Yep, i have pretty well finished accumulating which started in early 2020. So no more holding back from me.
BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
So what about people who still want to accumulate? A bit selfish for a brainchip member isn’t it? You know that the brainchip community has a strong team spirit! We are waiting with pushing until everyone have finished!
Smoothsailing
Regular
Humble Genius
Regular
New employee.....
www.linkedin.com
I’m happy to share that I’m starting a new position as Junior ASIC Design Verification Engineer at BrainChip ! | Haritha Reddy Kachireddy
I’m happy to share that I’m starting a new position as Junior ASIC Design Verification Engineer at BrainChip ! | 13 comments on LinkedIn
Welcome to BrainChip
Power innovation with BrainChip's first-to-market neuromorphic AI. Advance solutions to the Edge. Explore now!
Fullmoonfever
Top 20
Despite all their neuromorphic Loihi development.....well, research ability....maybe Intel should be talking a bit more to us for a licence to get to market before the ship actually gets over the horizon and out of view completely 
TSMC founder criticizes Intel's foundry pivot; says AI focus was crucial (Image source: Intel)
TSMC founder Morris Chang criticizes Intel's focus on becoming a contract chipmaker rather than developing AI capabilities, highlighting the challenges faced by the struggling tech giant following CEO Pat Gelsinger's departure and recent setbacks in AI hardware development.
Nathan Ali, Published 12/11/2024
Morris Chang, the person who founded TSMC, recently took a jab at Intel's strategy. He said the company should've focused more on developing AI instead of trying to become a contract chipmaker. Chang made these comments during the launch of his autobiography on Monday.
This comes right after Intel’s CEO Pat Gelsinger stepped down. The board wasn’t happy with how Gelsinger’s aggressive turnaround plan was progressing—or, well, not progressing.
Under Gelsinger, Intel aimed to reclaim its position as the top manufacturer of chips for other companies, a spot that TSMC currently owns.
"Compared with AI, he seemed to focus more on becoming a foundry. Of course now it seems that Gelsinger should have focused on AI," Chang said, taking a swing at Intel's direction. He also mentioned that Intel is now without both a clear strategy and a CEO, calling it a tough situation.
Chang's words hit hard, especially given how Intel’s been struggling with AI lately. The company recently announced it won’t hit its $500 million sales target for its Gaudi 3 AI accelerators this year, blaming software issues—another sign that the focus on AI may have been lacking.
Chang’s autobiography, which covers his life from 1964 to 2018, also throws some light on Intel’s past decisions. Like, he talks about how Intel passed on the chance to invest in TSMC back in the '80s—before eventually becoming one of its biggest customers. The book also outlines TSMC's relationships with companies like Apple and Qualcomm.
TSMC founder: Intel should have prioritized AI over foundry business
TSMC founder criticizes Intel's foundry pivot; says AI focus was crucial (Image source: Intel)TSMC founder Morris Chang criticizes Intel's focus on becoming a contract chipmaker rather than developing AI capabilities, highlighting the challenges faced by the struggling tech giant following CEO Pat Gelsinger's departure and recent setbacks in AI hardware development.
Nathan Ali, Published 12/11/2024
Morris Chang, the person who founded TSMC, recently took a jab at Intel's strategy. He said the company should've focused more on developing AI instead of trying to become a contract chipmaker. Chang made these comments during the launch of his autobiography on Monday.
This comes right after Intel’s CEO Pat Gelsinger stepped down. The board wasn’t happy with how Gelsinger’s aggressive turnaround plan was progressing—or, well, not progressing.
Under Gelsinger, Intel aimed to reclaim its position as the top manufacturer of chips for other companies, a spot that TSMC currently owns.
"Compared with AI, he seemed to focus more on becoming a foundry. Of course now it seems that Gelsinger should have focused on AI," Chang said, taking a swing at Intel's direction. He also mentioned that Intel is now without both a clear strategy and a CEO, calling it a tough situation.
Chang's words hit hard, especially given how Intel’s been struggling with AI lately. The company recently announced it won’t hit its $500 million sales target for its Gaudi 3 AI accelerators this year, blaming software issues—another sign that the focus on AI may have been lacking.
Chang’s autobiography, which covers his life from 1964 to 2018, also throws some light on Intel’s past decisions. Like, he talks about how Intel passed on the chance to invest in TSMC back in the '80s—before eventually becoming one of its biggest customers. The book also outlines TSMC's relationships with companies like Apple and Qualcomm.
TSMC founder: Intel should have prioritized AI over foundry
TSMC founder: Intel should have prioritized AI over foundry News
www.design-reuse-embedded.com
Why Akida 2?
Sean Hehir mentioned that Akida 1 has narrow application, so what does Akida 2 add?
What do these features facilitate? ( https://brainchip.com/akida-generations/ )
We’ve heard a little about denoising earphones/hearing aids.
We already knew about key word spotting , but speech processing involves the temporal element and long skip (to preserve the context of the speech).
Healthcare involves reading physiological signals, X-ray and ultrasound interpretation, etc.
Predictive maintenance from vibration analysis.
Video object detection was within Akida 1’s capability, so the tracking is new – this would have needed to be done by an associated CPU for Akida 1. This is for consumer, automotive, and industrial applications. It would be especially advantageous for EVs as it reduces the CPU power drain.
Vision, lidar analysis for ADAS – Akida 1 does vision/lidar classification, so “analysis” is an added feature, again relieving the CPU of the task. In particular, this may relate to object identification and tracking, possibly utilizing vision transformer and long skip to keep track of an object’s movements. Similar considerations apply to robotic autonomy.
So, all-in-all, I think that the Akida 2/TENNs improvements bring significant power and latency benefits for EVs.
Unfortunately, as far as we know, there is no Akida 2 silicon. Still, using Akida and or TENNs models with the corresponding simulation software would bring substantial advantages to battery-powered devices including EVs, because Akida models are much more compact than competing tech models, and TENNs models are more compact again.
We know Valeo, Mercedes and others are developing SDVs.
We know we've been working with Valeo and Mercedes for a few years. Even if there has been insufficient testing of Akida 2 for safety-critical applications, I think there would be scope for Akida 2's long skip to be used in speech recognition in the infotainment system in the not too distant future.
Sean Hehir mentioned that Akida 1 has narrow application, so what does Akida 2 add?
- 8-bit weights and activations;
- Vision transformer;
- Long skip;
- TENNs.
What do these features facilitate? ( https://brainchip.com/akida-generations/ )
- Audio Processing, Filtering, Denoising for Hearing Aids, and Hearables
- Speech Processing for Consumer, Automotive and Industrial Applications
- Vital Signs Prediction & Monitoring in Healthcare
- Time Series Forecasting for Industrial Predictive Maintenance
- Video Object Detection and Tracking in Consumer, Automotive and Industrial
- Vision, LIDAR Analysis for ADAS
- Advanced Sequence Prediction for Robotic Navigation and Autonomy
We’ve heard a little about denoising earphones/hearing aids.
We already knew about key word spotting , but speech processing involves the temporal element and long skip (to preserve the context of the speech).
Healthcare involves reading physiological signals, X-ray and ultrasound interpretation, etc.
Predictive maintenance from vibration analysis.
Video object detection was within Akida 1’s capability, so the tracking is new – this would have needed to be done by an associated CPU for Akida 1. This is for consumer, automotive, and industrial applications. It would be especially advantageous for EVs as it reduces the CPU power drain.
Vision, lidar analysis for ADAS – Akida 1 does vision/lidar classification, so “analysis” is an added feature, again relieving the CPU of the task. In particular, this may relate to object identification and tracking, possibly utilizing vision transformer and long skip to keep track of an object’s movements. Similar considerations apply to robotic autonomy.
So, all-in-all, I think that the Akida 2/TENNs improvements bring significant power and latency benefits for EVs.
Unfortunately, as far as we know, there is no Akida 2 silicon. Still, using Akida and or TENNs models with the corresponding simulation software would bring substantial advantages to battery-powered devices including EVs, because Akida models are much more compact than competing tech models, and TENNs models are more compact again.
We know Valeo, Mercedes and others are developing SDVs.
We know we've been working with Valeo and Mercedes for a few years. Even if there has been insufficient testing of Akida 2 for safety-critical applications, I think there would be scope for Akida 2's long skip to be used in speech recognition in the infotainment system in the not too distant future.
Last edited:
Learning
Learning to the Top 🕵♂️
Thank you sensei Dio!
Thank you for all the educationals
and all the laughter post throughout the years 
.Learning
Always learning
1000x, geez TCS, stop being so dramatic!
Its only a matter of time. Companies cannot continue to ignore these energy savings.
Last edited:
Akida has the capability to run 1-bit weights and activations. This is very low latency, but probably not hi-fi, but there may be cases where precise discrimination is not required, eg, motion detection, and we know 1-bit can be more selective than that. In its original conception, Akida was 1-bit.
Bravo
If ARM was an arm, BRN would be its biceps💪!
Morning All,
As we all know, the Nintendo Switch 2 is widely expected to launch in 2025. And I was just reading some of the latest rumours (best taken with a grain of salt by the way) suggesting the big reveal could happen as early as January 8, 2025!
If Nintendo does decide to make an announcement that soon, I certainly won't be complaining because it will finally put to bed years of speculation. Obviously there's a decent chance that our technology might be incorporated in the next-generation console on the basis of the information I've included below.
And if f we are incorporated, it would likely be alongside NVIDIA’s Tegra 239 processor. Being featured in a product from a globally renowned brand like Nintendo, alongside a technology giant like NVIDIA, would be nothing short of a dream come true - like hitting two major targets with one golden arrow!
The level of attention this would garner for BrainChip if our tech were to be incorporated in such a widely popular system is impossible to overstate IMO, especially if it enables capabilities previously unimaginable in gaming with features like gesture recognition, face recognition, voice recognition, and voice identification alongside benefits of low power consumption and longer battery life. Not only would it bring huge value to the user experience but it would also help us to showcase on a global scale the transformative power of our innovations.
Patience has been a crucial virtue in this process, given the lengthy product cycles involved in developing large-scale integration (LSI) systems. However, if this achievement comes to fruition, the payoff for our perseverance will be monumental.
As for the recent rise in our share price, it’s hard to pinpoint the exact cause. Is it the likelihood of our involvement in the soon to be released Nintendo Switch 2? The anticipation surrounding CES 2025 and potential reveals there? The strategic positioning of our intellectual property with Renesas? Or perhaps the credibility we’ve gained from recent announcements involving Airbus and the AFRL?
Whatever the reason, I believe the increasing share price is a sign that the market is starting to wake up to the potential of our stock and with the right announcements forthcomming, we could go absolutely gang-busters.
My opinion only.
As we all know, the Nintendo Switch 2 is widely expected to launch in 2025. And I was just reading some of the latest rumours (best taken with a grain of salt by the way) suggesting the big reveal could happen as early as January 8, 2025!
If Nintendo does decide to make an announcement that soon, I certainly won't be complaining because it will finally put to bed years of speculation. Obviously there's a decent chance that our technology might be incorporated in the next-generation console on the basis of the information I've included below.
And if f we are incorporated, it would likely be alongside NVIDIA’s Tegra 239 processor. Being featured in a product from a globally renowned brand like Nintendo, alongside a technology giant like NVIDIA, would be nothing short of a dream come true - like hitting two major targets with one golden arrow!
The level of attention this would garner for BrainChip if our tech were to be incorporated in such a widely popular system is impossible to overstate IMO, especially if it enables capabilities previously unimaginable in gaming with features like gesture recognition, face recognition, voice recognition, and voice identification alongside benefits of low power consumption and longer battery life. Not only would it bring huge value to the user experience but it would also help us to showcase on a global scale the transformative power of our innovations.
Patience has been a crucial virtue in this process, given the lengthy product cycles involved in developing large-scale integration (LSI) systems. However, if this achievement comes to fruition, the payoff for our perseverance will be monumental.
As for the recent rise in our share price, it’s hard to pinpoint the exact cause. Is it the likelihood of our involvement in the soon to be released Nintendo Switch 2? The anticipation surrounding CES 2025 and potential reveals there? The strategic positioning of our intellectual property with Renesas? Or perhaps the credibility we’ve gained from recent announcements involving Airbus and the AFRL?
Whatever the reason, I believe the increasing share price is a sign that the market is starting to wake up to the potential of our stock and with the right announcements forthcomming, we could go absolutely gang-busters.
My opinion only.
Business and Other Risks | MegaChips Corporation
We aim at sustainable growth through profitability and growth opportunity.
www.megachips.co.jp
Image Processing | MegaChips Corporation
We respond to various issues of customers including cost and development period with our integrated support leveraging foundries around the world.
www.megachips.co.jp
Pom down under
Top 20
Up 119% this year, can BrainChip shares soar again in 2025?
BrainChip shares have outperformed in 2024 and will finish the year in triple digits in the green. Will 2025 be the same? Let's see.
www.fool.com.au
Townyj
Ermahgerd
Up 119% this year, can BrainChip shares soar again in 2025?
BrainChip shares have outperformed in 2024 and will finish the year in triple digits in the green. Will 2025 be the same? Let's see.
.... really.. no one takes this guy seriously.
Bravo
If ARM was an arm, BRN would be its biceps💪!
"Best-in-class power efficiency", so they say! Whose NPU is this I wonder?
Says here the "basic R-Car X5H includes up to 32 Arm Cortex-720AE" and we know were are compatible across Arm's product range.
Renesas previously collaborated with Hailo to offer combined solutions that pair the R-Car V4H SoC with Hailo-8 AI accelerators.
However, there isn't any publicly available information indicating that Renesas and Hailo have collaborated on the R-Car X5H, at least none that I've found as yet.
Chiplets Extend Automotive SoC AI and GPU Capability
Dec. 28, 2024
Renesas’ R-Car X5H SoC, which meets ASIL B/D, provides scalable automotive compute.
William G. Wong
https://www.electronicdesign.com/print/content/55252079
The R-Car X5H family is a fifth-generation automotive system-on-chip (SoC) developed by Renesas that supports ASIL B/D capabilities as well as a neural processing unit (NPU). Built on the latest 3-nm chip technology, enhanced versions of the SoC come courtesy of chiplet technology. I talked with Cyril Clocher, Senior Director of the Automotive Product Line, about the details.
Renesas
1. The Renesas R-Car X5H includes 32 Arm Cortex-720AE applications cores, six Arm Cortex-R52 cores with lockstep support, an NPU, and a GPU.
There are general-purpose DSP cores, too, along with specialized accelerators such as the image signal processor (ISP) and dense-optical-flow (DOF) hardware accelerator (HWA) for handling multi-megapixel camera video streams.
The on-chip NPU can deliver up to 400 TOPS, while the on-chip GPU generates 4 TFLOPS of performance.
The chip includes an 8-port Ethernet switch, USB 2/3 ports, and PCI Express (PCIe) that supports Gen 4 and Gen 6. Also in the mix are an on-chip dedicated NPU and GPU. The GPU can drive a car’s display panel while the NPU handles artificial-intelligence and machine-learning (AI/ML) models.
Renesas
2. The R-Car X5H can be enhanced by including an NPU and GPU chiplet.
Renesas has two types of chiplets that can be included in enhanced versions of the R-Car SoC—again, an NPU and a GPU. These are designed to augment the functionality of the built-in NPU and GPU. The chiplet and on-chip NPU are able to run a separate set of AI/ML models. Likewise, the GPU can drive additional displays.
Renesas’ R-Car Open Access (RoX) SDV platform helps get developers up to speed by simplifying their development chores (Fig. 3). It works with a variety of pre-integrated operating systems and frameworks, tying them into the Arm Cortex-A720AE and Cortex-R52 compute arrays. It utilizes open-source software and standard. APIs. Software built on the reference stacks can be turned into products.
Renesas
3. The R-Car Open Access (RoX) SDV platform supports pre-integrated operating systems and frameworks.
www.electronicdesign.com
Says here the "basic R-Car X5H includes up to 32 Arm Cortex-720AE" and we know were are compatible across Arm's product range.
Renesas previously collaborated with Hailo to offer combined solutions that pair the R-Car V4H SoC with Hailo-8 AI accelerators.
However, there isn't any publicly available information indicating that Renesas and Hailo have collaborated on the R-Car X5H, at least none that I've found as yet.
Chiplets Extend Automotive SoC AI and GPU Capability
Dec. 28, 2024
Renesas’ R-Car X5H SoC, which meets ASIL B/D, provides scalable automotive compute.
William G. Wong
https://www.electronicdesign.com/print/content/55252079
- Features of the R-Car X5H automotive system-on-chip family.
- How Renesas is taking advantage of chiplets.
The R-Car X5H family is a fifth-generation automotive system-on-chip (SoC) developed by Renesas that supports ASIL B/D capabilities as well as a neural processing unit (NPU). Built on the latest 3-nm chip technology, enhanced versions of the SoC come courtesy of chiplet technology. I talked with Cyril Clocher, Senior Director of the Automotive Product Line, about the details.
High-Performance Compute for Automotive Safety-Critical Apps
The basic R-Car X5H includes up to 32 Arm Cortex-720AE applications cores capable of delivering 1000K DMIPS of performance (Fig. 1). Real-time support is provided by half-a-dozen Arm Cortex-R52 cores with dual lockstep capability. These can deliver 60K DMIPS of performance while meeting ASIL B and ASIL D certification requirements.Renesas
1. The Renesas R-Car X5H includes 32 Arm Cortex-720AE applications cores, six Arm Cortex-R52 cores with lockstep support, an NPU, and a GPU.
There are general-purpose DSP cores, too, along with specialized accelerators such as the image signal processor (ISP) and dense-optical-flow (DOF) hardware accelerator (HWA) for handling multi-megapixel camera video streams.
The on-chip NPU can deliver up to 400 TOPS, while the on-chip GPU generates 4 TFLOPS of performance.
The chip includes an 8-port Ethernet switch, USB 2/3 ports, and PCI Express (PCIe) that supports Gen 4 and Gen 6. Also in the mix are an on-chip dedicated NPU and GPU. The GPU can drive a car’s display panel while the NPU handles artificial-intelligence and machine-learning (AI/ML) models.
Enhanced Automotive Chips Utilize UCIe
While the basic R-Car X5H monolithic chip is very impressive, it is designed to be enhanced using chiplets that employ Universal Chiplet Interconnect Express (UCIe) connectivity (Fig. 2). It can include up to two chiplets.Renesas
2. The R-Car X5H can be enhanced by including an NPU and GPU chiplet.
Renesas has two types of chiplets that can be included in enhanced versions of the R-Car SoC—again, an NPU and a GPU. These are designed to augment the functionality of the built-in NPU and GPU. The chiplet and on-chip NPU are able to run a separate set of AI/ML models. Likewise, the GPU can drive additional displays.
Building a Software-Defined Vehicle
The R-Car X5H family is destined for new automobiles including software-defined vehicles (SDVs). Thanks to the massive amount of computing power, the chip can handle everything from the advanced driver-assistance system (ADAS) to driving automation.Renesas’ R-Car Open Access (RoX) SDV platform helps get developers up to speed by simplifying their development chores (Fig. 3). It works with a variety of pre-integrated operating systems and frameworks, tying them into the Arm Cortex-A720AE and Cortex-R52 compute arrays. It utilizes open-source software and standard. APIs. Software built on the reference stacks can be turned into products.
Renesas
3. The R-Car Open Access (RoX) SDV platform supports pre-integrated operating systems and frameworks.
Chiplets Extend Automotive SoC AI and GPU Capability
Renesas’ R-Car X5H SoC, which meets ASIL B/D, provides scalable automotive compute.
Last edited:
SNN-Based Lightweight AI Accelerator (Akida™ Core):
1. Event-Based Processing for High Performance:
• Achieves high efficiency and optimized performance.
2. Ideal for Battery-Powered Applications:
• Designed for low-power consumption.
3. SDK Support for CNN-to-SNN Conversion:
• Enables seamless integration of existing AI models into SNN architecture.
Evaluation Board/SDK (Linux-Based):
• Purpose:
The evaluation board, running on Linux, allows developers to test and evaluate the performance of AI inference models implemented on the Akida™ Core in real-world applications.
• Key Features:
1. TensorFlow/Keras Integration:
• For dataset preparation and model training.
2. BrainChip MetaTF Framework
For model quantization and conversion from CNN to SNN.
3. Akida Runtime:
• For deploying models.
• Goal: Provides developers with a powerful and flexible platform to implement Akida™-based AI solutions.
Interesting, great post, It would be unbelievably huge for BRN (and holders) if we were supplying to Nintendo via Microchip.Morning All,
As we all know, the Nintendo Switch 2 is widely expected to launch in 2025. And I was just reading some of the latest rumours (best taken with a grain of salt by the way) suggesting the big reveal could happen as early as January 8, 2025!
If Nintendo does decide to make an announcement that soon, I certainly won't be complaining because it will finally put to bed years of speculation. Obviously there's a decent chance that our technology might be incorporated in the next-generation console on the basis of the information I've included below.
And if f we are incorporated, it would likely be alongside NVIDIA’s Tegra 239 processor. Being featured in a product from a globally renowned brand like Nintendo, alongside a technology giant like NVIDIA, would be nothing short of a dream come true - like hitting two major targets with one golden arrow!
The level of attention this would garner for BrainChip if our tech were to be incorporated in such a widely popular system is impossible to overstate IMO, especially if it enables capabilities previously unimaginable in gaming with features like gesture recognition, face recognition, voice recognition, and voice identification alongside benefits of low power consumption and longer battery life. Not only would it bring huge value to the user experience but it would also help us to showcase on a global scale the transformative power of our innovations.
Patience has been a crucial virtue in this process, given the lengthy product cycles involved in developing large-scale integration (LSI) systems. However, if this achievement comes to fruition, the payoff for our perseverance will be monumental.
As for the recent rise in our share price, it’s hard to pinpoint the exact cause. Is it the likelihood of our involvement in the soon to be released Nintendo Switch 2? The anticipation surrounding CES 2025 and potential reveals there? The strategic positioning of our intellectual property with Renesas? Or perhaps the credibility we’ve gained from recent announcements involving Airbus and the AFRL?
Whatever the reason, I believe the increasing share price is a sign that the market is starting to wake up to the potential of our stock and with the right announcements forthcomming, we could go absolutely gang-busters.
My opinion only.
View attachment 74814
View attachment 74816
View attachment 74815
Business and Other Risks | MegaChips Corporation
We aim at sustainable growth through profitability and growth opportunity.www.megachips.co.jp
Image Processing | MegaChips Corporation
We respond to various issues of customers including cost and development period with our integrated support leveraging foundries around the world.www.megachips.co.jp
With AKIDA technology, Nintendo could push the boundaries of what's possible in handheld gaming, creating a more powerful, efficient, and innovative gaming console. Latency, low power, enhanced gaming experiences etc.
Microchip obviously took a license with a use for AKIDA in mind. Let's hope its Nintendo.
4 years since the IP license... finally a product!!!"Best-in-class power efficiency", so they say! Whose NPU is this I wonder?
Says here the "basic R-Car X5H includes up to 32 Arm Cortex-720AE" and we know were are compatible across Arm's product range.
Renesas previously collaborated with Hailo to offer combined solutions that pair the R-Car V4H SoC with Hailo-8 AI accelerators.
However, there isn't any publicly available information indicating that Renesas and Hailo have collaborated on the R-Car X5H, at least none that I've found as yet.
View attachment 74837
Chiplets Extend Automotive SoC AI and GPU Capability
Dec. 28, 2024
Renesas’ R-Car X5H SoC, which meets ASIL B/D, provides scalable automotive compute.
William G. Wong
https://www.electronicdesign.com/print/content/55252079
- Features of the R-Car X5H automotive system-on-chip family.
- How Renesas is taking advantage of chiplets.
The R-Car X5H family is a fifth-generation automotive system-on-chip (SoC) developed by Renesas that supports ASIL B/D capabilities as well as a neural processing unit (NPU). Built on the latest 3-nm chip technology, enhanced versions of the SoC come courtesy of chiplet technology. I talked with Cyril Clocher, Senior Director of the Automotive Product Line, about the details.
High-Performance Compute for Automotive Safety-Critical Apps
The basic R-Car X5H includes up to 32 Arm Cortex-720AE applications cores capable of delivering 1000K DMIPS of performance (Fig. 1). Real-time support is provided by half-a-dozen Arm Cortex-R52 cores with dual lockstep capability. These can deliver 60K DMIPS of performance while meeting ASIL B and ASIL D certification requirements.
Renesas
View attachment 74834
1. The Renesas R-Car X5H includes 32 Arm Cortex-720AE applications cores, six Arm Cortex-R52 cores with lockstep support, an NPU, and a GPU.
There are general-purpose DSP cores, too, along with specialized accelerators such as the image signal processor (ISP) and dense-optical-flow (DOF) hardware accelerator (HWA) for handling multi-megapixel camera video streams.
The on-chip NPU can deliver up to 400 TOPS, while the on-chip GPU generates 4 TFLOPS of performance.
The chip includes an 8-port Ethernet switch, USB 2/3 ports, and PCI Express (PCIe) that supports Gen 4 and Gen 6. Also in the mix are an on-chip dedicated NPU and GPU. The GPU can drive a car’s display panel while the NPU handles artificial-intelligence and machine-learning (AI/ML) models.
Enhanced Automotive Chips Utilize UCIe
While the basic R-Car X5H monolithic chip is very impressive, it is designed to be enhanced using chiplets that employ Universal Chiplet Interconnect Express (UCIe) connectivity (Fig. 2). It can include up to two chiplets.
Renesas
2. The R-Car X5H can be enhanced by including an NPU and GPU chiplet.
Renesas has two types of chiplets that can be included in enhanced versions of the R-Car SoC—again, an NPU and a GPU. These are designed to augment the functionality of the built-in NPU and GPU. The chiplet and on-chip NPU are able to run a separate set of AI/ML models. Likewise, the GPU can drive additional displays.
Building a Software-Defined Vehicle
The R-Car X5H family is destined for new automobiles including software-defined vehicles (SDVs). Thanks to the massive amount of computing power, the chip can handle everything from the advanced driver-assistance system (ADAS) to driving automation.
Renesas’ R-Car Open Access (RoX) SDV platform helps get developers up to speed by simplifying their development chores (Fig. 3). It works with a variety of pre-integrated operating systems and frameworks, tying them into the Arm Cortex-A720AE and Cortex-R52 compute arrays. It utilizes open-source software and standard. APIs. Software built on the reference stacks can be turned into products.
Renesas
3. The R-Car Open Access (RoX) SDV platform supports pre-integrated operating systems and frameworks.
Chiplets Extend Automotive SoC AI and GPU Capability
Renesas’ R-Car X5H SoC, which meets ASIL B/D, provides scalable automotive compute.
Bravo
If ARM was an arm, BRN would be its biceps💪!
As mentioned, I'm not sure it's going to include our technology, but I am very hopeful. Bearing in mind, if it does, Renesas has announced that the R-Car X5H System-on-Chip (SoC) will only be available for sampling to select automotive customers in the first half of 2025, and then mass production would be scheduled for the second half of 2027.
Similar threads
