On November 14, 2019, the review embargo for the AMD Ryzen 9 3950X mainstream desktop processor expired. As a result, there were a flood of written and video reviews of AMD’s new flagship processor for the mainstream market segment. This 7nm processor has 16C/32T with a base clock speed of 3.5GHz, a max boost clock of up to 4.7GHz, a 64MB L3 cache, a 105W TDP, and PCIe 4.0 support. The SRP is $749.99.

It is essentially the same Zen 2 processor as the 12C/24T AMD Ryzen 9 3900X (with two CCX) with four more cores and slightly different base and max boost clock speeds that has a SRP of $499.99. One important difference is that the 3900X comes with an included Wraith Prism CPU cooler, while the 3950X does not include a CPU cooler. AMD actually recommends an all-in-one liquid cooler with a 280mm radiator (or greater) for the 3950X.

This is actually a strange recommendation, since according to several reviews, the 3950X runs cooler than the 3900X (in an otherwise identical system). I suspect that you would also be fine with a high quality, large air cooler from Noctua. This apparent paradox is due to better binning of the chiplets used in the 3950X, which lets them run at lower voltage at the same clock speeds compared to the 3900X. This reduces energy usage and reduces the heat output.

Figure 1: AMD Ryzen 9 3950X

My Analysis

After reading and watching multiple reviews of the Ryzen 9 3950X, I am very impressed, more so than I thought I would be. It’s single-threaded performance is comparable to the 8C/16T Intel Core i9-9900K and 9900KS on most benchmarks, while its multi-threaded performance is far superior to those two flagship Intel desktop processors on nearly every benchmark. To make matters worse for Intel, the 3950X has significantly better single-threaded performance than Intel’s much more expensive current  Skylake-X HEDT processors and comparable or better multi-threaded performance on most benchmarks.

The Ryzen 9 3950X also dominates the existing 12nm 16C/32T AMD Ryzen Threadripper 2950X HEDT processor in both single and multi-threaded performance. It does have less memory capacity (two memory channels and four DIMM slots vs. four memory channels and eight DIMM slots), but it supports faster memory. It has fewer PCIe lanes, but PCIe 4.0 lanes have twice the bandwidth of PCIe 3.0 lanes.

Intel really doesn’t have a viable competitive response in the mainstream or HEDT segments available now, or on the short-term horizon (meaning the next six to twelve months). About all Intel can do to try to minimize the damage is to reduce their prices pretty significantly. They have the financial resources to do that if they want to, and I predict they will. If you simply must have an Intel processor, I suggest you wait a month or two to take advantage of this.

Who Is This Processor For?

Despite AMD’s marketing, you don’t really need an AMD Ryzen 3950X for gaming. If all you do is game, you can use a less expensive AMD or Intel processor, and spend the savings on a better video card. If you are a hard-core content creator, where rendering and encoding time is a really big deal, where time is literally money, then you would be better off waiting for the upcoming 3rd Generation AMD Ryzen Threadripper processors that will have more cores, more memory channels and capacity, and more PCIe 4.0 capacity.

The target audience for this processor is someone who does some content creation, some development, perhaps likes to run multiple VMs or containers, and also likes to do some gaming. It is a versatile, relatively affordable mainstream consumer processor (compared to an HEDT system) that has the performance and capacity to handle most common workloads very well.

To be clear, most people don’t really need to go this high up in the desktop stack to get great general purpose desktop performance. You can use something like an 8C/16T AMD Ryzen 7 3700X or even a 6C/12T AMD Ryzen 5 3600 for a lot less money. If you are running an older Intel 4C/8T desktop processor including as new as a Core i7-7700K, moving to even a lower-end AMD Zen 2 processor system is going to be a substantial upgrade.

Selected Reviews

Here are some reviews to watch and read.

Intel Could Take YEARS to Catch Up… – Ryzen 9 3950X Review

Ryzen 9 3950X Review, The New Performance King!

AMD Ryzen 9 3950X Review & Benchmarks – The Intel Destroyer

AMD Ryzen 9 3950X Review: Premiere, Blender, Overclocking, & Gaming CPU Benchmarks

Ryzen 3950X Review & Benchmarks: 16-Core Dominance!

RYZEN 3950X vs. TR 2950X, i9-9900KS – Gaming, Rendering, OC

Ryzen 9 3950X review: AMD’s 16-core CPUs is an epic end-zone dance over Intel

The AMD Ryzen 9 3950X Review: 16 Cores on 7nm with PCIe 4.0

AMD Ryzen 9 3950X Review: 16 Cores Muscles Into the Mainstream

AMD Ryzen 9 3950X Review: A 16-Core Zen 2 Powerhouse

The post AMD Ryzen 9 3950X Processor Released appeared first on Glenn Berry.

With the older SpeedStep technology, it would typically take 100-150ms for a processor core to fully ramp up its clock speed in response to a lower P-state. With Speed Shift, this delay goes down to 30-35ms to fully ramp up.

Figure 1: Intel Speed Shift

This technology has been in Intel desktop and mobile processors since Q3 2015 (although you couldn’t use it until Microsoft patched Windows 10 in November 2015). It showed up in Intel server processors in the Skylake-SP family and in the current Cascade Lake-SP family. Figure 2 shows a current Intel Xeon Gold 6244 processor which has Intel Speed Shift support (although you can’t actually tell from CPU-Z).

Figure 2: Intel Xeon Gold 6244 in CPU-Z

Remember, you need a new enough processor (Skylake or newer) and operating system support in order to enable Intel Speed Shift. This means a new enough build of Windows 10, Windows Server 2016 or Windows Server 2019.

One way to confirm whether Intel Speed Shift is enabled is to use the free HWiNFO64 utility. On the main HWiNFO screen, in the CPU section, there is a Features section that shows various AMD and Intel processor features. They will be green if that feature is enabled on your system, and greyed out if it is not.

The one for Intel Speed Shift is SST, at the bottom right of the section. You can see this feature enabled in Figure 3.

Figure 3: HWiNFO64 Showing Intel Speed Shift Enabled

SST is something you want to have enabled on your database server if at all possible. If you have the two main prerequisites, you may still have to poke around in your BIOS settings to make sure this ends up being enabled. If you don’t see it enabled in HWiNFO64, you might want to bug your server vendor to find out what combination of BIOS settings are required your your model server.

The post Checking To See If Intel Speed Shift Is Enabled appeared first on Glenn Berry.

AMD and Intel Financial Results for Q3 2019

Normally the financial results of tech companies is not that interesting (unless you work there or own stock in the company). In this case, looking at how AMD and Intel are doing, and comparing their relative size is relevant from an technical perspective since it may help you understand what they are doing with their products and pricing.

AMD has had their best financial quarter since 2005, with 1.8 billion dollars in revenue, and while this sounds impressive, they are still dwarfed by Intel with 19.2 billion dollars in revenue for the quarter. From a net earnings perspective, the picture is even more in Intel’s favor, with Intel posting 6.0 billion in GAAP net income, while AMD posted 120 million in net income for the quarter.

There are a couple of reasons why this matters. First, a resurgent AMD will have more money available for R & D and new product development than they did in the past, which will allow them to maintain their competitive pressure on Intel. On the other hand, Intel has the financial resources and very high margins that will let them lower prices in order to maintain their market share. In the recent past, they haven’t had to do this due to lack of competition from AMD in most market segments.

Since the release of the Zen 2 architecture (with the Ryzen 3000 series desktop processors and EPYC 7002 series server processors), AMD has been reclaiming some market share in those two segments. They have also done well with the Ryzen Threadripper 2000 series HEDT processors, and should do even better with upcoming Zen 2 based Ryzen Threadripper 3000 series HEDT processors. Intel is still doing very well in the mobile segment, which is very important to them.

We have already seen a pretty massive price decrease (over 50%) with the new Intel Cascade Lake-X HEDT processors, as I discussed here. There are pretty strong rumors that Intel is going to announce some price cuts on their mainstream desktop processors pretty soon. I wouldn’t be too surprised to see Intel announce some official price cuts on their Xeon processors in the next few months.

The point here is that AMD has developed into a serious competitor in the mainstream desktop, HEDT, and server market, while Intel is maintaining their dominance in the mobile market. This relative weakness in some segments has already caused Intel to reduce prices on some products, and their financial resources will allow them to do more of that if they want to. Intel has actually touted their financial strength as a key competitive advantage vs. AMD, which makes it even more likely they will announce price cuts on more products. This is good for consumers, but perhaps not so much for Intel stockholders.

AMD AGESA 1.0.0.4 Begins Rolling Out for Ryzen 3000 Series Processors

AGESA stands for AMD Generic Encapsulated Software Architecture. This is a procedure library that AMD developed and maintains, that is supplied to their partner motherboard vendors for use as part of the BIOS of the motherboard. AMD periodically releases new AGESA versions that contain bug fixes and performance enhancements. The motherboard vendors then take this AGESA code and incorporate it into a new BIOS version that you have to download and install on your system.

Even though this may sound trivial, it is actually pretty important if you want to get the best performance and reliability out of your system. Keeping your BIOS up to date is important, whether is is for your laptop, gaming machine, or database server. AGESA 1.0.0.4 improves system boot times by 20-30%, improves turbo clock speed performance and improves NVMe device compatibility, on top of having many other small bug fixes. If you have an AMD desktop system, you should check with your motherboard vendor over the next couple of weeks to get an updated BIOS.

This reminds me of how Tesla pushes out free OTA software updates. They recently pushed out version 2019.36.1, which included a 5% peak power increase for the Model 3, among other new features and improvements. This is the second 5% power increase they have enabled with a software update. Getting extra performance for free is a great thing, whether it is for your car or for your computer.

Intel Delays Release of Cascade Lake-X HEDT Processors

According to WCCFTech (which has a somewhat mixed record regarding rumors and leaks), Intel has decided to slightly delay the planned release of Cascade Lake- X from November 5 to November 25. The supposed reason for this is so Intel can see the pricing for the upcoming AMD Ryzen Threadripper 3000 series HEDT processors, and then decide whether they want to make any pricing adjustments to Cascade Lake-X.

Speaking of that, AMD has scheduled a “Meet The Experts” webinar on November 6, 2019, where they will cover “AMD plans for high-end desktop systems” and “The future of the high-end desktop market”, meaning it is pretty likely they will release more information about the AMD Ryzen Threadripper 3000 series during the webinar.

The post Glenn’s Technical Insights For November 4, 2019 appeared first on Glenn Berry.

Intel has released the Intel Core i9-9900KS Special Edition mainstream desktop processor that was originally announced back on May 26, 2019 at the Computex trade show. This was the same day that AMD revealed the details about the 7nm AMD Ryzen 3000 series mainstream desktop processors. The preview announcement of the Core i9-9900KS was seen at the time as an attempt to upstage AMD’s announcement of Ryzen 3000 series.

Now, roughly five months later, Intel has actually released the Core i9-9900KS, which they are touting as “the world’s best gaming processor”. Is this true, and should you want one of these processors for your next gaming rig?

Figure 1: Intel Core i9-9900KS Packaging (from PCMag.com)

Specifications

Let’s start with the main specifications for this new processor. It is a 14nm, 8C/16T “Coffee Lake” processor with a base clock speed of 4.00 GHz and a Max Turbo speed of 5.00 GHz. It has a 16 MB L3 cache, 16 PCIe 3.0 lanes, and a 127W TDP rating. It uses an LGA 1151 socket and will work in existing 300 series motherboards with a BIOS update. It includes integrated Intel UHD Graphics 630, but does not have a stock CPU cooler in the box. The recommended customer price is $513.00. The warranty is only one year instead of the normal three years that Intel usually offers on most of its other processors.

This new processor is essentially a specially binned version of the existing Intel Core i9-9900K processor (which was released in Q4 2018) that will let you run all of the eight cores at 5.00 GHz without any manual overclocking. One challenge for this new processor is that the existing Core i9-9900K can usually be overclocked to 5.00 GHz on all cores, depending on whether you were lucky in the silicon lottery (meaning you got a “good” sample), your CPU cooler, and your motherboard and BIOS settings. Individual motherboard vendors can choose to use features like Multi-Core Enhancement (MCE), and they can also decide how they want to regulate power usage and Turbo duration. These factors can have a huge effect on benchmark results and real-world performance. Keep in mind that you will want/need a high quality, fairly expensive CPU cooler for an Intel Core i9-9900KS. This might cost anywhere from $75-$200.

Gaming Performance

Intel claims this is the absolute best processor for gaming, but is this actually true? This depends on what type of gaming you plan to do, especially the screen resolution you will be playing at. It makes a big difference whether you game at 1080P (1920 x 1080) or lower; or whether you game at 2K (2560 x 1440) or 4K (3840 x 2160). If you game at 1080P or lower, then your single-threaded CPU performance is usually your bottleneck for getting high frames per second (FPS), assuming you have a good enough video card such that the video card is not the bottleneck. You can use a relatively low performance video card and still get high FPS performance when you are running at 1080P or lower resolution.

Once you go above a certain level of FPS (depending on whether you have a high refresh rate, low latency monitor and whether your monitor has G-Sync or FreeSync), getting even more FPS is not going to make any noticeable difference in your gaming experience. Once you go above 1080P gaming, the video card becomes the bottleneck, unless you have an extremely slow processor. As long as the processor meets a certain relatively low level of performance, your FPS performance in 2K and higher gaming is gated by your video card performance.

What this means is that if your main priority is the absolute highest FPS performance at 1080P or lower, then yes, the Intel Core i9-9900KS is the world’s best gaming processor. If that use case is not your main priority, there are other less expensive choices, and also other similar cost choices that will work much better for many other scenarios.

Other Processor Choices

If you are an Intel fan, you could choose an Intel Core i9-9900K (with the right motherboard and BIOS settings), and very likely get the same level of 1080P gaming performance as a 9900KS. You would probably save $50-$100 by doing this, depending on the actual street prices of both processors. You could also choose a less expensive 8C/8T Intel Core i7-9700K processor and probably save $200-$250 and still get nearly the same level of 1080P gaming performance as a 9900KS. In either case, you could spend those savings on a better video card, or keep the savings yourself. If you are thinking about building a new Intel desktop system, I would urge you to wait until November/December, since there are pretty strong rumors that Intel is going to reduce the prices of their older existing CPUs by perhaps $50 or more.

What about using an AMD processor? One excellent choice for gaming and general purpose usage is the 7nm 8C/16T AMD Ryzen 7 3700X, which is currently selling for $319 (including a pretty good stock Wraith Prism CPU cooler in the box) at Micro Center. The Ryzen 7 3700X is pretty competitive with these Intel processors for gaming, depending on the game and the resolution. It is going to be much better than the Intel Core i7-9700K for general purpose computing since it has 16 threads instead of only 8. You could use the money savings (vs. a Core i9-9900KS) for a better video card, more RAM, or better storage.

You could also step up to a 12C/24T AMD Ryzen 9 3900X (if you can find one) or wait a few weeks and get a 16C/32T AMD Ryzen 9 3950X (which may also be in short supply when it is released). The 3900X is $499 and the 3950X will be $749. These processors will also be pretty competitive with the Intel processors for gaming, depending on the game and the resolution. They will be much better than any mainstream Intel processor for workstation performance because of their higher core and thread counts and PCIe 4.0 support. Speaking of that, the upcoming Ryzen 9 3950X is very likely to be better than the new $979 18C/36T Intel Core i9-10980XE Cascade Lake-X HEDT processor for many workstation workloads.

Frankly, the initial written reviews for the Intel Core i9-9900KS have been pretty brutal:

The Intel Core i9-9900KS Review: The 5 GHz Consumer Special

The Intel Core i9-9900KS Special Edition Review: 5.0 GHz on All the Cores, All the Time

Intel Core i9-9900KS Special Edition Review: More power, less point

There are also many YouTube reviews that have been even more negative about the Intel Core i9-9900KS. Here are a few:

Intel Core i9-9900KS Review, Winner of 2019’s Most Boring CPU Award

Intel is selling BINNED 9900Ks! Core i9-9900KS Unboxing

$513 5GHz Special Edition CPU – Intel 9900KS Review

Intel i9-9900KS Review: Overclocking, Power, & Gaming CPU Benchmarks

INTEL i9 9900KS Release! REVIEW & OVERCLOCK to 5.4 GHz!

Intel i9-9900KS Marketing: Rushed and Hilarious!

Well this is awkward…My golden sample 9900K BEAT the 9900KS

Conclusion

Does all of this mean that the Intel Core i9-9900KS is a “bad” processor? No, absolutely not. If 1080P gaming with the highest FPS performance is your main concern, then this is a great processor. As long as you have a high quality Z390 motherboard with good VRMs, a high quality CPU cooler, and a good enough graphics card, you will be very happy.

If you game at higher resolutions, or do other things besides gaming, you have other choices that are much more affordable, such as an AMD Ryzen 7 3700X processor. For the same amount or slightly more money, you can get much better general purpose and workstation performance with a higher core count AMD Ryzen 9 3900X or 3950X processor.

What are the implications for the overall mainstream desktop CPU market? Well currently, Intel is losing a lot of both market-share and mind-share with their current offerings. The Core i9-9900KS is a pretty weak response to the AMD Ryzen 3000 series outside of one particular narrow use case. Intel’s next short-term move is likely to be price reductions, which they have never really had to do in the past. Intel has milked the 2015-vintage 14nm Skylake architecture (and its Kaby Lake, Cannon Lake, and Coffee Lake derivatives) about as far as they can.

Intel will eventually have a better response, probably in the late 2020/2021 time frame. By then, AMD should have the next generation Zen 3 processors. If you enjoy computer hardware, this is a great time to watch what is happening in the industry! 

The post Some Thoughts About the Intel Core i9-9900KS Processor appeared first on Glenn Berry.

Microsoft SQL Server Cumulative Updates

Microsoft has recently released (and then removed) SQL Server 2016 SP2 CU9. There was nothing wrong with the actual payload of SQL Server 2016 SP2 CU9, but there was a problem if you tried to uninstall it. To be fair, uninstalling a CU doesn’t happen that often, but if you want/need to do it, it should work properly. It was quickly replaced with SQL Server 2016 SP2 CU10, which is identical to CU9, except that the uninstall issue has been fixed.  Since SQL Server 2016 SP1 is no longer supported, there was no CU for that branch.

Microsoft also released SQL Server 2017 CU17 on October 8, 2019. This is Build 14.0.3238.1, with 34 public hotfixes. So far, there are no reported issues with this CU. I wrote more about this CU here. Despite some recent stumbles by Microsoft, I am still a big proponent of trying to keep your SQL Server instances as up to date as possible. That does not mean throwing a new CU into Production the day it is released, but it also does not mean avoiding patching SQL Server indefinitely either.

Intel Cascade Lake-X HEDT Processors

On October 7, 2019, Intel released a new line of high end desktop (HEDT) processors for the existing X299 chipset. This is the 14nm Core i9-10900 Series that is meant for HEDT and workstation usage on the LGA2066 platform on existing X299 and new X299X motherboards. There are four SKUs in this release, ranging from 10C/20T up to 18C/36T.

These processors have slightly higher base and Turbo Boost clock speeds than the previous Skylake-X HEDT processors, with support for up to 256GB of DDR4-2933 memory. They also have several other minor improvements compared to Skylake-X. Overall, the majority of the enthusiast tech community seems to be pretty underwhelmed by this product family.

The big news with this release is a rather dramatic price reduction compared to Skylake-X, especially on the higher core count SKUs. For example, the new 18C/36T Core i9-10980XE has a launch price of $979.00 compared the previous 18C/36T Core i9-9980XE that went for about $2000.00.

Figure 1: Intel Core i9-10900 Series SKUs

These price cuts seem to be a pretty obvious response to what AMD has been doing over the past year (and what they are going to release in November). AMD is due to release the 7nm 16C/32T mainstream desktop Ryzen 9 3950X for $750.00 in November, along with the 7nm 3rd Generation Threadripper processors. The 3rd Generation Threadripper processors are rumored to have between 24C/48T at launch, up to possibly 64C/128T later. There are also strong rumors of new TRX40 and TRX80 chipsets that may have additional memory channels and more PCIe 4.0 lanes compared to 2nd Generation Threadripper. We don’t know clock speeds or pricing yet.

This is another example of why viable competition between Intel and AMD is good for the market and for consumers. AMD seems to be winning a lot of battles in different market segments lately, but Intel has many talented engineers and lots of resources that they can throw into the fight. Intel will eventually have a better response than drastic price cuts, so this will be an interesting fight over the next couple of years.

The post Glenn’s Technical Insights For October 11, 2019 appeared first on Glenn Berry.

Introduction

I’ve been writing and presenting about SQL Server hardware for many years now. I actually wrote a book called SQL Server Hardware back in 2011, which is probably the only book about server hardware from a SQL Server perspective. During most of my coverage of SQL Server hardware related topics, I have been a big proponent of using Intel processors for SQL Server workloads. I even used to make joking comments during some of my presentations about how AMD probably had a contract out on me, because I gave such negative opinions about their processors for SQL Server usage. There were valid reasons why I had a negative opinion of AMD processors though.

Why I Used to Only Recommend Intel Processors

After the introduction of the 45nm Intel Nehalem microarchitecture in 2008, Intel was completely dominant compared to AMD when it came to single-threaded CPU performance for server processors. Intel was also successfully executing their Tick-Tock release cadence, where they released a new CPU microarchitecture roughly every two years (a Tock) and then introduced a manufacturing process shrink on the same basic microarchitecture (with minor improvements) the following year (a Tick).

This Tick-Tock release cycle made it easier to plan when to push for a hardware upgrade or a complete data platform refresh. Figure 1 shows the Intel Server Processor Family Tree from 2008 to the present. The Tick-Tock model was in place from 2007 until early 2016. During this period, Intel captured over 99% of the overall x86 server CPU market, with many server vendors discontinuing their AMD-based server models. The situation was so bad that Microsoft offered a 25% license cost discount if you used qualifying AMD processors with Biztalk Server and SQL Server 2012 or 2014 in a document called the Core Factor Table.

Figure 1: Intel Server Processor Family Tree

When SQL Server 2012 was released on April 1, 2012, it brought with it a move to core-based licensing for SQL Server, which replaced the old processor-based licensing that was used in previous versions of SQL Server. This licensing change made it very important to do some careful analysis before selecting the exact processor(s) for a database server or virtualization host that was going to be running SQL Server VMs.

This licensing change by Microsoft happened shortly after the introduction of the ill-fated 32nm AMD Bulldozer microarchitecture, which featured up to 16 physical cores in the Opteron 6200 series. Unfortunately, these AMD processors had very poor single-threaded performance and high power usage to go with their high SQL Server licensing costs. This was not a good combination, hence the Microsoft Core Factor Table.

For licensing purposes, Microsoft didn’t care whether you had a fast processor core or a slow processor core, the license price per core was exactly the same. Knowing this, a smart database professional could purposely select the fastest processor SKU at a given core count, and also try to select a lower core count (but faster) processor SKU in order to get the most performance per core and in order to minimize their SQL Server core license costs.

If you did this properly, it was pretty easy to save many tens of thousands of dollars on SQL Server core license costs on a two-socket server, which would more than offset the hardware cost of of a typical two-socket database server. Using a frequency-optimized processor SKU would also deliver better single-threaded CPU performance and more memory bandwidth than an entry level processor SKU at the same core count.

Why I Now Recommend You Seriously Consider AMD Processors

For Opteron server processors, AMD was stuck with the Bulldozer microarchitecture (and minor improvements with the newer Piledriver and Excavator microarchitectures) until the release of the completely new Zen architecture in 2017. During this period, Intel continued to completely dominate the server CPU market, with no meaningful competition from AMD, except on the low-end. As often happens with a lack of competition, the market leader became complacent over time, to the point where AMD was able to catch up and actually surpass Intel in many areas. As a result, AMD is starting to regain some market share in the server CPU market.

Intel has badly stumbled over the past 4-5 years as they have tried to move from a 14nm manufacturing process to a 10nm manufacturing process. This has forced them to abandon the old Tick-Tock release cycle, and it has also lead to a longer product cycle overall.

This has been accompanied by a very noticeable reduction in generational performance increases since Broadwell-EP, as shown in Figure 2. These numbers are estimated TPC-E scores for a two-socket server with two, eight-core processors, using the fastest eight-core processor from each generation. Based on this, we have seen an extremely small increase in performance over the last four years.

Figure 2: Generational Intel Xeon Processor Performance Increases

Intel Security Vulnerabilities

Intel has also had to deal with multiple processor security vulnerabilities. These include Spectre, Meltdown, Foreshadow and their variants, along with newer exploits such as Zombieload. The latest CPU security vulnerability I have heard of is NetCAT, which only affects Intel processors.

Generally speaking, modern Intel processors are more vulnerable to these types of attacks than modern AMD processors are. The required fixes for these vulnerabilities also have a more negative effect on performance for Intel processors than on AMD processors, especially since AMD processors are not affected by many of these exploits. Microsoft’s current SQL Server specific guidance about this subject is here.

On August 7, 2019, AMD finally unveiled their new 7nm EPYC 7002 Series of server processors, formerly code-named “Rome” at the AMD EPYC Horizon Event in San Francisco. This is the second generation EPYC server processor that uses the same Zen 2 architecture as the AMD Ryzen 3000 Series desktop processors. These new processors are socket compatible with the previous generation 14nm AMD EPYC 7001 Series processors, so they will work in existing model servers (with a BIOS update). Despite that, you will need a new model server to be able to use PCIe 4.0 support from the newer processors. The major server vendors like Dell/EMC and HPE have already released new server models that let you fully leverage the new AMD EPYC 7002 series processors.

AMD is not slowing the pace of innovation, since they are on track to release the Zen 3 based “Milan” server processors in Q3/Q4 of 2020. These will have IPC improvements, better L3 cache performance, and probably increased clock speeds.

Figure 3: AMD EPYC 7000 Series Roadmap

Conclusion

I have previously written about why the AMD EPYC 7002 Series processors are going to be significant for SQL Server. The 7nm EPYC 7002 series has higher memory density and capacity, higher memory speed and bandwidth, more PCIe bandwidth, PCIe 4.0 support, and much lower pricing than 14nm Intel Cascade Lake-SP processors.

A one-socket AMD server will be a superior replacement for many legacy two-socket Intel servers, while a two-socket AMD server will also be a superior replacement for many legacy four-socket Intel servers. I think we will see AMD’s server CPU market share go up to 10-15% over the next 12-18 months. We may also see more aggressive pricing from Intel as a result (which has already happened with the new Intel Cascade Lake-X HEDT and Xeon W workstation processors).

I think an AMD platform is a viable choice for many SQL Server workloads, so I have changed my mind compared to what I thought in the past.

The post T-SQL Tuesday #119 Changing Your Mind appeared first on Glenn Berry.

Useful Utility/Benchmark Software Updates

Samsung has released a new version of Samsung Magician, which is now version 6.0. This release has a completely new user interface, and quite a bit of additional functionality. I have noticed that it takes longer to startup and scan your drives compared to the previous version. If you have any Samsung SSDs in your system, you really should have their Magician software, especially for obtaining and installing firmware updates.

Figure 1: Samsung Magician 6.0

CrystalDiskMark 7 Beta 4 is available, with many new features along with additional testing and display modes. These include displaying IOPS and latency information in the main GUI.

You can also choose from different testing profiles, which essentially let you do similar testing compared to running Microsoft DiskSpd natively. This is going to make CDM a much more useful tool.

Figure 2: CrystalDiskMark 7.0 Beta4 – Default Profile

Figure 3: CrystalDiskMark 7 Text Results

This is one of the new testing profiles.

Figure 4: CrystalDiskMark 7.0 Beta4 – Peak Performance + Mix Profile

2nd Generation Intel Optane DC SSDs Coming in 2020

I’ve been very impressed with the 1st generation Intel Optane SSD DC P4800X “Coldstream” storage devices that use two-layer 3D XPoint media. They have been available since mid-2017, and they are extremely well-suited for certain types of SQL Server I/O workloads. One prime example is write heavy tempdb workloads.

Now, Intel is starting to reveal more details about the 2nd generation devices in this family. These are code named “Alder Stream”, and they will use Barlow Pass 3D XPoint media with four layers. It is also probable that they will have PCIe 4.0 support, and a new, faster controller. They are due for release in 2020, and they will have up to double the capacity and significantly better performance than the current generation.

One key advantage of these devices is that they will work with legacy versions of SQL Server and legacy hardware. As long as you have PCIe 3.0 x4 hardware support and your OS supports NVMe drivers, you can use them.

Figure 5: Intel Memory and Storage Roadmap

The post Glenn’s Technical Insights For September 26, 2019 appeared first on Glenn Berry.

I previously promised some benchmarks on the new system, so one very quick and easy one is the CPU-Z benchmark. This test only takes about 15 seconds, and it is part of the very useful  CPU-Z utility, which requires no installation. This makes it very easy to run on a system, whether it is a gaming rig or a VM that will be running SQL Server. Figure 1 shows an example result on my AMD Ryzen Threadripper 2950X workstation.

Figure 1: Example CPU-Z Benchmark Results

Today, I decided to run the CPU-Z 1.89.1 CPU benchmark on eight different systems that I have around the house. Two of these are high-end desktops (HEDT), three are mainstream desktops, and three are laptops. The ST Score is the single-threaded score, while the MT score is the multi-threaded score.

The oldest system in the bunch is the 14nm Intel Core i7-6700K from Q3 2015, while the newest is the 7nm AMD Ryzen R7-3700X from Q3 2019. My AMD Ryzen Threadripper systems don’t quite have the same single-threaded CPU performance as the mainstream desktop systems, but they do have a lot more cores (and PCIe 3.0 lanes).

Figure 2: Comparative CPU-Z Benchmark Scores

None of these systems are the current “top of the line” anymore. The AMD Ryzen R7-3700X is roughly in the middle of the stack for the AMD Ryzen 3000 series. The value proposition of the AMD Ryzen 3000 series is that you get great multi-threaded CPU performance, and close enough single-threaded CPU performance for significantly less money than comparable Intel mainstream desktop processors. You also get PCIe 4.0 support with an X570 motherboard.

Rumor has it that AMD may introduce the 3rd generation Ryzen Threadripper processors as soon as September 7, 2019, supposedly with new X599 motherboards to enable PCIe 4.0 support.

The post Some Comparative CPU-Z Benchmark Scores appeared first on Glenn Berry.

Leaked Intel Internal Memo About AMD

There was quite a bit of discussion and commentary last week about a leaked memo from an internal Intel “Circuit News” employee portal. This memo, which is entitled “AMD competitive profile: Where we go toe-to-toe, why they are resurgent, which chips of ours beat theirs“. The memo is a pretty frank analysis of Intel’s current challenges in the desktop and server CPU market. Since it was written for internal consumption at Intel, it also seems to be little bit of a “buck up the troops” document, which seems understandable in that context.

The 7nm AMD Ryzen 3000 series processors and new X570 chipset motherboards are going to be on store shelves on July 7, 2019. The review embargos will expire on the same day, so we will probably have many reviews and benchmark numbers from a multitude of reputable 3rd party review sites. That is when we will finally know for sure whether the AMD Ryzen 3000 series processors actually have better single-threaded CPU performance than the best modern Intel processors.

This matters for SQL Server because the upcoming (Q3 2019) AMD 7nm EPYC “Rome” processors use the same Zen 2 architecture as the Ryzen 3000 desktop processors. If Ryzen 3000 lives up to the expectations and hype, that will be a good omen for “Rome”. SQL Server core-based licensing makes single-threaded CPU performance important if you want to maximize CPU performance and capacity while keeping license costs under control. Having a viable alternative to Intel for server processors is good for the market. Strong competition between AMD and Intel will force both companies to continue to innovate at a more rapid pace.

Despite what you may read and hear, Intel is not going to completely fail in those markets. They will lose some market share, and they will probably have to respond by offering lower prices for many of their existing processors. Intel is definitely under pressure in those two market segments, and they just don’t have an announced product release that will be a good competitive response for at least six to twelve months.

Microsoft Releases SQL Server 2019 CTP 3.1

On June 26, 2019, Microsoft released SQL Server 2019 CTP 3.1. The release notes are here. Some of the highlights for the database engine include the ability to have the SQL Server setup program suggest recommended MIN and MAX Server memory values (which you can override) during installation.

Figure 1: Memory Configuration During Installation

Another improvement is a new option for indexes, which is OPTIMIZE_FOR_SEQUENTIAL_KEY. This lets you enable an optimization within the database engine that helps improve throughput for high-concurrency inserts into the index. This option is intended for indexes that are prone to last-page insert contention, typically seen with indexes that have a sequential key such as an identity column, sequence, or date/time column.

Microsoft continues to add new features to every SQL Server 2019 CTP release. So far, SQL Server 2019 looks like it is going to be good version release with a lot of genuinely useful new features and improvements compared to SQL Server 2017.

.

The post Glenn’s Technical Insights For June 30, 2019 appeared first on Glenn Berry.

AMD Computex 2019 Announcements

On May 27, 2019, AMD President and CEO, Dr. Lisa Su delivered the opening keynote at Computex 2019 Taipei. During this keynote, Dr. Su announced more details about the 7nm Ryzen 3000 series mainstream desktop processors, 7nm AMD EYPC “Rome” server processors, 7nm AMD Radeon RX 5700 “Navi” video cards and the upcoming X570 chipset motherboards.

AMD is claiming a 15% IPC improvement, a 2X L3 cache size increase, and a 2X floating point performance improvement over the Ryzen 2000 series. AMD revealed some fairly detailed specifications and pricing for some of the Ryzen 3000 series processors, as shown in Figure 1.

Figure 1: AMD Ryzen 3000 Series Processors

AMD ran some Cinebench R20 and Blender demonstrations on stage comparing Ryzen 3000 series processors to various Intel mainstream desktop and HEDT processors. If these demonstrations are accurate (and we won’t know for sure until the various hardware enthusiast sites and respected YouTube hardware reviewers do independent testing), then AMD should have an amazing, game-changing product. They will have better single-threaded CPU performance, better multi-threaded CPU performance, PCIe 4.0 support, and lower prices than equivalent current Intel processors.

Just in case 12C/24T isn’t enough, there are many reports from good sources that there will be a 16C/32T SKU that will be released later this year. The Ryzen 3000 processors are due to be on store shelves on July 7, 2019.

Figure 2: AMD Ryzen 3000 Performance Comparisons

There was also a quick AMD EPYC “Rome” demonstration, comparing a two-socket AMD EPYC “Rome” system to a two-socket Intel Xeon Platinum 8280M system, where the AMD system had more than twice the performance. This isn’t a huge surprise, since the AMD system had 64C/128T processors vs. 28C/56T processors for the Intel system. We still don’t know the detailed specifications for the  7nm “Rome” processors, but if they show similar IPC improvements to the AMD Ryzen 3000 series desktop processors (they both use the same Zen 2 architecture), it will be very impressive.  Forrest Norrod, AMD’s SVP and GM of the Datacenter and Embedded Solutions Group, confirmed a Q3 2019 Release Date for “Rome” during the keynote.

Here are some relevant YouTube videos:

AMD R9 3900X, 3800X, 3700X Specs & Price: 16-Core Held Back for Now (& RX 5700 GPU)

3rd Gen AMD Ryzen 5, 7 & 9 Announced… It’s Official, Intel’s Screwed

AMD’s $500 12-Core Ryzen 9 3900X CONFIRMED! Computex 2019 Keynote Recap

I need to buy AMD stock. NOW.

Gigabyte X570 Master VRM & PCB Analysis | Efficiency Estimations

Corsair Force Series MP600 SSD PCIe 4.0

Corsair announced a new Force Series MP600 PCIe 4.0 M.2 SSD at Computex 2019. If you have this drive in a PCIe 4.0 system, you will get up to 4,950 MB/s of sequential read performance and 4,240 MB/s of sequential write performance. That is pretty impressive, but it is not close to what a PCIe 4.0 x4 M.2 socket can deliver, which would be nearly 8 GB/sec. Apparently, the Psison PS5016-E16 controller is the bottleneck, keeping the drive limited to about 5GB/sec on reads.

The large heatsink means this won’t fit in your laptop! Actually, because PCIe 4.0 uses significantly more power than PCIe 3.0, I don’t think we will be seeing PCIe 4.0 support in laptops for a while. That large heatsink should help reduce thermal throttling of the drive in desktop systems.

Figure 3: Corsair Force Series MP600 SSD

This is one of the first announced PCIe 4.0 drives in the consumer space. There are no details yet about capacity, pricing, or availability.

The post Glenn’s Technical Insights For May 28, 2019 appeared first on Glenn Berry.