at 50% off! Unlock powerful investing tools, advanced data, and expert analyst insights to help you invest with confidence. According to TipRanks, Li is a 5-star analyst with an average return of 26.5% and a 67.57% success rate. Li covers the Technology sector, focusing on stocks such as Micron, TSMC, and United Micro. TSMC has an analyst consensus of Strong Buy, with a price target consensus of $269.00, which is a 12.61% upside from current levels. In a report released on August 13, Bank of America Securities also reiterated a Buy rating on the stock with a $290.00 price target. The company has a one-year high of $248.28 and a one-year low of $134.25. Currently, TSMC has an average volume of 11.21M.
