Wild_C
@wild-c.bsky.social
Mostly AMD, Intel, and NVIDIA stuff
No sources or exclusive info
No sources or exclusive info
Reposted by Wild_C
Rubin CPX looks very similar to GB202, at least in the image Nvidia released. Could be very well a full GPU, with raster engines, PCI-Expess and display outputs. While unlikely, it might be how the RTX 6090 will look like.
September 11, 2025 at 10:25 AM
Rubin CPX looks very similar to GB202, at least in the image Nvidia released. Could be very well a full GPU, with raster engines, PCI-Expess and display outputs. While unlikely, it might be how the RTX 6090 will look like.
Reposted by Wild_C
July 16, 2025 at 8:26 AM
Reposted by Wild_C
Intel's newer Emerald Rapids improves L3 latency compared to Sapphire Rapids, at least when one core is able to allocate a similar amount of L3 capacity. It's still high at ~105 core cycles, but better than ~125 cycles from the last generation.
July 11, 2025 at 10:36 PM
Intel's newer Emerald Rapids improves L3 latency compared to Sapphire Rapids, at least when one core is able to allocate a similar amount of L3 capacity. It's still high at ~105 core cycles, but better than ~125 cycles from the last generation.
Reposted by Wild_C
when you open a service you've been using for a decade only to find it out it caught the virus
July 5, 2025 at 5:52 PM
when you open a service you've been using for a decade only to find it out it caught the virus
Reposted by Wild_C
oh and fuck Future, PLC. they are the ones that killed AnandTech as well.
bye laptopmag :/ so many of the good ones got their start with them.
oh, and fuck corp publishing.
www.theverge.com/news/695969/...
oh, and fuck corp publishing.
www.theverge.com/news/695969/...
Laptop Mag is shutting down
The end of an era.
www.theverge.com
July 1, 2025 at 6:48 PM
oh and fuck Future, PLC. they are the ones that killed AnandTech as well.
Reposted by Wild_C
Quaternions - Freya Holmer | NGJ2025
YouTube video by Nordic Game Jam
www.youtube.com
June 3, 2025 at 8:39 PM
Reposted by Wild_C
AMD Navi 44 GPU
- 29.7 Billion Transistors
- 199 mm² Die Size
- 29.7 Billion Transistors
- 199 mm² Die Size
June 4, 2025 at 2:12 PM
AMD Navi 44 GPU
- 29.7 Billion Transistors
- 199 mm² Die Size
- 29.7 Billion Transistors
- 199 mm² Die Size
Reposted by Wild_C
An Intel slide with #NovaLakeU, #NovaLakeS, #WildcatLake, P-Only #BartlettLake:
www.intel.com/content/www/...
www.intel.com/content/www/...
May 14, 2025 at 3:57 PM
An Intel slide with #NovaLakeU, #NovaLakeS, #WildcatLake, P-Only #BartlettLake:
www.intel.com/content/www/...
www.intel.com/content/www/...
Reposted by Wild_C
Just released by @fritzchensfritz.bsky.social
Arrow Lake-S die shots projected on the full package.
Full resolution: www.flickr.com/photos/13056...
Arrow Lake-S die shots projected on the full package.
Full resolution: www.flickr.com/photos/13056...
May 14, 2025 at 6:14 PM
Just released by @fritzchensfritz.bsky.social
Arrow Lake-S die shots projected on the full package.
Full resolution: www.flickr.com/photos/13056...
Arrow Lake-S die shots projected on the full package.
Full resolution: www.flickr.com/photos/13056...
Reposted by Wild_C
this isn't clickbait, watch it before nintendo gets it taken down lol www.youtube.com/watch?v=3pr_...
This is Nintendo Switch 2's CPU!
YouTube video by Geekerwan
www.youtube.com
May 7, 2025 at 7:36 PM
this isn't clickbait, watch it before nintendo gets it taken down lol www.youtube.com/watch?v=3pr_...
Venice Classic SP8 → 8 CCD * 12 = 96 cores
Venice Dense SP7 → 8 CCD * 32 = 256 cores
?
🤔
Could more closely mirror Intel's 2 platform strategy, especially if SP8 supports 2P configurations
Venice Dense SP7 → 8 CCD * 32 = 256 cores
?
🤔
Could more closely mirror Intel's 2 platform strategy, especially if SP8 supports 2P configurations
May 6, 2025 at 10:47 PM
Venice Classic SP8 → 8 CCD * 12 = 96 cores
Venice Dense SP7 → 8 CCD * 32 = 256 cores
?
🤔
Could more closely mirror Intel's 2 platform strategy, especially if SP8 supports 2P configurations
Venice Dense SP7 → 8 CCD * 32 = 256 cores
?
🤔
Could more closely mirror Intel's 2 platform strategy, especially if SP8 supports 2P configurations
Reposted by Wild_C
April 29, 2025 at 11:50 AM
Reposted by Wild_C
Reposted by Wild_C
AMD had a separate Shader Array subdivision within Shader Engines even in the original GCN architecture. Interesting that it never mattered until RDNA added a L1 cache to the Shader Arrays and had multiple SAs per SE
April 13, 2025 at 1:33 AM
AMD had a separate Shader Array subdivision within Shader Engines even in the original GCN architecture. Interesting that it never mattered until RDNA added a L1 cache to the Shader Arrays and had multiple SAs per SE
Reposted by Wild_C
I recently had the honor of interviewing Zen’s chief architect Mike Clark! I tried to fit in as many microarchitecture questions as I could, including x64 vs ARM ISA power efficiency, 4k vs larger page sizes, 64-byte cache lines, scatter/gather and more:
www.computerenhance.com/p/an-intervi...
www.computerenhance.com/p/an-intervi...
An Interview with Zen Chief Architect Mike Clark
Zen is one of the most important microarchitectures in the history of the x86 ecosystem.
www.computerenhance.com
March 24, 2025 at 6:51 PM
I recently had the honor of interviewing Zen’s chief architect Mike Clark! I tried to fit in as many microarchitecture questions as I could, including x64 vs ARM ISA power efficiency, 4k vs larger page sizes, 64-byte cache lines, scatter/gather and more:
www.computerenhance.com/p/an-intervi...
www.computerenhance.com/p/an-intervi...
Reposted by Wild_C
Good news: according to ark.intel.com, every #Intel #GraniteRapids-based #Xeon6 6900P, 6700P, 6500P SKU supports #AVX512 with dual 512bFMA, even the #GraniteRidgeD ones too
www.intel.com/content/www/...
www.intel.com/content/www/...
February 25, 2025 at 10:50 AM
Good news: according to ark.intel.com, every #Intel #GraniteRapids-based #Xeon6 6900P, 6700P, 6500P SKU supports #AVX512 with dual 512bFMA, even the #GraniteRidgeD ones too
www.intel.com/content/www/...
www.intel.com/content/www/...
Re: Nova Lake rumors
In before 8P16E dies get canned in favour of double 4P8E or 6P8E compute tiles for Nova Lake-S
I just can't take 2x8P16E at face value after the cancellation of 8P32E Arrow Lake
It's not like a 12P16E4e flagship with Big LLC would be *that* uncompetitive with Medusa, right?
In before 8P16E dies get canned in favour of double 4P8E or 6P8E compute tiles for Nova Lake-S
I just can't take 2x8P16E at face value after the cancellation of 8P32E Arrow Lake
It's not like a 12P16E4e flagship with Big LLC would be *that* uncompetitive with Medusa, right?
February 8, 2025 at 12:19 PM
Re: Nova Lake rumors
In before 8P16E dies get canned in favour of double 4P8E or 6P8E compute tiles for Nova Lake-S
I just can't take 2x8P16E at face value after the cancellation of 8P32E Arrow Lake
It's not like a 12P16E4e flagship with Big LLC would be *that* uncompetitive with Medusa, right?
In before 8P16E dies get canned in favour of double 4P8E or 6P8E compute tiles for Nova Lake-S
I just can't take 2x8P16E at face value after the cancellation of 8P32E Arrow Lake
It's not like a 12P16E4e flagship with Big LLC would be *that* uncompetitive with Medusa, right?
Reposted by Wild_C
Does anyone know why Apple did not release any chip pictures / die shots for the M4 series, like they usually do? I know there's a @techinsightsinc.bsky.social M4 die shot floating around, but I always enjoyed the images Apple released directly. Maybe someone has contacts at Apple?
February 3, 2025 at 12:43 PM
Does anyone know why Apple did not release any chip pictures / die shots for the M4 series, like they usually do? I know there's a @techinsightsinc.bsky.social M4 die shot floating around, but I always enjoyed the images Apple released directly. Maybe someone has contacts at Apple?
Reposted by Wild_C
Visualizing the massive size difference between AMD's Zen 5 CCD & Nvidia's GB202.
January 29, 2025 at 12:20 PM
Visualizing the massive size difference between AMD's Zen 5 CCD & Nvidia's GB202.
Reposted by Wild_C
Here's a quick look at Nvidia's GB203, image from "ASUS Tony". Spec wise basically 1/2 GB202, but physically a different design and not just half of a GB202.
January 29, 2025 at 5:33 PM
Here's a quick look at Nvidia's GB203, image from "ASUS Tony". Spec wise basically 1/2 GB202, but physically a different design and not just half of a GB202.
Reposted by Wild_C
Mmmmmnnnn, data.... thephd.dev/the-big-arra...
Results! - The Big Array Size Survey for C
Happy New Year! It is time report the results of the Array Size Operator survey and answer some comments people have been asking for!
thephd.dev
January 24, 2025 at 4:05 AM
Mmmmmnnnn, data.... thephd.dev/the-big-arra...
Reposted by Wild_C
Is the fact that Samsung is only using the Snapdragon 8 Elite for the Galaxy S25 series a sign of strength for Qualcomm or a sign of weakness for Samsung's SoC team and Foundry? Or does it just not matter?
January 22, 2025 at 7:12 PM
Is the fact that Samsung is only using the Snapdragon 8 Elite for the Galaxy S25 series a sign of strength for Qualcomm or a sign of weakness for Samsung's SoC team and Foundry? Or does it just not matter?
Reposted by Wild_C
Transistor count and die size for GB202, GB203 and GB205 aka Blackwell. Those and the predecessors are all manufactured in TSMC 4N.
Source: www.hardwareluxx.de/index.php/ar...
Source: www.hardwareluxx.de/index.php/ar...
January 15, 2025 at 4:02 PM
Transistor count and die size for GB202, GB203 and GB205 aka Blackwell. Those and the predecessors are all manufactured in TSMC 4N.
Source: www.hardwareluxx.de/index.php/ar...
Source: www.hardwareluxx.de/index.php/ar...
Reposted by Wild_C
"380 Ray tracing TFLOPS" will be on the list of things that drive me to be committed
January 7, 2025 at 3:45 PM
"380 Ray tracing TFLOPS" will be on the list of things that drive me to be committed
Is GB10 the high-end NVIDIA Laptop SoC?
Because otherwise why would it have an asymmetric CPU layout?
Looks like 2 clusters with 5x Cortex-X + 5x Cortex-A each
It also seems to have all the I/O you'd want for a Laptop
"1000 FP4 TOPS" (24TPCs?) would correspond GB205 (5070Ti Laptop) performance
Because otherwise why would it have an asymmetric CPU layout?
Looks like 2 clusters with 5x Cortex-X + 5x Cortex-A each
It also seems to have all the I/O you'd want for a Laptop
"1000 FP4 TOPS" (24TPCs?) would correspond GB205 (5070Ti Laptop) performance
January 7, 2025 at 4:33 AM
Is GB10 the high-end NVIDIA Laptop SoC?
Because otherwise why would it have an asymmetric CPU layout?
Looks like 2 clusters with 5x Cortex-X + 5x Cortex-A each
It also seems to have all the I/O you'd want for a Laptop
"1000 FP4 TOPS" (24TPCs?) would correspond GB205 (5070Ti Laptop) performance
Because otherwise why would it have an asymmetric CPU layout?
Looks like 2 clusters with 5x Cortex-X + 5x Cortex-A each
It also seems to have all the I/O you'd want for a Laptop
"1000 FP4 TOPS" (24TPCs?) would correspond GB205 (5070Ti Laptop) performance