Graphics Cards - Page 118

Intel is back again with another video detailing its Intel Arc A750 graphics card, which has been benchmarked in close to 50 games with both DX12 and Vulkan API-based games.

In a new video from Intel, we have Ryan Shrout and Tom Peterson benchmarking their lives away with the Arc A750 Limited Edition graphics card in 49 games at both 1080p and 1440p resolutions. Intel versed its own Arc A750 graphics card against NVIDIA's mid-range GeForce RTX 3060, where it beat the RTX 3060 by 3-5% on average.

Ryan explains on the official Intel website: "For games with dedicated benchmarks like Dirt 5 and Hitman 3, we used their benchmark modes. Other games without built-in benchmarks were run using repeatable scenarios, though other testers might come up with different results. And you'll see in our results disclosure that we had two different Intel labs with slightly different configurations contribute to this collection of data, but all measurements for both Intel Arc and competitive products on a per game basis were performed by the same labs. We're confident that the combined data tells the story of the type of performance you can expect when playing some of your favorite modern games".

NVIDIA has been playing with fire before the launch of its next-gen Ada Lovelace GPU architecture, which will power the new GeForce RTX 40 series graphics cards coming later this year.

But now we're hearing fresh news from Moore's Law is Dead, who reached out to his industry sources to find out what is going on with the current situation of warehouses filled with current-gen and even older-gen Ampere and Turing-based graphics cards.

MLID says that his sources have said that AIBs are being helped by NVIDIA to clear their reserve stockpiles of GA102 (GeForce RTX 3090 Ti, GeForce RTX 3090, GeForce RTX 3080 Ti, GeForce RTX 3080 12GB, GeForce RTX 3080). His sources state that this was "the compromise" of the "NVIDIA AIB Revolt" which is when AIBs told NVIDIA to "go pound sand" over their warehouses of older-gen GPUs before the next-gen Ada Lovelace cards arrive.

NVIDIA's next-gen GeForce RTX 4090 might get all the rumor limelight, but the GeForce RTX 4080 and GeForce RTX 4070 are going to be the real big sellers for gamers, and now we have the very latest rumors to continue driving up that hype train.

The next-gen GeForce RTX 4070 is rumored to have higher GPU clocks than the flagship GeForce RTX 4090, with leaker "kopite7kimi" tweeting last week that the RTX 4070 spec had been updated. NVIDIA's third-most powerful Ada Lovelace GPU in its upcoming GeForce RTX 40 series family will use the PG141-SKU331 GPU, with 7680 CUDA cores, and 12GB of GDDR6X memory clocked at 21Gbps which should provide 504GB/sec of memory bandwidth

The last we heard on the GeForce RTX 4070 and its memory system was that it would have 10GB of GDDR6X at 18Gbps, so we're looking at a decent upgrade: 12GB GDDR6X memory clocked at 21Gbps. Kopite7kimi also says that we should expect GPU boost clocks to be over 2800MHz+ which should result in custom AIB models of the GeForce RTX 4070 to hopefully breach 3000MHz+ which would be a very, very cool thing to see from NVIDIA.

UPDATE: Intel reached out to us to clarify some details, saying "Intel showed a Blender Cycles rendering demo at SIGGRAPH with Intel Arc graphics. Multi-GPU rendering support for Intel Arc and Intel Arc Pro graphics cards through oneAPI is supported starting in Blender 3.3. Intel Arc graphics does not support multi-GPU for gaming."

We learned something quite interesting at SIGGRAPH 2022 today: Intel is finalizing their oneAPi software for multi-GPU support. It turns out that it was only due to the inability to find the right chassis that prevented Intel from showing off a multi-GPU solution on the show floor this week.

Support for a multi-GPU solution could allow Intel to narrow the gap somewhat against NVIDIA and AMD on their entry-level cards for Arc discrete GPUs that are set to debut shortly, as we just reported.

Today, while wandering around the halls of SIGGRAPH 2022 in Vancouver, we caught up with someone from Intel who told us that discrete Arc graphics cards would launch a lot sooner than the end of the year.

Although we just reported yesterday that Intel formally announced product shipments before the end of the year, we were able to grease some wheels here at SIGGRAPH 2022.

Although our source would not give the exact date, they could confirm that the current plan would see product availability by the end of summer.

NVIDIA has released its new GeForce Game Ready 516.94 WHQL drivers, which provide the best day-0 gaming experience for Marvel's Spider-Man Remastered.

The new NVIDIA GeForce Game Ready 516.94 WHQL drivers will be ready for Marvel's Spider-Man Remastered, which packs NVIDIA technologies like NVIDIA DLSS, NVIDIA DLAA, NVIDIA HBAO+ and beefed-up ray tracing effects. The new GeForce Game Ready 516.94 WHQL drivers also support Madden NFL 23 and the beta of SUPER PEOPLE.

There's also a boat load of support for newly validated G-SYNC Compatible displays, including support for Corsair's new XENEON 32UHD144 gaming monitor which rocks out with a native 4K resolution and super-smooth 144Hz refresh rate. NVIDIA is supporting 18 newly validated G-SYNC Compatible displays in total, from ASUS, AOC, LG, and Philips.

NVIDIA is taking care of its staff with pay increases instead of lay offs during some hard financial times, not just for the company, but for the US economy and global economies.

In a new email picked up by Business Insider, NVIDIA is sticking to its guns with NVIDIA founder and CEO Jensen Huang keeping the can of whoop ass closed when it comes to hurting NVIDIA staffers during these hard times. Jensen explained in the email: "So what does this [THE REVENUE DROP] mean for us? Do we have a layoff? No. Instead, we have given raises to take care of your families as all of you are facing sky-high inflation".

He continued: "We will exercise extreme collaboration, a hallmark of our culture, finding every opportunity to leverage and reuse. We will find and eliminate all wasted time, process, and material. Take this opportunity to make NVIDIA even faster, leaner, and agile. So let's turn our alertness and agility to maximum, engines full-throttle, and fly through the challenges ahead while continuing to do our impactful work".

Chinese company Biren Technology has just unveiled its new GPGPU architecture for next-gen computing at its recent Biren Explore Summit 2022 event.

Biren's new BR100 GPU is built on the 7nm process node at TSMC using their TSMC 2.5D CoWoS packaging technology, featuring 77 billion transistors, 300MB of on-chip cache, and 64GB of super-fast HBM2e memory that pumps up to 2.3TB/sec of memory bandwidth. We have up to 256 TFLOPs of FP32 compute performance, with the GPU supporting both PCIe 5.0 and CXL interfaces.

The new BR100 GPGPU is based on Biren's own BiLiren architecture, but with the BR100 the company is also introducing the whole family of OAM-compatible cards, as well as the PCIe-based BR104 GPU. Biren is also unveiling their own software platform alongside the BR100 GPGPU launch, which is called BIRENSUPA, with support for mainstream deep learning frameworks like Baidu's PaddlePaddle.

NVIDIA's next-gen GeForce RTX 4080 graphics card is rumored to use up to 320W of power, which is down considerably from the previously rumored 420W of power.

The news on NVIDIA's next-gen Ada Lovelace GPU-powered GeForce RTX 4080 is from leaker "kopite7kimi" who tweeted: "We can expect RTX 4080 with 320W and RTX 4070 with 285W". The previous rumor for the RTX 4080 is that it would use 420W, so the drop to 320W is a lofty 100W... and that's a great thing.

NVIDIA has an additional 100W of power it can use for some monster overclocking on custom GeForce RTX 4080 graphics cards, something kopite7kimi addressed in a follow-up tweet, by saying: "Not much. The original power consumption limit is too loose which means great overclocking potential".

Intel is continuing its "marketing" for their upcoming Arc GPUs with something that leaker Moore's Law is Dead talked about: the Arc desktop GPU story. There's not much new here, but it's interesting that it's all playing out like this.

You can check out the "story" on Intel Arc GPUs on the official Intel website, where we find out that ex-PC Perspective owner and reviewer Ryan Shrout has a major hand in Arc. Shrout seems to be steering the Arc GPU ship, as the Intel website itself says that "Intel Gaming Access met with Ryan Shrout, Senior Director of Graphics and HPC Marketing at Intel".

Intel explains that "when it came to the creation of Intel Arc, Ryan and Intel's engineers had plenty of graphics experience to call on". Interesting, it seems that Ryan was integral to the entire Arc GPU process... so this marketing plan is his, and he's calling the shots.

Intel has officially entered the battlefield of professional graphics cards this week at SIGGRAPH 2022 in Vancouver, Canada. Today, Intel is showing off their upcoming professional discrete card offerings for the first time. They displayed their Arc Pro A40 and Arc Pro A50 video cards in their booth on the exposition floor.

Unfortunately, none of their demonstration systems used in the booth on the show floor are powered by their premier Arc Pro A50 solution. The Intel demo team was extremely proud and enthusiastic about the Arc Pro A40 and its current status.

One takeaway from seeing both cards next to each other is the physical size difference between the Arc Pro A40 and much larger Arc Pro A50 graphics cards. Although the smaller Arc Pro A40 card can fit in a small form factor solution, Intel likely will not be pushing their upcoming higher-end card into their smaller factor offerings in this generation of cards.

ASRock has posted a review of its new Intel Arc A380 Challenger ITX graphics card on Weibo, which is an interesting turn of events for the company.

Just weeks ago, ASRock only made AMD Radeon graphics cards and now the company has introduced its first Intel Arc graphics card, and then a review posted up on Chinese social networking site Weibo. ASRock's new Intel Arc A380 Challenger ITX is a small dual-slot, single-fan, single 8-pin PCIe power connector graphics card.

We knew most things we needed to know about the ASRock's new Intel Arc A380 Challenger ITX graphics card, but now we know that the fan hits 1700RPM or so under full load, while the ACM-G11 GPU hits 85C.

Micron is now making its ultra-fast 24Gbps GDDR6X memory, where it has entered production and is getting prepped for NVIDIA's next-gen Ada Lovelace-based GeForce RTX 40 series GPUs.

The new Micron GDDR6X modules at 24Gbps will arrive as 16Gb GDDR6X chips, which means we'll have 24GB of GDDR6X on flagship GeForce RTX 40 series GPUs with single-sided GDDR6X. This is what we want, as the 24GB of GDDR6X on the GeForce RTX 3090 was single-sided was a hot mess (literally) while the 24GB of GDDR6X on the GeForce RTX 3090 Ti was double-sided, and GDDR6X memory temperatures benefited greatly because of it.

Micron's new 24Gbps GDDR6X memory modules will also usher in 48GB of GDDR6X at 24Gbps, where the double-sided 24Gbps GDDR6X memory chips will be perfect for a new TITAN-class GPU, or workstation GPU powered by the next-gen Ada Lovelace GPU architecture from NVIDIA.

EVGA has just slashed a huge $1000 from its enthusiast-ready GeForce RTX 3090 Ti FTW3 graphics card, which cost $2149 just a week ago... and now it's down to $1149.

The custom EVGA GeForce RTX 3090 Ti FTW3 graphics card was introduced at $2149, with it being the cheapest of the three SKUs that EVGA has in its GeForce RTX 3090 Ti arsenal. As it stands, EVGA is selling its GeForce RTX 3090 Ti FTW3 graphics cards for between $1150 and $1400.

EVGA is discounting $1000 from its GeForce RTX 3090 Ti FTW3 ULTRA graphics card as well, down from $2199 to $1199 while the GeForce RTX 3090 Ti FTW3 BLACK is $600 discounted, down from $1999 to $1399. EVGA is still selling its higher-end GeForce RTX 3090 Ti HYDRO Copper and GeForce RTX 3090 Ti KINGPIN Hybrid graphics cards for $1500 and $2000, respectively.

Well, we now know that MSI isn't the AIB partner that pulled out of making custom Intel Arc graphics cards, as the company has just announced its new gaming PC that features the MSI Intel Arc A380 6G graphics card.

MSI's upcoming Intel Arc A380 6G graphics card is a little different to the ASRock and GUNNIR Intel Arc A380 graphics cards, where MSI is using Intel's own reference design: no factory overclocking, and a conservative 75W TDP. GPU clocks on the MSI Intel Arc A380 6G are at 2000MHz, with 6GB of GDDR6 memory clocked at 15.5Gbps.

You won't be able to buy MSI's new Intel Arc A380 6G graphics card anywhere yet, as it's only available inside of the MSI pre-built PC that is sold exclusively through Chinese etailer JD.com. Inside of said MSI system you'll find an H510M or H610M Bomber motherboard, with the cheaper model featuring the Intel Core i3-10105F while the slightly higher-end Core i5-10400F and Core i5-12400F processors are used. You'll be looking at $532 up to $650 for the pre-built MSI gaming PC.

We've been hearing all sorts of bad news about Intel's new Arc GPUs where I've been reporting on news that Intel would outright cancel their Arc GPUs altogether over how bad it has gotten, and now Intel has reportedly lost their first AIB.

The first AIB to stop production of custom Intel Arc GPUs has reportedly made history, becoming the first AIB to pull out of Intel's new Arc GPUs before they even really began. The news is coming from Igor Wallossek at Igor's Lab, who reports that the first of the big board partners have "stopped the production of Intel cards completely" which his sources say are "due to quality concerns".

Igor reports: "At least one of the big board partners has even stopped the production of Intel cards completely ("due to quality concerns"), as I could find out yesterday and today. [...] Other board partners have at least already completely capped their marketing activities, and it does not currently look as if there will be any real launch offensives from the board partners in the time window I mentioned between August 5, 2022 and September 29, 2022. What will really arrive on the market (as retail) will be seen in the next few weeks. From the customer's point of view, I can only hope for the best, I alone lack faith".

Intel itself has confirmed it will be showing off its very first Arc GPU for workstation PCs at SIGGRAPH 2022 next week.

The news is coming directly from Intel's own website, where it says "Intel will be showing our just announced Intel ARC Pro graphics workstation GPUs running Trimble, Inc's Sketchup with D5 renderer to seamlessly provide beautifully rendered architectural images with hardware accelerated Raytracing and hardware assisted AI (XeSS). An entry-level workstation segment first providing hardware accelerated ray tracing and AI".

Hopefully, this means we'll get some more demos and details on Intel XeSS technology, but if we do it will be more professional-based... not for gaming, unfortunately. Still, it's good to see that Intel will be showcasing workstation Arc GPUs at SIGGRAPH 2022 starting Monday.

NVIDIA's next-gen GeForce RTX 4090 is "still planned" for an October launch, according to the very latest from leaker Moore's Law is Dead.

In his latest video, Tom at Moore's Law is Dead explains that his sources teased that NVIDIA has "begun sending out embargo details to their partners this week that specifically denotes a plan to launch in October, but final dates are not decided yet". Another source added that the "RTX 4090 (at least) is still planned to launch in October".

NVIDIA's next-gen Ada Lovelace GPU architecture will debut with the GeForce RTX 4090, but we will also see the GeForce RTX 4080 and GeForce RTX 4070 shortly after. The question has been whether the GeForce RTX 4080 and RTX 4070 would launch this year, or whether NVIDIA debuts the new monster GeForce RTX 4090 -- in 450W form at first, a 600W+ SKU is reportedly coming after AMD drops Navi 31 -- and leaves it at that.

ASRock has just launched its new custom Intel Arc A380 Challenger ITX graphics card, the second custom Arc A380 graphics card to be launched after GUNNIR.

The new ASRock Intel Arc A380 Challenger ITX graphics card is a small dual-slot, single-fan, single 8-pin PCIe power connector graphics card. Inside, the Arc A380 has the full ACM-G11 GPU on the TSMC 6nm process node with 8 Xe-Cores or 1024 ALUs, with a max GPU clock of 2450MHz. 6GB of GDDR6 is here at 15.5Gbps on a 96-bit memory bus that pumps 186GB/sec of memory bandwidth, with a 92W TBP.

ASRock is going with a more simple, not super-gamer design which is fitting for the lower-end GPU. The smaller ITX form factor is beautiful, with a tiny card being perfect for a tiny PC. The single-fan supports 0dB technology, meaning that you won't hear the fan most of the time (especially for productivity work and light loads).

NVIDIA's new Ada Lovelace GPU architecture is ramping up considerably, and so too are the leaks with news on the "full-fat AD104" GPU with 7680 CUDA cores.

The new GeForce RTX 4070 Ti should be the graphics card that the "full-fat AD104" GPU will be powering, with 12GB of GDDR6X memory clocked at 21Gbps, according to leaker "kopite7kimi". The leaker adds that the performance of the full-fat AD104 GPU will "easily match" the GeForce RTX 3090 Ti.

Rewinding the leaks back to March 2022, Moore's Law is Dead teased that the AD103-based GeForce RTX 4070 "should offer another 10-30% performance over the current flagship RTX 3090". Remember, that was before NVIDIA unleashed the RTX 3090 Ti. So we should expect to see the AD103-based RTX 4070 beating the RTX 3090, while the "full-fat AD104" based RTX 4070 Ti beating the RTX 3090 Ti.