Latest Post

KPX Holdings Co., Ltd. (KRX:092230) looks like a good stock and will soon trade ex-dividend America as a Christian nation, fatherhood, eye medicine

Finnish startup Flow Computing Oy today announced seemingly far-fetched plans to revolutionize the chip industry with a new parallel processing unit that will increase the performance of any central processing unit by an incredible 100-fold.

This astonishing claim came after the company announced it had raised $4 million in pre-funding from a number of Nordic venture capital firms and companies. Butterfly Ventures led the round, with participation from FOV Ventures, Sarsia, Stephen Industries, Superhero Capital and Business Finland.

The Finnish VTT Technical Research Center, a government research laboratory, originally developed Flow’s technology and remains a shareholder in the company, although the intellectual property behind the technology now belongs to Flow.

Flow, which grew out of VTT, claims it can increase processing power by 100x by integrating its PPU companion chip into any CPU. The company claims its PPU chips are fully backwards compatible, meaning they can be integrated into any type of CPU to provide this acceleration to any existing software or application without requiring any changes to the code.

The exact extent of the performance increase will be determined by the number of integrated PPU cores, the startup explained, adding that it has optimized licenses for its technology for every level of the CPU market, including CPUs for mobile, supercomputers and personal computers.

According to the startup, its PPU chips bypass one of the main limitations of existing CPUs, namely their inability to perform parallel processing. Today’s CPUs are super fast and can switch between different tasks millions of times per second, but even so, they are still a one-way street as they can only perform one task at a time.

This limitation means that today’s CPUs, despite their nanosecond responsiveness, are still extremely inefficient at executing instructions simply because they have to complete one task before moving on to the next.

Flow says its PPUs get around this limitation by turning each CPU into a multi-lane highway. Although the CPU still only runs one task at a time, Flow’s PPU improves traffic management to the point where tasks can be moved in and out of the processor much faster than before.

The startup has yet to validate its technology for an official CPU, but has demonstrated its capabilities on various field-programmable gate arrays, chips that can be programmed before use to make them more efficient at a very specific task. It has also run a series of simulations designed to confirm its performance claims.

The diagram shows the improvements of an FPGA PPU-enhanced chip over unmodified Intel chips. By increasing the number of PPU cores, Flow continuously improves performance

Flow hopes to develop a business model similar to that of Arm Ltd., the British chip design company that simply licenses blueprints to other chipmakers. The company wants to convince chipmakers such as Intel Corp., Advanced Micro Devices Inc., Apple Inc., Nvidia Corp. and Qualcomm Inc. to license its technology.

Whether these talks will bear fruit remains to be seen. One of Flow’s biggest challenges will be convincing chipmakers to integrate its technology at the chip design level. This is a big challenge because chipmakers would have to invest significant resources to do so, and it would likely seriously disrupt their long-term development plans.

Still, the magnitude of Flow’s performance gains, combined with the fact that chipmakers have only been able to make incremental improvements to their CPUs over the past few years, might be enough to convince someone. If Flow can truly double the processing speed of any CPU, it’s probably worth implementing, no matter how much it might disrupt chipmakers’ existing plans.

The startup has at least caught the attention of several “major semiconductor vendors,” and while it didn’t name names, it said it would reveal more “technical details” later this year.

According to Timo Valtonen, co-founder and CEO of Flow, advances in CPU performance have slowed to the point where the CPU has become the “weakest link” in computing.

“A new era of CPU performance has become a necessity to meet the ever-increasing demand for more computing power, driven largely by the needs of AI, edge and cloud computing,” he said.

Featured image: SiliconANGLE/Microsoft Designer

Your support is important to us and helps us keep the content FREE.

By clicking below you support our mission to provide free, in-depth and relevant content.

Join our community on YouTube

Join the community of more than 15,000 #CubeAlumni experts, including CEO Andy Jassy, ​​Dell Technologies Founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner for the industry. You are truly a part of our events and we are very happy that you are coming. And I know that people also appreciate the content that you create” – Andy Jassy


Leave a Reply

Your email address will not be published. Required fields are marked *