Benchmarking the Xeon E5-1620: A 4-core Sandy Bridge in modern games and applications

Back when the LGA 2011 v1 platform was still relevant, the Xeon E5-1620 was arguably one of the most sought-after CPUs among its Sandy Bridge brethren. And it's no surprise: the E5-1620 was one of the highest-clocked chips of its generation. This meant it should handle games quite well. Plus, its closest desktop analog was the ultra-popular Core i7-2600K, a chip that needs no introduction.

That's how the puzzle came together. Gamers picked the 4-core Xeon for its decent per-core performance. Less experienced users, in turn, were swayed by online recommendations or its similarity to the more conventional desktop i7-2600K.

But it's been over four years since the so-called "Sandy Bridge renaissance." This raises an obvious question: can the high-frequency 4-core Xeon E5-1620 deliver even a minimally acceptable performance level in today's computing landscape?

In this article, we'll examine what the legacy Xeon E5-1620 processor can achieve in 2024 games and applications. We'll also compare it against several CPUs from a similar price bracket — and some pricier ones too.

*Where new units are unavailable in stores, prices reflect the secondary market.

The Processor

Our test sample is marked SR0LC. This is a retail tray-packaged workstation CPU.

The Intel Xeon E5-1620 processor is based on a 4-core, 32nm C2 revision die, built on the Intel Sandy Bridge-EP architecture. This chip only supports single-processor configurations, as indicated by the first digit in its name (1620).

The processor features an unlocked multiplier, but we couldn't test its overclocking potential. Unfortunately, our test motherboard, a DELL T3610 (09M8Y8), lacks the necessary BIOS options. Attempting to overclock from Windows also failed, as multiplier and base clock adjustments in Intel Extreme Tuning Utility (XTU) were simply locked.

⤢ ВІДКРИТИ

The chip features 256 KB of L2 cache per core and a relatively small, by modern standards, 10 MB total L3 cache. This CPU is designed for LGA 2011 motherboards. Its nominal frequency is 3600 MHz, but with Turbo Boost, it can reach 3800 MHz for a single core and 3700 MHz for all 4 cores and 8 threads.

The 1620's integrated memory controller (IMC) and L3 cache speed, like all v1 and v2 chips in the series, is hard-locked to the core frequency and uses its divider.

As for supported RAM frequency, the 1620 officially supports a maximum quad-channel DDR3-1600 MHz RAM speed. Unfortunately, we couldn't change this through overclocking or other methods. This is due to the DELL branded motherboard used in our test bench.

This chip has a TDP rating of 135 watts. Intel clearly played it safe here, setting the TDP with a significant margin. Our measurements indicate the E5-1620 consumes up to 100 watts under heavy computational loads, dropping to around 65-85 watts in games. This means a budget cooler with 2-3 heat pipes will be more than enough for stock cooling.

Crucially, the Xeon E5-1620 doesn't support the essential AVX2 and FMA3 instruction sets. Unfortunately, in 2024, this lack of support is a critical flaw, preventing some games and applications from even launching.

Test bench, software, and CPU settings

Resizable BAR was activated on platforms that support it in the BIOS.

Test bench

• Intel CPUs: Core i3-10100F, Core i5-10400F, Core i7-11700K, Core i3-12100F, Core i5-12400F, Xeon E5-1620, Xeon E5-2690, Xeon E5-2630 v3, Xeon E5-2670 v3, Xeon E5-2640 v4;

• AMD CPUs: Ryzen 5 1600X, Ryzen 7 1800X, Ryzen 5 3600;

• CPU cooling: Cooler Master Hyper 212 Black Edition (RR-212S-20PK-R1);

• RAM for LGA 1200, LGA 1700, and AM4: 2x 8 GB Corsair Vengeance RGB PRO (CMW16GX4M2C3600C18), totaling 16 GB (Micron E-Die chips);

• RAM for LGA 2011: 4x 8 GB Micron MT18KSF1G72PZ-1G6E1HI, totaling 32 GB (Micron D9PQL chips);

• RAM for LGA 2011 v3: 4x 4 GB G.SKILL DDR4 F4-2400C15S-4GNT, totaling 16 GB (Hynix MFR chips);

• LGA 1200 motherboard: GIGABYTE Z490 AORUS ELITE AC for Core i7-11700K, ASUS PRIME B560M-A for Core i3-10100F and Core i5-10400F;

• LGA 1700 motherboard: MSI PRO Z690-A DDR4 (MS-7D25);

• LGA 2011 motherboard: DELL T3610 (09M8Y8);

• LGA 2011 v3 motherboard: Kllisre X99-D8 (AD12) with modified BIOS (Unlock Turbo Boost, Undervolt, and unlocked timing control);

• AM4 motherboard: ASUS TUF GAMING B450M-PRO II;

• Graphics card: PALIT GAMEROCK GeForce RTX 3090 24 GB (~1900/19000 MHz, Power Limit 113%);

• SSDs: 2 x KINGSTON SUV400S37120G 120,0 GB (AMD/Intel Windows 11), SAMSUNG 870 EVO 1 TB (Games/Applications);

• Power supply: Chieftec GPS-1250C.

Software

• Operating system: Windows 11 Pro x64 with the latest updates as of February 2024. Core isolation/memory integrity disabled;

• Graphics drivers: NVIDIA GeForce 551.23 WHQL;

• FPS measurement software: MSI Afterburner 4.6.5;

• Games: testing was performed on current game versions as of February 2024;

• Game settings: testing was conducted at maximum possible graphics settings at 1080p resolution.

Settings of tested processors

• Intel processors:Core i3-10100F@3600-4300 MHz, Dual Channel DDR4@2667 MHz (automatically by motherboard: 16-18-18-36);

• Core i3-10100F@3600-4300 MHz, Dual Channel DDR4@4000 MHz (16-21-21-42), IO voltage – 1,2v, SA voltage – 1.2v, DDR4 voltage — 1.420v;

• Core i5-10400F@2900-4300 MHz, Dual Channel DDR4@2667 MHz (automatically by motherboard: 16-18-18-36);

• Core i5-10400F@2900-4300 MHz, Dual Channel DDR4@4000 MHz (16-21-21-42), IO voltage – 1,2v, SA voltage – 1.2v, DDR4 voltage — 1.420v;

• Core i7-11700K@3600-5000 MHz, Dual Channel DDR4@3200 MHz (automatically by motherboard: 16-18-18-36);

• Core i7-11700K@4800 MHz, UnCore@4400 MHz, Dual Channel DDR4@3600 MHz (16-19-19-38) GEAR 1, vCore voltage – 1.33v, mem-IO voltage – 1.2v, SA voltage – 1.23v, DDR4 voltage – 1.36v;

• Core i3-12100F@3300-4300 MHz, Dual Channel DDR4@3200 MHz (automatically by motherboard: 18-19-19-39) GEAR 1;

• Core i3-12100F@3300-4300 MHz, Dual Channel DDR4@3600 MHz (16-19-19-38) GEAR 1;

• Core i5-12400F@2500-4400 MHz, Dual Channel DDR4@3200 MHz (automatically by motherboard:18-19-19-39) GEAR 1;

• Core i5-12400F@2500-4400 MHz, Dual Channel DDR4@3600 MHz (16-19-19-38) GEAR 1;

• Xeon E5-1620@3600-3800 MHz, Quad-Channel DDR3@1600 MHz (automatically by motherboard: 11-11-11-28);

• Xeon E5-2690@2900-3800 MHz, Quad-Channel DDR3@1600 MHz (automatically by motherboard: 11-11-11-28);

• Xeon E5-2630 v3@3200 MHz (Unlock Turbo Boost in UTB charts), vCore -60mv, UnCore -50mv, SA -50mv, Quad-Channel DDR4@1866 MHz (10-10-10-24);

• Xeon E5-2670 v3@3100 MHz (Unlock Turbo Boost in UTB charts), vCore -50mv, UnCore -50mv, SA -50mv, Quad-Channel DDR4@2133 MHz (12-12-12-35).

• Xeon E5-2640 v4@2400-3400 MHz, Quad-Channel DDR4@2133 MHz (12-12-12-28).

AMD processors: Ryzen 5 1600X@3600-4000 MHz, Dual Channel DDR4@2667 MHz (automatically by motherboard: 18-18-18-44);

Ryzen 5 1600X@4000 MHz, Dual Channel DDR4@3600 MHz (16-19-16-38), vCore voltage – 1.42v, SOC voltage — 1.075v, cLDO VDDP voltage – 0.975v, DDR4 voltage — 1.350v;

Ryzen 7 1800X@3600-4000 MHz, Dual Channel DDR4@2667 MHz (automatically by motherboard: 18-18-18-44);

Ryzen 7 1800X@3900 MHz, Dual Channel DDR4@3600 MHz (16-19-16-38), vCore voltage – 1.4v, SOC voltage — 1.1v, cLDO VDDP voltage – 1.025v, DDR4 voltage — 1.350v;

Ryzen 5 3600@3600-4200 MHz, Dual Channel DDR4@3200 MHz (automatically by motherboard: 22-22-22-53) Infinity Fabric@1600 MHz (1:1);

Ryzen 5 3600@4325 MHz, Dual Channel DDR4@3733 MHz (16-19-16-38) Infinity Fabric@ 1866 MHz (1:1), vCore voltage – 1.39v, SOC voltage — 1.125v, cLDO VDDP voltage – 1.075v, VDDG CCD voltage – 1.025v, VDDG IOD voltage – 1.025v, DDR4 voltage — 1.380v;

You can learn more about virtually all tested processors from our full articles, or by checking out the blogs, where we post shorter notes.

Let's reiterate our CPU testing methodology: each benchmark, application, or game was run five times. We then calculated the average score from those five runs, and that was recorded as the final result. All games and applications were installed on an SSD.

Testing results

Data archiving

7-Zip

7-Zip, the most popular free file archiver, supports multiple compression algorithms and numerous data formats, including its proprietary 7z format with the highly efficient LZMA compression algorithm. This archiver can utilize a large number of CPU threads and responds well to increased RAM frequencies.

File compression

⤢ ВІДКРИТИ

File decompression

⤢ ВІДКРИТИ

3D rendering

Blender

Blender is a versatile, free, open-source software suite for 3D creation. It supports the entire 3D modeling pipeline, from rigging, animation, simulation, rendering, compositing, and motion tracking, all the way to video editing and game development.

We benchmark CPU rendering speed using Blender's built-in Cycles engine and the BMW scene.

⤢ ВІДКРИТИ

Corona 10 Benchmark

The Corona 10 Benchmark is based on the Corona 10 render engine, which is popular among professionals and available for scene visualization in 3ds Max and Cinema 4D. This benchmark assesses CPU rendering speed using its own proprietary technologies.

⤢ ВІДКРИТИ

Cinebench R23

This is a slightly outdated but still relevant benchmark version of the highly popular Cinema 4D editor, which is used for computer 3D animation, modeling, simulation, and rendering.

Single-core performance score

⤢ ВІДКРИТИ

Multi-core performance score

⤢ ВІДКРИТИ

Cinebench R24

This is the latest benchmark version of the popular Cinema 4D editor for computer 3D animation, modeling, simulation, and rendering. Starting with this release, the main CPU test requires AVX2 instruction set support from the processor.

Single-core performance score

⤢ ВІДКРИТИ

Multi-core performance score

⤢ ВІДКРИТИ

V-Ray 6 Benchmark

This is the current benchmark version for the V-Ray render engine. Various versions of this product are available for numerous solutions, including 3DS Max, Maya, Cinema 4D, Blender, and Unreal Engine.

⤢ ВІДКРИТИ

xNormal – texture map baking

While external texture baking programs aren't as popular as they once were, xNormal is still used by tens of thousands of game developers. This is largely due to its incredibly user-friendly interface and a wealth of useful features.

Normal map rendering

⤢ ВІДКРИТИ

Ambient occlusion map rendering

⤢ ВІДКРИТИ

Overall performance

CPU-z Benchmark

The CPU-Z information utility's benchmark offers little insight into a CPU's real-world performance and is now largely optional. However, following a long-standing tradition, we still include tests for this metric.

Single-core performance score

⤢ ВІДКРИТИ

Multi-core performance score

⤢ ВІДКРИТИ

Geekbench 6

Geekbench 6 measures both single-core and multi-core CPU performance across a range of tasks. These include everything from checking email, to photography, and playing music—or even doing all three at once. Beyond these common uses, Geekbench 6 also benchmarks CPU performance in newer applications like augmented reality and machine learning.

Single-core performance score

⤢ ВІДКРИТИ

Multi-core performance score

⤢ ВІДКРИТИ

Video encoding

HandBrake

HandBrake is a free, open-source application that converts video from almost any format into a range of modern, widely supported codecs, including AV1, H265, H264, and many others.

Codec – AV1

⤢ ВІДКРИТИ

Codec – H265

⤢ ВІДКРИТИ

Web browsing

JetStream 2.1

JetStream 2.1 is a benchmark suite that uses JavaScript and WebAssembly, specifically designed for modern browsers and web applications. We've observed that most of the sub-tests within the benchmark can utilize up to four threads, which is fairly typical for web browsing scenarios.

⤢ ВІДКРИТИ

Speedometer 2.1

Speedometer tests the responsiveness of web applications within a browser. The benchmark simulates user actions like adding, completing, and removing items in a to-do list, using several TodoMVC examples. Some tests call the DOM API directly from ECMAScript 5 (ES5), ECMAScript 2015 (ES6), ES6 transpiled to ES5, and Elm transpiled to ES5. Others utilize one of eleven popular JavaScript frameworks: React, React with Redux, Ember.js, Backbone.js, AngularJS, (new) Angular, Vue.js, jQuery, Preact, Inferno, and Flight.

⤢ ВІДКРИТИ

Kraken 1.1

Kraken is a JavaScript performance benchmark developed by Mozilla. It measures the execution speed of several different test cases drawn from real-world applications and libraries. Its sub-tests cover audio processing with the DSP.js library, image filtering operations, JSON parsing, and cryptographic operations.

⤢ ВІДКРИТИ

The data we gathered isn't particularly surprising. As expected, the 4-core Xeon E5-1620 doesn't excel in most software tests, often lagging behind. Its sole exception is web browsing, where the high-frequency Sandy Bridge chip delivers relatively good performance, on par with the 8-core Xeon E5-2690. This isn't necessarily a credit to the E5-1620, but rather highlights the poor multi-core optimization of current browsers and web applications.

Gaming, synthetics

3DMark Time Spy

Time Spy is a DirectX 12 benchmark designed for Windows 10/11 gaming PCs. Built with an engine developed from the ground up, Time Spy supports all the latest DirectX 12 API features, including asynchronous compute, AMD Crossfire and NVIDIA SLI, and multi-threading.

⤢ ВІДКРИТИ

Games

Assassin's Creed Valhalla

This is the current major installment of the Assassin's Creed franchise. The game is built on the Ubisoft Anvil engine and can fully utilize up to 12 computational threads, with partial support for 16-24 threads.

⤢ ВІДКРИТИ

Baldur’s Gate 3

One of the best turn-based RPGs today, and last year's top game overall. Baldur's Gate 3 uses the Divinity 4.0 Engine, which can utilize up to 16 threads, though it performs optimally with 12-thread CPUs. Furthermore, the game features extremely high detail, leading to frequent RAM access. Consequently, Baldur's Gate 3 thrives on ample L3 cache and high-frequency RAM.

Our test scene is set in the city of Baldur's Gate, during the game's third act.

⤢ ВІДКРИТИ

Cyberpunk 2077

CD Projekt RED's latest creation, built on REDengine 4, can leverage more than 16 CPU threads. The game also responds very positively to increased RAM frequency and reduced latency.

Ray Tracing – ON, Path Tracing – ON

⤢ ВІДКРИТИ

Ray Tracing – OFF, Path Tracing – OFF

⤢ ВІДКРИТИ

Far Cry 6

This project uses the Dunia Engine v2. Throughout its long history, dating back to Far Cry 2, this engine has been notorious for its poor multi-threaded CPU optimization. Based on our observations, the game can operate reasonably well with eight threads. Interestingly, some CPUs with over 10 cores and SMT/HT technology (simultaneous processing of two or more threads per core) can actually lose performance in this game. However, this doesn't apply to all existing CPUs.

Ray Tracing – ON

⤢ ВІДКРИТИ

Ray Tracing – OFF

⤢ ВІДКРИТИ

Marvel’s Spider-Man Miles Morales

The former PlayStation exclusive, Marvel's Spider-Man Miles Morales, is a relatively decent PC port. Overall, Insomniac Games' proprietary engine can utilize multi-core CPUs effectively. However, the stability of games built on it often suffers and leaves much to be desired.

Ray Tracing – ON

⤢ ВІДКРИТИ

Ray Tracing – OFF

⤢ ВІДКРИТИ

Starfield

Starfield is the highly anticipated new game from acclaimed guru Todd Howard. The project is based on a revamped version of Creation Engine 2, which was previously used in Fallout 4. However, 'revamped' is the key word here, and Bethesda didn't lie in their statements. While the current Creation Engine can be criticized for many things (terrible storage management, poor optimization for modern graphics cards, etc.), the developers have significantly optimized their code for multi-core processors.

Our test scene is located in the city center of Nova Atlantis – or New Atlantis, if you prefer. We measure FPS along a segment from the landing pad to the central plaza.

⤢ ВІДКРИТИ

The Witcher 3 Next-Gen Update 4.04

The updated version of The Witcher 3 moved to an improved version of REDengine 3 with Ray Tracing support. However, the project wasn't ready for such complex changes, ultimately making the game far more demanding than even Cyberpunk 2077.

The Next-Gen Update is extremely CPU-dependent, yet it can't adequately utilize powerful CPUs with eight or more cores. The Witcher 3 performs most effectively on 6-core, 12-thread chips. Additionally, REDengine 3 responds quite well to high-frequency RAM.

Ray Tracing – ON

⤢ ВІДКРИТИ

Ray Tracing – OFF

⤢ ВІДКРИТИ

Watch Dogs Legion

The third installment of the Watch Dogs franchise likely runs on an improved Disrupt 2 engine. Since the first game's release, titles in this series have performed quite well with multi-core CPUs, and Legion is no exception. The game can easily utilize over 20 threads and responds positively to high-frequency memory.

Ray Tracing – ON

⤢ ВІДКРИТИ

Ray Tracing – OFF

⤢ ВІДКРИТИ

RPCS3, Red Dead Redemption

RPCS3 is the most popular PlayStation 3 emulator. The software excels at parallelizing shader compilation across a huge number of threads. However, when it comes to actual game emulation, the load distribution quality significantly drops. While performance certainly depends on the specific game, our observations show that modern 6-8 core CPUs with high clock speeds perform best.

Additionally, noticeable performance gains can be achieved with instruction sets like AVX-512 and TSX. However, with TSX, some projects occasionally experience instability.

Emulator settings for Red Dead Redemption: SPU block size – Mega, ZCULL accuracy – Relaxed, Write color buffers – On, Sleep timers accuracy – As Host, RSX FIFO accuracy – Atomic, 1080p resolution.

⤢ ВІДКРИТИ

Of all the games we tested, the Xeon E5-1620 processor could only deliver relatively acceptable FPS in Assassin's Creed Valhalla, Cyberpunk 2077 (barely, and without ray tracing), Far Cry 6 (also barely and without ray tracing), and Marvel's Spider-Man Miles Morales (without ray tracing). Meanwhile, the 4-core Sandy Bridge proved unable to provide a minimally comfortable frame rate in current titles like Baldur's Gate 3, Starfield, and The Witcher 3 Next-Gen Update. And as the cherry on top: emulating PlayStation 3 games with RPCS3 on an E5-1620 chip is a special kind of masochism.

Summary

It's entirely predictable that a 4-core processor, even a high-frequency one based on an outdated architecture, can no longer provide decent performance in games or daily tasks. Frankly, it would be naive to expect performance miracles from the aging Xeon E5-1620. However, this chip still has some use: as internet-connected typewriters with the added bonus of 1080p and 1440p YouTube video playback.

Fortunately, owners of this CPU have a real opportunity to significantly boost performance while staying on their LGA 2011 v1 platform. Replacing the Xeon E5-1620 with, say, a Xeon E5-2690 or a similar relatively high-frequency 8-core processor will provide a noticeable performance increase. Alternatively, you could look into the Xeon v2 series of processors (but make sure to check your motherboard's compatibility with this CPU series first!), which also offers many high-frequency, high-core-count options.

However, the problem isn't just about clock speed or core count. Neither v1 nor v2 chips support AVX2, an extension crucial in 2024. This means that even if you install a multi-core Sandy/Ivy Bridge solution into your motherboard, you still won't be able to run some games and applications.

If you don't have enough spare cash to upgrade to current hardware (AM4/AM5 or LGA 1200/1700), we modestly suggest considering a more up-to-date LGA 2011 v3 platform and transitioning to it with a relatively minimal investment. Processors on this platform can still provide decent performance, plus they feature the current AVX2 and FMA3 instruction sets, allowing you to run almost any game or application.