AMD Expands EPYC Lineup with 64-Core EPYC 7662 & Large Cache EPYC 7532 CPUsby Anton Shilov on February 19, 2020 5:30 PM EST
Today AMD has added two new processors into the EPYC lineup: the EPYC 7662, its fifth 64-core CPU for applications that need loads of cores, as well as the EPYC 7532, a 32-core CPU for programs that can take advantage of a large L3 cache. Dell and Supermicro are already signed up to use these new chips, and other system builders will be sure to follow.
Like AMD's other 64 core EPYC processors, the EPYC 7662 processor is a 64 core part with 256 MB of L3 cache. Intended to serve as a cheaper 64 core option for customers, the new processor comes in a tier lower than AMD's existing chips, and fittingly it has the lowest clockspeeds with a base clock of just 2.0 GHz, while the chip can boost to 3.3 GHz. Meanwhile, the TDP is rated for 225W, which is typical for many higher-end EPYC SKUs, but also higher than the 200W 7702 above it. In essence, we're looking at a less power efficient SKU for those parties who want to save some money on hardware at the cost of greater cooling needs and power consumption.
Meanwhile AMD's other new chip is the 32 core EPYC 7532. This chip is clocked at 2.4 GHz base while turboing to 3.3 GHz; but more importantly, it offers something not found on any other 32 core EPYC SKU: 256 MB of L3 cache. This allows the 7532 to fill the large cache niche that AMD and other server vendors always produce an SKU or two for, with the souped-up chip offering 8 MB of L3 cache per core instead of the normal 4 MB. Depending on the workload, a large cache configuration can help a program maximize its performance in cache sensitive applications, such as ANSYS CFX benchmarks, as well as its single-threaded/lightly-threaded performance in general that otherwise won't benefit from more cores. The catch for AMD, in turn, is that building a 256 MB L3 SKU requires eight chiplets no matter how many cores it has, so the 7532 is still a full-chiplet design, just with half of the CPU cores disabled..
|AMD EPYC 7001 & 7002 Processors (2P)|
|EPYC 7H12||64 / 128||2.60||3.30||256 MB||280 W||?|
|EPYC 7742||64 / 128||2.25||3.40||256 MB||225 W||$6950|
|EPYC 7702||64 / 128||2.00||3.35||256 MB||200 W||$6450|
|EPYC 7662||64 / 128||2.00||3.30||256 MB||225 W||?|
|EPYC 7642||48 / 96||2.30||3.20||256 MB||225 W||$4775|
|EPYC 7552||48 / 96||2.20||3.30||192 MB||200 W||$4025|
|EPYC 7542||32 / 64||2.90||3.40||128 MB||225 W||$3400|
|EPYC 7532||32 / 64||2.40||3.30||256 MB||200 W||?|
|EPYC 7502||32 / 64||2.50||3.35||128 MB||200 W||$2600|
|EPYC 7452||32 / 64||2.35||3.35||128 MB||155 W||$2025|
|EPYC 7402||24 / 48||2.80||3.35||128 MB||155 W||$1783|
|EPYC 7352||24 / 48||2.30||3.20||128 MB||180 W||$1350|
|EPYC 7302||16 / 32||3.00||3.30||128 MB||155 W||$978|
|EPYC 7282||16 / 32||2.80||3.20||64 MB||120 W||$650|
|EPYC 7272||12 / 24||2.90||3.20||64 MB||155 W||$625|
|EPYC 7262||8 / 16||3.20||3.40||128 MB||120 W||$575|
|EPYC 7252||8 / 16||3.10||3.20||64 MB||120 W||$475|
Like all the latest AMD EPYC processors, the new CPUs also feature 128 PCIe 4.0 lanes, support up to 4 TB of DDR4-3200 DRAM support, and have robust security capabilities.
Dell and Supermicro will be the first companies to use AMD’s EPYC 7662 and EPYC 7532 processors in their PowerEdge R6515, R7515, R6525, R7525, and C6525 as well as A+ and Big Twin machines.
- AMD Rome Second Generation EPYC Review: 2x 64-core Benchmarked
- AMD May Be Prepping More 280 W EPYC Enterprise CPUs
- AMD’s New 280W 64-Core Rome CPU: The EPYC 7H12
Post Your CommentPlease log in or sign up to comment.
View All Comments
Irata - Thursday, February 20, 2020 - linkA good case of the trickle down effect actually working.
AndrewPhilips - Wednesday, February 19, 2020 - linkWhat's the advantage of more cache?
Supercell99 - Thursday, February 20, 2020 - linkfaster p0rn
yeeeeman - Thursday, February 20, 2020 - linkMore cache means more chances that the CPU cores have the required data ready to go, hence faster execution. A lot of Zen 2 core weaknesses are hidden by this huge cache.
AshlayW - Thursday, February 20, 2020 - linkRemember that the L3 is part of the architecture. If the large cache helps alleviate "weaknesses" then they are no longer weaknesses. I know you just want to slander Zen2's performance, but the IPC advantage over Skylake is very, very real. Remember that Skylake Server parts have a Huge L2 cache per core (1MB) and the desktop parts in lightly threaded workloads can acccess the same amount of cache as Zen2 on desktop (9900K has 16MB, the same as in 1 Zen2 CCX). It's only really coming into play in heavy threaded workloads. Zen2 has the best x86 prefetchers and branch prediciton available on desktop, and is much wider than Skylake, too. The only "weakness" of the Zen2 design I can see versus Skylake is the higher raw memory latency, but it's using a chiplet design so Go figure.
Spunjji - Thursday, February 20, 2020 - linkNailed it. Tired of people (Okay, mostly HStewart) pounding on this "Zen 2 only has good performance because it has lots of cache" non sequitur.
If cache was the key advantage, Intel would have already jammed more onto the third or fourth re-spin of Skylake. They haven't because they'd need to redesign the core to see any significant benefit.
FreckledTrout - Thursday, February 20, 2020 - linkCertainly an odd argument. It's like saying a Porsche 911 only goes as fast as it does due to the twin turbos that came with the engine. Imagine that.
I do hope AMD can get the latency worked out so once Zen3 lands they have a CPU that also looks good on the gaming charts next to Intel especially in very high FPS. That is really the only hold out and once they can pass Intel at very high FPS gaming it should change the average gamers perception.
Qasar - Thursday, February 20, 2020 - linkthe only reason intel has any performance lead, is because of the high clocks, clock intel the same as zen 2, and they would loose
Qasar - Thursday, February 20, 2020 - linkit isnt hstewart that keeps saying that is gondalf..
prisonerX - Friday, February 21, 2020 - linkThere's a number of Intel shills on here. They're mostly butthurt stockholders who are bitter about holding Intel and not AMD.