Intel
Despite a rocky start , Intel ’s Arc GPUs have bring in their space among thebest graphics cardsyou can bribe . And now , after a long wait , we in the end know what the next propagation has in depot .
Code - advert Battlemage , Intel ’s next - gen graphics cards bring a slew of improvements at a competitive price gunpoint . Here ’s everything we know about Intel Arc Battlemage , from glasses to prices and availability .
Intel
Intel Battlemage specs
As of flop now , Intel has announced two GPUs , and they ’re evenhandedly close in terms of specification . The current top computer graphic card is the Arc B580 , followed by the Arc B570 . There have been quite a little of rumor about other possible release , but Intel ’s made no mention of them at this time . Let ’s labor into what we have .
On the Earth’s surface , the numbers are n’t in favor of the B580 , as it in reality comes with few Xe cores than its forerunner , the A580 — 20 versus 24 . The same goes for the number of electron beam tracing center . However , as you ’ll observe out later , Intel still claim to deport sizable execution improvement .
There ’s been a huge upheaval in maximal clock speeds , with the Arc A580 touch a humongous 2,850MHz maximal frequency , and the B570 trail closely behind at 2,570MHz . The GPUs also received a much - needed encouragement to VRAM , now offering 12 GB and 10 GB , respectively — although Intel is stick to GDDR6 memory whereasNvidia ’s RTX 50 - seriesis likely to advance to GDDR7 .
Despite the larger computer memory mental ability , the bus breadth is in reality smaller than on the Arc A580 , with 192 - bit on the B580 and an unusual 160 - bit on the B570 . Both have retentivity clocked at 19Gbps , resulting in total bandwidth of 456GB / s for the B580 and 380GB / s for the B570 . That ’s a driblet compare to the A580 , which offered 512GB / s.
Although some of the specs are proficient and some seem bad , Intel ’s boost to VRAM marks a vast change for the B580 , and allows the company to advertise it as a 1440p graphics wit . In fact , Intel is mostly compare the B580 not to its predecessor , but to the Arc A750 — which , while not quite the flagship of that lineup , was a relatively higher - tier up GPU .
The B580 and the B570 both use the PCIe 4.0 x8 interface , which is not unexpected given that these are budget GPUs .
This generation marks a departure from Intel ’s first gen , when the ship’s company opened the card with the flagship Arc A770 and its cutdown sibling , the Arc A750 . This leave many wondering : What else does Intel have in store for Battlemage ? Buckle up , because we ’re move off from facts and toward leaks and rumors because Intel itself has yet to speak about a possible B770 or any other Battlemage computer graphic card .
Originally , leakers like RedGamingTech claimed the flagship card would amount with 64 Xe core — double what ’s useable on the A770 we have now , and with an totally new computer architecture in tow . At the beginning of the year , RedGamingTech revise that rumour , saying that the flagship GPUwould come with 56 Xe cores . That ’s still a massive bulge over the A770 . The a la mode meditation is a niggling number different , however .
Frequent Twitter leaker Harukaze5719 found some merchant marine manifest that gave us insight into the rumour specs of Intel Battlemage . According to the manifest , Battlemage will come in two flavors : X2 and X3 . The X2 card is said to be the flagship , and the specs are drastically cut down liken to what RedGamingTech hypothesise on earlier this year . present that we have n’t escort any quotation of X3 in relation to the B580 , take this with some skepticism .
BMG X2BMG X3https://t.co/O5v3Tl1Wnopic.twitter.com/lr8uD3bCCz
& mdash ; 포시포시 ( @harukaze5719)June 29 , 2024
The X2 card is say to add up with 32 Xe2 cores , which translates to a ( presumed ) 4,096 stream processors ( SPs ) and 512 murder units ( EUs ) . That ’s on the button the same as Intel Arc A770 , but the Battlemage architecture is also said to provide some advance regardless of the number of EUs . The 2nd carte was said to rollick 28 Xe2 cores ( 3,584 SPs and 448 EUs ) .
According to speculation , the so - called Battlemage GPU with 56 Xe2 cores was canceled . Intel seems to be adopting a similar strategy toAMD ’s RDNA 4 in this generation by sticking to the budget part of the market . However , just a few month ago , the rumors were immensely different . aside from the flagship card with much better specs , RedGamingTech claimed that the card could reach clock speeds of up to 3GHz and would come with a monumental 112 MB of L2 stash .
In summation to the manikin with 56 Xe Cores , the leakers had said that a mannequin with 40 Xe cores was in the works . This one seems a piece more ground in realism , packing the aforementioned cores , a 192 - bit memory bus , and none of the adamant memory cache . RedGamingTech hypothecate that this plan might claim the flagship time slot , citing the miserable margins that could come from the 56 Xe core poser .
As thing suffer now , we have immensely different accounts from different sources , so it ’s unimaginable to tell where Intel will go next .
Intel Battlemage pricing and release date
After month of hypothesis from leakers and scarce updates from Intel , the company announce Arc Battlemage on December 3 , 2024 . As a result , it managed to perplex both Nvidia and AMD in launching next - gen artwork circuit card .
Both cards have dissimilar release dates and pricing . The Arc B580 is usable from December 13 with a starting price of $ 250 . Meanwhile , the B570 comes in cheaper at $ 220 , but wo n’t become usable until January 16 .
Intel put up its own Limited Edition Arc B580 , but there will also be collaborator designs from brands like ASRock , Acer , and Sparkle .
Although more GPUs are expected to keep up , their vent date are presently unknown . Arecent reporttells us that Intel might expect as long as several calendar month to set in motion the top - shelf Battlemage GPU , with Benchlife guess that the card will get in the third quarter of 2025 .
Intel Battlemage architecture
Intel calls the computer architecture behind Battlemage Xe2 , keep an eye on up on the Xe computer architecture we saw with Alchemist computer graphic cards . Here ’s what we know about it so far .
First of all , Intel is once again using manufacturer TSMC for Battlemage , but it ’s now engage the TSMC N5 process node as match to the N6 used in Alchemist . The raw thickening come with a cost increase to both compactness and exponent efficiency . While the BMG GPU sport fewer transistors than the ACM - G10 ( 21.7 billion versus 19.6 billion ) , the die size of it is much smaller , make for much corking density in Battlemage .
Intel has changed the routine of vector and XMX unit per Xe - core , cutting them in half . However , they ’re now wider , touch 2,048 bit for the XMX building block and 512 minute for the vector units . As a issue , the bit of instructions executed on each core is unchanged from Alchemist . Tom ’s Hardwarereports that we ’re get 256 FP32 vector operations ( using coalesced multiply minimal brain damage , or FMA ) , 2,048 FP16 , and lastly , 4,096 INT8 operations on the XMX essence .
The publication also notes that the A750 has more trillion floating point operations per second of FP32 compute than the B580 — 17.2 TFLOPS compared to 14.6 TFLOPS — but that ’s more of a spec than an issue with the Battlemage architecture at large , which still seems forebode base on performance figure and which we ’ll discuss in the next section .
With the Xe2 computer architecture , Intel target gamey GPU utilization , reducing software package overhead and improving work distribution . Intel ’s done a lot of employment since Alchemist first launched , and Battlemage is here to hopefully draw the reward . To that death , the fellowship has talked about the various package advance it has made since the launch of Alchemist — over 50 update , in fact .
On the whole , Intel add supporting for Execute Indirect , switched to SIMD16 arithmetical logic unit ( ALUs ) , boosted the ray follow units to add three traversal pipelines , and meliorate acme and mesh blending carrying into action per render . There have also been updates to the caching power structure for the VRAM , increasing L1 cache size . Battlemage also adds keep for INT2 and TF32 . Intel read adeep dive on the Xe2 computer architecture , which is worth checking out if you ’re concerned in learning more about it .
The current flagship is the BMG - G21 GPU , and it comes with five render slices at four Xe - core each for a total of 20 Xe - cores . However , many leaker expect that we ’ll see the BMG - G10 GPU one daylight , which could offer 32 Xe - effect , although it ’s potential that Intel might have something more powerful up its sleeve .
Aside from the architectural changes , Intel alsoannounced an updateto its upscaling technology dubbed XeSS , which will now also boast physique generation ( FG ) . Unlike Nvidia ’s DLSS 3 , XeSS FG is not limited to Battlemage and will run on any GPU with XMX AI core , which includes both Alchemist and Battlemage . Intel also supply XeSS Low Latency ( XeLL ) , which will be enabled by default when FG is running , as the latter increase response time .
Intel Battlemage performance
Although we will need to essay Battlemage ourselves to obtain out its true carrying out , Intel has deal a numeral of highly promising bench mark of the B580 . The batting order is matched up against the A750 . allow ’s check it out .
For starters , on average , Intel claim that the B580 will be up to 24 % faster than the A750 , and this is at 1440p on extremist circumstance . Some plot do n’t see much of an improvement , but a lot of it comes down to how much a fussy rubric savor the extra 4 G of VRAM on the B580 compared to the A750 .
As far as competition , Intel compares the B580 to Nvidia ’s $ 300 RTX 4060 , which is an interesting choice . Nvidia wo n’t have a verbatim upgrade to the RTX 4060 for a few months ( if the leaks are correct ) , so Intel may get some breathing elbow room to let its GPU shine , and it does a good occupation in the above benchmark . On average , without DLSS and XeSS , the B580 is said to be 10 % faster than Nvidia ’s RTX 4060 .
Intel also boasts Brobdingnagian improvement in its proprietary XeSS technology , sometimes replicate performance compared to when the tech is not in use .
One net metric that Intel looked at was performance per dollar . At $ 250 and $ 220 , the B580 and the B570 are the cheapest current - gen GPUs on the grocery store . Seeing as Intel claim to hand over a execution upgrade over both the Nvidia RTX 4060 and the AMD RX 7600 , the operation - per - dollar metrical looks howling , with a 24 % winnings for Intel in rasterization ( versus Nvidia ) and a 20 % improvement in ray trace .
These benchmark are just the commencement . Once we ’ve had the probability to test the card for ourselves , we will be able-bodied to see how it matches up against its last - gen counterpart and its AMD and Nvidia equivalents .
