Google Tensor Processor: A Brief History & The Road To 3nm
Here’s everything you need to know about Google’s Tensor processor, including its history, future iterations (G3 and G4), what it can do, and how Google’s improving it…
Like Apple, Google likes to build its own custom CPUs – or SoCs. But unlike Apple, Google hasn’t yet managed to match Qualcomm where it counts: performance.
Tensor is all about AI and machine learning, making your Pixel phone smarter and more useful.
And in many ways, Google’s Tensor project is a resounding success in this regard.
Google’s Pixel phones are some of the smartest and most useful devices on the market, despite Google’s never-ending QC issues.
But what does the future hold for Google’s Tensor CPU? Read on, because we’re about to cover all of the following stuff:
- Current and past iterations of Google’s Tensor platform
- The Pixel 8 series Tensor G3 CPU
- The Pixel 9 Tensor G4 CPU
- Performance metrics versus Apple’s A16 / A17 and Snapdragon 8 GEN 2
- The future of Tensor
Let’s dig in…
A Brief History of Google’s Tensor Processor
Google’s journey into crafting its own system-on-chip (SoC) kicked off in April 2016, post-launching their inaugural Pixel smartphone.
Sundar Pichai and Rick Osterloh, the big guns at Google, knew it was a long game.
Fast forward to 2017, Google’s hardware division is buzzing. A team of 76 semiconductor aficionados, AI and ML specialists, are all hands on deck, working on the chip.
The Pixel series starts flaunting custom-designed co-processors. The Pixel Visual Core and the Pixel Neural Core make their debuts.
By April 2020, the buzzword is “Whitechapel”. Google’s custom ARM-based processor is in the works, aimed at Pixel and Chromebook devices.
Pichai’s excitement over Google’s “deeper investments” in hardware in an October investor call fuels speculations about Whitechapel.
Come 2020, the Pixel 5 drops the Neural Core. Why? The Snapdragon 765G SoC had it covered, hitting the camera performance targets Google was aiming for.
And in April 2021, the word is out.
Whitechapel is set to power Google’s upcoming Pixel smartphones.
August rolls in, and Google pulls the curtain on Tensor, as a sneak peek into the Pixel 6 and Pixel 6 Pro smartphones.
It’s a shift from the Qualcomm Snapdragon chips, marking 2021’s Pixel 5a as the last of its kind.
Pichai hints at more off-the-shelf solutions for Pixel phones, thanks to the development of Tensor and the Pixel 6.
But, September 2022 brings some blues. A Tensor-powered successor to the Pixelbook laptop, slated for a 2023 release, gets the axe due to cost-cutting.
“Tensor” is a nod to Google’s TensorFlow and Tensor Processing Unit techs.
Developed by the Google Silicon team and the Google Research division, it’s a brainchild of Phil Carmack and Monika Gupta.
Tensor’s design is a break from the norm. It packs two large cores, two medium, and four small ones, a rare combo for octa-core SoCs.
Carmack spills that it’s all about keeping Tensor efficient during intense workloads, managing co-processors by running both large cores simultaneously at a low frequency.
Performance metrics were low compared to Apple and Qualcomm’s chips, but this wasn’t the point.
Tensor’s performance isn’t about synthetic benchmarks, according to Google
Tensor is about the ML capabilities it unlocks—advanced speech recognition, real-time language translation, unblurring photographs, and HDR-like processing for videos, frame by frame.
Tensor Capabilities & Features – It’s Main USPs Unpacked
- Enhanced User Experience:
- The chip enables more personalized and intuitive user experiences, with phones adapting and becoming more helpful over time.
- The AI and ML capabilities allow Pixel phones to understand user context, preferences, and unique needs.
- Photography Advancements:
- Google Tensor aids in capturing better photos by understanding and adjusting focus and brightness according to the subject.
- Features like Face Unblur and Magic Eraser allow users to rectify blurry faces and remove unwanted items from pictures without losing background details.
- Communication Efficiency:
- It facilitates faster communication through features like Live Caption and Live Translate, translating languages in real-time, either speech-to-text or directly to audio.
- Power Efficiency and Data Protection:
- Despite running advanced ML models, Google Tensor consumes less power compared to previous Pixel phones.
- It includes a separate core for sensitive tasks and controls to run in an isolated environment, making it resilient to attacks.
- The Tensor Security core, combined with the next-gen Titan M2™ co-processor, adds an additional layer of protection for personal information.
- Adaptive Learning and Suggestions:
- Google Tensor helps Pixel phones learn user behaviors and preferences, providing relevant information and suggestions when needed.
- The Pixel’s always-on display, powered by Google Tensor, keeps you informed about appointments and detected songs through Now Playing song detection.
The First Google Tensor Processors
Out of the gates, Google’s first Tensor processor did not blow the doors off the competition. But it did pack in plenty of smarts that Apple and Qualcomm’s lacked.
So, while the performance was a bit iffy, there were plenty of “extras” to get excited about.
Here’s how Google’s first ever Tensor processor, dubbed “Whitechapel”, compared to its second-generation Tensor G2 processor.
Google Tensor G1 vs Google Tensor G2
- Original: October 19, 2021
- G2: October 6, 2022
Model Number & Codename:
- Original: GS101 (Whitechapel)
- G2: GS201 (Cloudripper)
Both chips are made by Samsung, using its 5 nm fabrication process.
- Original: It’s an octa-core beast, featuring 2.8 GHz Cortex-X1, 2.25 GHz Cortex-A76, and 1.8 GHz Cortex-A55.
- G2: The successor ups the ante with a 2.85 GHz Cortex-X1, 2.35 GHz Cortex-A78, and retains the 1.8 GHz Cortex-A55.
TrustZone with Trusty OS is the guardian angel for both, ensuring top-notch security.
- Original: Mali-G78 MP20 operates at 848 MHz.
- G2: Enter Mali-G710 MP7. The frequency? It’s still under wraps!
LPDDR5 is the common thread, ensuring swift operations and multitasking.
UFS 3.1 is the storage type, offering high-speed read and write capabilities for both.
- Original: It’s equipped with an Exynos 5123 modem.
- G2: The modem gets a boost with Exynos 5300.
Wireless & Navigation:
Wi-Fi 6 and Wi-Fi 6E, Bluetooth 5.2, and Dual-band GNSS are constants, ensuring seamless connectivity and precise navigation.
The edgeTPU is the brain behind both, handling image signal processing with finesse.
Tensor G2 Versus The Competition
|Feature||Google Tensor G2||Apple A16 Bionic||SD 8+ Gen 1||Exynos 2200|
|CPU||2x Arm Cortex-X1 (2.85GHz)||2x Everest (3.46GHz)||1x Cortex-X2 (3.2GHz)||1x Cortex-X2 (2.8GHz)|
|2x Arm Cortex-A78 (2.35GHz)||4x Sawtooth (2.02GHz)||3x Cortex-A710 (2.75GHz)||3x Cortex-A710 (2.52GHz)|
|4x Arm Cortex-A55 (1.80GHz)||4x Cortex-A510 (2.0GHz)||4x Cortex-A510 (1.82GHz)|
|GPU||Arm Mali-G710 MP7||Apple 5-core GPU||Adreno 730||Xclipse 920|
|Caches||4MB shared L3||24MB system cache||6MB shared L3||Unknown|
|8MB system level||4MB system level|
|Machine Learning||Next-gen Tensor Processing Unit||16-core Neural Engine||Hexagon||Dual-core NPU|
|Media Decode||H.264, H.265, VP9, AV1||H.264, H.265, VP9||H.264, H.265, VP9||H.264, H.265, VP9, AV1|
|Modem||4G LTE, 5G sub-6Ghz and mmWave||4G LTE, 5G sub-6Ghz and mmWave||4G LTE, 5G sub-6Ghz and mmWave||4G LTE, 5G sub-6Ghz and mmWave|
|Process||Samsung 5nm (5LPE?)||TSMC N4||TSMC N4||Samsung 4LPE|
Tensor G2’s Reception
Performance has never been Tensor’s strong suit, not on the first iteration nor the G2.
But as Google constantly likes to point out: Tensor is NOT about benchmarks.
And reviewers and critics seemed to understand this when they got their hands on the Pixel 7 and Pixel 7 Pro.
Here’s some choice comments made about the first iteration of Google’s Tensor processor inside the Pixel 6 and Pixel 6 Pro:
- Philip Michaels from Tom’s Guide was all in, giving a nod to the Pixel 6 and Pixel 6 Pro’s Tensor-driven features and video enhancements. And guess what? Marques Brownlee and Wired’s Julian Chokkattu were on the same page!
- But it doesn’t stop there. Lily Hay Newman, also from Wired, spotlighted the chip’s security capabilities. She didn’t hold back, calling them Tensor’s top selling point!
- CNN Underscored’s Jacob Krol didn’t shy away either, stating Tensor brought “some of the most fluid and fastest performance” to the smartphone game. However, not everyone was sold. Android Authority’s Jimmy Westenberg seemed to be on the fence.
- Here’s the kicker. Ryne Hager from Android Police felt the chip did the job for the everyday user but threw a curveball. He wished for more years of Android updates from Google, especially since they’ve broken free from Qualcomm’s chains.
- TechRadar’s James Peckham didn’t mince words, labeling Tensor a “standout feature.” However, his colleague, David Lumb, threw in a twist, describing the chip’s performance as “strong but not class-leading.”
I tested the Pixel 6 Pro and the Pixel 6. I also used the Pro model as my daily driver until, well… things took a turn for the worse.
Tensor G3 and Tensor G4
Kamila Wojciechowska, the leaker who’s been our guide to the Pixel universe, is back with the inside scoop on Tensor G3, codenamed Zuma! And it’s all about leveling up. We’re talking modern CPUs, a leap to ARMv9 cores, and a goodbye to being two generations behind!
Here’s the lowdown on Tensor G3:
- Cores: It’s rocking a 1+4+4 architecture, a shift from the usual 2+2+4 setup. We’ve got 1x Cortex-X3, 4x Cortex-A715, and 4x Cortex-A510, all revved up with higher frequencies!
- GPU: Google’s rolling with the Mali-G715, possibly the 10-core Immortalis variant!
- Manufacturing Node: It’s all about the 3nm process.
- Storage: Speed is the name of the game with UFS 4.0.
Here’s a quick snapshot of everything else currently known about the Tensor G3:
- 64-bit Only! The Pixel 8 is breaking the mold, running only 64-bit code, potentially leaving some older apps in the dust. And it’s not just about the Pixel 8; the Pixel 7 and 7 Pro are technically on the same boat, capable of running 32-bit apps but offering 64-bit support only.
- Connectivity & Graphics: Rumor has it, we’re sticking with the Exynos Modem 5300, and Google’s betting big on the AV1 encoding, leading the charge in the video codec revolution!
- Hot or Not? The first Tensor and the Tensor G2 had their share of thermal issues. The big question is, can Google keep the Pixel 8 cooler than its Snapdragon and Apple silicon counterparts?
What’s Next? The Tensor G3 is set to power the Google Pixel 8 and Pixel 8 Pro, eyeing a fall 2023 launch. And if the rumors hold, we might see it in more devices in the Pixel lineup, including a potential Pixel 8a, Pixel Tablet, and an updated Pixel Fold.
But here’s where it gets spicy! The Information dropped a bombshell in July 2023. Google hit the brakes on the development of Tensor G4, aka “Redondo,” slated for a 2024 release. Why? The Google Silicon team missed a crucial 2022 deadline for kicking off trial production.
Tensor G5 Moving To 3nm Process
But wait, there’s more! Google wasn’t about to sit still. They shifted gears and jumped straight into the development of Tensor G5, giving it the codename “Laguna.”
And here’s the twist: it’s being designed fully in-house, leaving Samsung in the rearview mirror and partnering with TSMC for manufacturing.
And the cherry on top? It’s being built on TSMC’s groundbreaking 3 nm process which is the same process it used to make Apple’s new A17 CPU.