Matt's Homepage

More eyes are nVidia’s GH200 Grace Superchip. The GH200 Superchip is the combination of a Grace CPU and a Hopper-based H200 GPU. While the results aren’t definitive, they should raise eyebrows.

In 39 individual Linux-based benchmark tests, Grace (the CPU side) beat the AMD Threadripper 7980X in 17 tests and the 7995WX in 15. It even stacks up well against Intel Sapphire Rapids.

Sapphire Rapids and Threadripper enjoy many advantages. Far more apps are optimized for x86 than for Arm. Threadripper has much more aggressive clock speeds than the efficiency-focused Grace chip and far more L3 cache (7980X has more than double, and the 7995WX more than triple).

But raw performance may not be the only consideration. There is speculation that Grace Hopper is more energy efficient – but there is no real data on TDP outside the whole package requirement of 500w. Also, for tasks that are more GPU bound than CPU bound, the combination may provide higher effective processing power than a faster CPU paired with a discrete GPU. Time will tell.

It shows that nVidia’s Grace entry is not to be ignored. Paired with the Hopper GPUs, it might offer a very viable alternative to x86 stacks – if your software can run on Arm.

Links:

• https://www.phoronix.com/review/nvidia-gh200-amd-threadripper
• https://www.tomshardware.com/pc-components/cpus/nvidia-grace-falls-short-of-threadripper-7000-in-head-to-head-linux-benchmarks

ZZAZZGlitch has successfully reverse-engineered a Game Boy Advance game’s data solely from the sound made when a GBA game experiences a hard crash. The per-game crash ‘songs’ that happen when a GBA game crashes actually contains the entire cartridge’s ROM data and every sound in the game played back in raw audio in sequential order. In theory, with the correct tools and know-how, any GBA game should be recoverable from recording that audio.

ZZAZZGlitch shows us how in his video. Wow. He even made the source code is available on his personal site, labeled “gbacrashsound_dumper.zip”. It still took a LOT of hacking and manual fix-ups; but he got a bootable game in the end.

Reminds me of the guy that tried to reconstruct the Yars Revenge source from the explosions shown onscreen.

There’s been some trouble lately in which free VPN services have been collecting and selling your data. Others have had major leaks or hacks (such as the new TunnelVision attack). So why not set up your own VPN and avoid those issues?

A few important reminders. VPN’s do not make you anonymous. They only create a secure pipe between you and that server. From that point on, your traffic can be collected and used – and many free VPN services do exactly that. Anonymity comes only if you use things like the TOR network.

But instead of paying a VPN service fee or potentially having your data collected and sold, you might set up your own VPN server on a Rasberry Pi.

1. Create an account on a cloud hosting provider like DigitalOcean
2. Download Algo VPN on your local computer, unzip it
3. Install the dependencies with the command lines on this page
4. Run the installation wizard
5. Double click on the configuration profiles in the configs directory

It’s important to note that there are some limitations. This setup is good if you need a secure connection from where you are to the location of the server (ex: You’re in China and need access to US services that are blocked). Again, this doesn’t make you anonymous as your data exits the VPN and becomes public again.

Paid VPN services also often offer servers in different countries so you can spoof being in specific countries. This will not do that unless you have paid for hosting in those countries.

Articles:

• https://techcrunch.com/2017/04/09/how-i-made-my-own-vpn-server-in-15-minutes/

Stacksmashing demonstrates that the communication between the CPU and TPM is unencrypted and can be snooped by attaching wires to the traces between them. This is not new, but now has all the source/board design to make it easier – on old systems with a long known security flaw of exposed traces.

This isn’t really new info. It requires numerous things to be right: physical access to the device and non-integrated TPM with a design flaw. Modern CPUs don’t have this easily exploitable design given the TPM is integrated into the die now. This was somewhat common in early days. At one point just connecting a firewire cable into a Mac let you read the encryption keys out of memory from a sleeping or running Apple.

Additionally, Bitlocker using TPM without pin was cracked years ago using fairly common electronic components. Any secure Bitlocker deployment has long been understood to be using TPM and a pin.

A reminder that security is only as good as its weakest link

Links:

• https://www.tomshardware.com/pc-components/cpus/youtuber-breaks-bitlocker-encryption-in-less-than-43-seconds-with-sub-dollar10-raspberry-pi-pico
• https://www.zdnet.com/article/new-bitlocker-attack-puts-laptops-storing-sensitive-data-at-risk/
• https://github.com/stacksmashing/pico-tpmsniffer

It’s long been known that the graphical explosions and safe zone graphical glitchy area in Yars Revenge was the game binary code. Retro Game Mechanics Explained wondered if it was possible to reverse-engineer what the code was from this display.

He does an AMAZING job analyzing and dissecting the graphical patterns to determine not only how it works, but what the underlying code might have been.

It’s a wonderful bit of reverse engineering and definitely worth a watch.