RX 6700 XT results with SAM. How will we test GeForce?

Ľubomír Samák

3 years ago

Control

After the entry test of the Sapphire RX 6700 XT Nitro+, the second part of the series is here, tests with active Smart Access Memory. Immediately after the launch of the card, we would write about the performance that attacks the RTX 3070. In the meantime, all GeForce RTX 30 cards started to support Resizable BAR and the situation is changing a bit. ReBAR can no longer be ignored in Nvidia’s GPUs, but we don’t have to take it too seriously.

Before we get to compare the RX 6700 Nitro+ with active and inactive SAM, let’s make a small turn to GeForce. After the BIOS update on March 30, Resizable BAR with driver version 465.89 is now supported on all gaming graphics cards with Nvidia Ampere. It might seem like the time has come to discard all the old results without ReBAR, but that would be a mistake for several reasons.

With and without ReBAR

During the finalization of the methodology for testing graphics cards, which was not so long ago, we were discussing how to approach Smart Access Memory. We also considered a faster way to test only with SAM, as the cards already support it and it was their technological advantage. Of course, it depends on the platform or motherboard and processor you own.

In the end, I’m glad we decided to test both options – with active as well as inactive SAM. Also because this comparison showed two basic things, for which not only will we not discard the GeForce results without SAM out of the database, but we will even continue to execute them.

The first thing is that SAM optimizations are noticeable with each test, even to the level where newer results do not make sense when compared with older ones. We have already wondered about this in the article SAM tests on the RX 6800. AMD tunes more than it reveals. The smaller percentage improvement with active Resizable BAR than what Nvidia reports now was also shown by the time when only the RTX 3060 supported it. One of the options is to retest the cards, but this is impossible both because of the crazy size of tests, and because we do not dispose of the cards for a long time and we have to return them relatively quickly. But if the performance hasn’t changed that much over time, ReBAR degrades performance in some applications. Especially in those for computing, so it is good to keep track of which situations you’d be better off to turn it off.

It follows from the above that we will perform tests with active and inactive SAM or ReBAR (as you wish) on GeForce graphics as well. Just that we will probably not divide it into two articles anymore, but we’ll put everything into one. It will cost a huge amount of effort, but this comes to us as the right, uncompromising solution we like in the tests.

For the sake of consistency and not to be confusing, we will use the term Resizable BAR in the future, which is more suitable for GeForce (and it doesn’t matter with Radon), as SAM is more or less AMD’s marketing designation for the same thing. We will use the fact that we have interactive graphs for better orientation in the results. We’ve added “Resizable BAR” with on and off values among their sorting criteria. The default order is set according to them as well, the results will be grouped at the top of the graphs with ReBAR on, and ReBAR off will be below. Descending and ascending sorting by values is otherwise preserved.

If the presentation of the results does not seem clear enough to you, let us know and we will find a better solution. You can also arrange the bars in the graphs as you like. In the lower left corner of all graphs, there is a button via which you can set the sorting also according to GPU, test date or any other of the criteria.

Gaming tests

The largest sample of tests is from games. This is quite natural given that GeForce and Radeons, i.e. cards primarily intended for gaming use, will mostly be tested.

We chose the test games primarily to ensure the balance between the titles better optimized for the GPU of one manufacturer (AMD) or the other one (Nvidia). But we also took into account the popularity of the titles so that you could find your own results in the charts. Emphasis was also placed on genre diversity. Games such as RTS, FPS, TPS, car racing as well as a flight simulator, traditional RPG and sports games are represented by the most played football game. You can find a list of test games in the library of chapters (9–32), with each game having its own chapter, sometimes even two (chapters) for the best possible clarity, but this has its good reason, which we will share with you in the following text.

Before we start the gaming tests, each graphics card will pass the tests in 3D Mark to warm up to operating temperature. That’s good synthetics to start with.

We’re testing performance in games across three resolutions with an aspect ratio of 16:9 – FHD (1920 × 1080 px), QHD (2560 × 1440 px) and UHD (3840 × 2160 px) and always with the highest graphic settings, which can be set the same on all current GeForce and Radeon graphics cards. We turned off proprietary settings for the objectivity of the conclusions, and the settings with ray-tracing graphics are tested separately, as lower class GPUs do not support them. You will find their results in the complementary chapters. In addition to native ray-tracing, also after deploying Nvidia DLSS (2.0) and AMD FidelityFX CAS.

If the game has a built-in benchmark, we use that one (the only exception is Forza Horizon 4, where due to its instability – it used to crash here and there – we drive on our track), in other cases the measurements take place on the games’ own scenes. From those we capture the times of consecutive frames in tables (CSV) via OCAT, which FLAT interprets into intelligible fps speech. Both of these applications are from the workshop of colleagues from the gpureport.cz magazine. In addition to the average frame rate, we also write the minimum in the graphs. That contributes significantly to the overall gaming experience. For the highest possible accuracy, all measurements are repeated three times and the final results form their average value.

Computational tests

Testing the graphics card comprehensively, even in terms of computing power, is more difficult than drawing conclusions from the gaming environment. Just because such tests are usually associated with expensive software that you don’t just buy for the editorial office. On the other hand, we’ve found ways to bring the available computing performance to you. On the one hand, thanks to well-built benchmarks, on the other hand, there are also some freely available and at the same time relevant applications, and thirdly, we have invested something in the paid ones.

The tests begin with ComputeBench, which computes various simulations (including game graphics). Then we move on to the popular SPECviewperf benchmark (2020), which integrates partial operations from popular 2D and 3D applications, including 3Ds max and SolidWorks. Details on this test package can be found at spec.org. From the same team also comes SPECworkstation 3, where GPU acceleration is in the Caffe and Folding@Home tests. You can also find the results of the LuxMark 3.1 3D render in the graphs, and the remarkable GPGPU theoretical test also includes AIDA64 with FLOPS, IOPS and memory speed measurements.

For obvious reasons, 3D rendering makes the largest portion of the tests. This is also the case, for example, in the Blender practical tests (2.91). In addition to Cycles, we will also test the cards in Eevee and radeon ProRender renderers (let AMD have a related test, as most are optimized for Nvidia cards with proprietary CUDA and OptiX frameworks). Of course, an add-on for V-ray would also be interesting, but at the moment the editorial office can’t afford it, we may manage to get a “press” license in time, though, we’ll see. We want to expand application tests in the future. Definitely with some advanced AI testing (we haven’t come up with a reasonable way yet), including noise reduction (there would be some ideas already, but we haven’t incorporated those due to time constraints).

Graphics cards can also be tested well in photo editing. To get an idea of the performance in the popular Photoshop, we’re using a script in PugetBench, which simulates real work with various filters. Among them are those that use GPU acceleration. A comprehensive benchmark suggesting the performance of raster and vector graphics is then also used in alternative Affinity Photo. In Lightroom, there are remarkable color corrections (Enhance Details) of raw uncompressed photos. We apply these in batches to a 1 GB archive. All of these tasks can be accelerated by both GeForce and Radeon.

From another perspective, there are decryption tests in Hashcat with a selection of AES, MD5, NTLMv2, SHA1, SHA2-256/512 and WPA-EAPOL-PBKDF2 ciphers. Finally, in the OBS and XSplit broadcast applications, we measure how much the game performance will be reduced while recording. It is no longer provided by shaders, but by coders (AMD VCE and Nvidia Nvenc). These tests show how much spare performance each card has for typical online streaming.

There are, of course, more hardware acceleration options, typically for video editing and conversion. However, this is purely in the hands of encoders, which are always the same within one generation of cards from one manufacturer, so there is no point in testing them on every graphics card. It is different across generations and tests of this type will sooner or later appear. Just fine-tuning the metric is left, where the output will always have the same bitrate and pixel match. This is important for objective comparisons, because the encoder of one company/card may be faster in a particular profile with the same settings, but at the expense of the lower quality that another encoder has (but may not have, it’s just an example).

Methodology: how we measure power draw

We have been tuning the method of measuring power draw for quite a long time and we will also be tuning it for some time. But we already have gimmicks that we can work with happily.

To get the exact value of the total power draw of the graphics card, it is necessary to map the internal power draw on the PCI Express slot and the external one on the additional power supply. For the analysis of the PCIe slot, it was necessary to construct an in-between card on which the power draw measurement takes place. Its basis is resistors calibrated to the exact value (0.1 Ω) and according to the amount of their voltage drop we can calculate the current. We then substitute it into the formula for the corresponding value of the output voltage ~ 12 V and ~ 3.3 V. The voltage drop is so low that it doesn’t make the VRM of the graphics card unstable and the output is still more than 12/3.3 V.

We measure power consumption on the card between the graphics card and the PCI Express slot. Rado Kopera took care of the design and implementation (thank you!)

We are also working on a similar device for external power supply. However, significantly higher currents are achieved there, longer cabling and more passages between connectors are necessary, which means that the voltage drop will have to be read on an even smaller resistance of 0.01 Ω, the current state (with 0.1 Ω) is unstable for now. Until we fine-tune it, we will use Prova 15 current clamp for cable measurements, which also measures with good accuracy, they just have a range of up to 30 A. But that is also enough for the OC version of the RTX 3090 Gaming X Trio. If a card is over the range, it is always possible to split the consumption measurement (first into one half and then into the other half of the 12 V conductors).

And why bother with such devices at all when Nvidia has a PCAT power draw analyzer? For complete control over the measurements. While our devices are transparent, the Nvidia’s tool uses the processor that can (but of course does not have to) affect the measurements. After testing the AMD graphics card on the Nvidia’s tool, we probably wouldn’t sleep well.

To read and record measurements, we use a properly calibrated multimeter UNI-T UT71E, which exports samples to XLS. From it we obtain the average value and by substituting into the formula with the exact value of the subcircuit output voltages we obtain the data for the graphs.

We will analyze the line graphs with the waveforms for each part of the power supply separately. Although the 3.3 V value is usually negligible, it needs to be monitored. It is difficult to say what exactly this subcircuit powers, but usually the consumption on it is constant and when it changes only with regard to whether a static or dynamic image is rendered. We measure consumption in two sort of demanding games (F1 2020 and Shadow of the Tomb Raider) and one less demanding one (CS:GO) with the highest graphic details preset and UHD resolution (3840 × 2560 px). Then in 3D rendering in Blender using the Cycles renderer on the famous Classroom scene. However, in addition to high-load tests, it’s important to know your web browser consumption (which, in our case, is accelerated Google Chrome), where we also spend a lot of time watching videos or browsing the web. The usual average load of this type is represented by the FishIE Tank (HTML5) website with 20 fish and the web video in our power draw tests is represented by a sample with the VP9 codec, data rate of 17.4 mb/s and 60 fps. In contrast, we also test offline video consumption, in VLC player on a 45 HEVC sample (45.7 mb/s, 50 fps). Finally, we also record the power consumption of the graphics card on the desktop of idle Windows 10 with one or two active UHD@60 Hz monitors.

Noise measurement…

Noise, as well as other operating characteristics, which we will focus on, we’re measuring in the same modes as consumption, so that the individual values overlap nicely. In addition to the level of noise produced, we also record the frequency response of the sound, the course of the GPU clock speed and its heating.

In this part of the methodology description, we will present something about the method of noise measurement. We use a Reed R8080 sound level meter, which we continuously calibrate with a calibrated Voltcraft SLC-100 digital sound level meter. A small addition to the sound level meter is a parabola-shaped collar, which has two functions. Increases the sensitivity to distinguish the sound produced even at very low speeds. It is thus possible to better compare even very quiet cards with the largest possible ratio difference. Otherwise (without this adjustment) it could simply happen that we measured the same noise level across several graphics cards, even though it would actually be a little different. This parabolic shield also makes sense because, from the outer convex side (from the back), it reflects all the parasitic sounds that everyone who really aims for accuracy of the measurements struggles with during the test. These are various cracks of the body or objects in the room during normal human activity.

To ensure the same conditions when measuring the noise level (and later also the sound), we use acoustic panels with a foam surface around the bench-wall. This is so that the sound is always reflected to the sound level meter sensor in the same way, regardless of the current situation of the objects in the test room. These panels are from three sides (top, right and left) and their purpose is to soundproof the space in which we measure the noise of graphics cards. Soundproofing means preventing different reflections of sound and oscillations of waves between flat walls. Don’t confuse it with sound-absorbing, we’ve had that solved well in the test lab for a long time.

During the measurements, the sound level meter sensor is always placed on a tripod at the same angle and at the same distance (35 cm) from the PCI Express slot in which the graphics card is installed. Of course, it’s always closer to the card itself, depending on its depth. The indicated reference point and the sensor angles are fixed. In addition to the “aerodynamic noise” of the coolers, we also measure the noise level of whining coils. Then we stop the fans for a moment. And for the sake of completeness, it should be added that during sound measurements, we also switch off the power supply fan as well as the CPU cooler fan. Thus, purely the graphics card is always measured without any distortion by other components.

… and the sound frequency response

From the same place, we also measure the frequency of the sound produced. One thing is the noise level (or sound pressure level in decibels) and the other thing is its frequency response.

According to the data on the noise level, you can quickly find out whether the graphics card is quieter or noisier, or where it is on the scale, but it is still a mix of different frequencies. Thus, it does not say whether the sound produced is more booming (with a lower frequency) or squeaking (with a high frequency). The same 35 dBA can be pleasant but also unpleasant for you under certain circumstances – it depends on each individual how they perceive different frequencies. For this reason, we will also measure the frequency response of the sound graphics card in addition to the noise level, via the TrueRTA application. The results will be interpreted in the form of a spectrograph with a resolution of 1/24 octave and for better comparison with other graphics cards we will include the dominant frequency of lower (20–200 Hz), medium (201–2,000 Hz) and higher (2,001–20,000 Hz) sound spectrum into standard bar graphs. For measurements, we’re using a calibrated miniDSP UMIK-1 microphone, which accurately copies the position of the sound level meter, but also has a collar, even with the same focal length.

At the end of this chapter, it should be noted that measurements of noise and frequency response of sound will be performed on most cards only in load tests, as out of load and at lower load (including video decoding) operation is usually passive with fans turned off. On the other hand, we must also be prepared for exceptions with active operation in idle or graphics cards with dual BIOS setup, from which the more powerful one never turns off the fans and they run at least at minimum speed. Finally, as with measuring the noise level in one of the tests, we also record the frequency response of whining coils. But don’t expect any dramatic differences here. It will usually be one frequency, and the goal is rather to detect any potential anomalies. The sound of the whining coils is of course variable, depending on the scene, but we always measure in the same scene (in CS:GO@1080p).

Methodology: temperature tests

We’re also bringing you heat tests. You are at HWCooling after all. However, in order to make it sensible at all to monitor temperatures on critical components not only of the graphics card, but anything in the computer, it is important to simulate a real computer case environment with healthy air circulation. The overall behavior of the graphics card as such then follows from this. In many cases, an open bench-table is inappropriate and results can be distorted. Therefore, during all, not only heat tests, but also measurement of consumption or course of graphics core frequencies, we use a wind tunnel with equilibrium flow.

Two Noctua NF-S12A fans are at the inlet and the same number is on the exhaust. When testing various system cooling configurations, this proved to be the most effective solution. The fans are always set to 5 V and the speed corresponds to approx. 550 rpm. The stability of the inlet air is properly controlled during the tests, the temperature being between 21 and 21.3 °C at a humidity of ±40%.

We read the temperature from the internal sensors via GPU-Z. This small, single-purpose application also allows you to record samples from sensors in a table. From the table, it is then easy to create line graphs with waveforms or the average value into bar graphs. We will not use the thermal camera very much here, as most graphics cards have a backplate, which makes it impossible to measure the PCB heating. The key for the heating graphs will be the temperature reading by internal sensors, according to which, after all, the GPU frequency control also takes place. It will always be the heating of the graphics core, and if the sensors are also on VRAM and VRM, we will extract these values into the article as well.

Test rig

RAM Patriot Blackout (4× 8 GB, 3600 MHz/CL18)

2× SSD Patriot Viper VPN100 (512 GB + 2 TB)

Power supply BeQuiet! Dark Power Pro 12 1200 W


Test configuration
Processor	AMD Ryzen 9 5900X
CPU Cooler	Noctua NH-U14S@12 V s NT-H2
Motherboard	MSI MEG X570 Ace
Memory (RAM)	Patriot Blackout, 4× 8 GB, 3600 MHz/CL18
SSD	2× Patriot Viper VPN100 (512 GB + 2 TB)
PSU	BeQuiet! Dark Power Pro 12 (1200 W)

/* Here you can add custom CSS for the current table */ /* Lean more about CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets */ /* To prevent the use of styles to other tables use "#supsystic-table-979" as a base selector for example: #supsystic-table-979 { ... } #supsystic-table-979 tbody { ... } #supsystic-table-979 tbody tr { ... } */

Note.: At the time of testing, graphics drivers AMD Adrenalin 21.3.1 are used and the OS Windows 10 Enterprise build is 19042.

3DMark

For the tests we’re using 3DMark Professional and the Night Raid (DirectX12) is suitable for comparing weaker GPUs, for more powerful ones there is Fire Strike (DirectX11) and Time Spy (DirectX12).

Age of Empires II: DE

Test platform benchmark, API DirectX 11; graphics settings preset Ultra; no extra settings.

Assassin’s Creed: Valhalla

Test platform benchmark; API DirectX 12; graphics settings preset Ultra High; no extra settings.

Battlefield V

Test platform custom scene (War stories/Under no flag); API DirectX 12, graphics settings preset Ultra; TAA high; no extra settings.

Battlefield V with DXR

Test platform custom scene (War stories/Under no flag); API DirectX 12, graphics settings preset Ultra; TAA high; extra settings DXR.

Note: The game also supports DLSS for upscaling and sharpening, but due to the relatively low hardware requirements in the native settings, we will not address them in standard tests. However, measurements on request are possible if you ask for it.

Borderlands 3

Test platform benchmark; API DirectX 12, graphics settings preset Ultra; TAA; no extra settings.

Control

Test platform custom scene (chapter Polaris); API DirectX 11, graphics settings preset High; no extra settings.

Control with DXR

Test platform custom scene (chapter Polaris); API DirectX 12, graphics settings preset High; extra settings DXR.

DXR (native)

Counter Strike: GO

Test platform benchmark (Dust 2 map tour); API DirectX 9, graphics settings preset High; 4× MSAA; no extra settings.

Cyberpunk 2077

Test platform custom scene (Little China); API DirectX 12, graphics settings preset Ultra; no extra settings.

Cyberpunk 2077 with FidelityFX CAS

Test platform custom scene (Little China); API DirectX 12, graphics settings preset Ultra; extra settings FidelityFX CAS.

FidelityFX CAS (50%)

Cyberpunk 2077 with DXR

Test platform custom scene (Little China); API DirectX 12, graphics settings preset Ultra; extra settings DXR with DLSS and FidelityFX CAS.

DXR

Note: The combination of ray-tracing graphics with FidelityFX CAS does not work stably. Although the GPU renders a few frames, then the image freezes and the game crashes. We’ve discussed it before in a separate article, where we wrote about how the new patch 1.2 affected the performance. Among other things, it introduced ray tracing support for Radeon.

DOOM Eternal

Test platform custom scene; API Vulkan, graphics settings preset Ultra Nightmare; no extra settings.

F1 2020

Test platform benchmark (Australia, Clear/Dry, Cycle); API DirectX 12, graphics settings preset Ultra High; TAA; extra settings Skidmarks blending off*.

*on GeForce graphics cards, the Skidmarks blending option is disabled. This option is missing on AMD graphics cards. However, the overall quality of Skidmarks is otherwise set to High on both GeForce and AMD.
Note: The game also supports DLSS 2.0 and FidelityFX for upscaling and sharpening, but due to the relatively low hardware requirements in the native settings, we will not address them in standard tests. However, measurements on request are possible if you ask for it.

FIFA 21

Test platform custom scene (Autumn/Fall, Overcast, 9pm, Old Trafford); API DirectX 12, graphics settings preset Ultra; no extra settings.

Forza Horizon 4

Test platform custom scene; API DirectX 12, graphics settings preset Ultra; 2× MSAA; no extra settings.

Mafia: DE

Test platform custom scene (from the Salieri’s Bar parking lot to the elevated railway gate); API DirectX 11, graphics settings preset High; no extra settings.

Metro Exodus

Test platform benchmark; API DirectX 12, graphics settings preset Extreme; no extra settings.

Metro Exodus with DXR

Test platform benchmark; API DirectX 12, graphics settings preset Ultra; extra settings DXR.

DXR (native)

Microsoft Flight Simulator

Test platform custom scene (Paris-Charles de Gaulle, Air Traffic: AI, February 14, 9:00 am) autopilot: from 1000 until hitting the terrain; API DirectX 11, graphics settings preset Ultra; TAA; extra settings Motion Blur off.

Red Dead Redemption 2 (Vulkan)

Test platform custom scene; API Vulkan, graphics settings preset Favor Quality; no extra settings.

Red Dead Redemption 2 (Dx12)

Test platform custom scene; API DirectX 12, graphics settings preset Favor Quality; no extra settings.

Shadow of the Tomb Raider

Test platform custom scene; API DirectX 12, graphics settings preset Highest; TAA; no extra settings.

Shadow of the Tomb Raider with DXR

Test platform benchmark; API DirectX 12, graphics settings preset Highest; extra settings DXR.

Note: This game also supports DLSS and FidelityFX CAS, but since this is an older title and there are more than enough tests, we will not address this setting in standard tests. However, testing on request is possible if you ask for it.

Total War Saga: Troy

Test platform benchmark; API DirectX 11, graphics settings preset Ultra; 4× AA, no extra settings.

Wasteland 3

Test platform custom scene; API DirectX 11, graphics settings preset Ultra; no extra settings.

Overall game performance

Performance per euro

CompuBench 2.0 (OpenCL)

Test platform benchmark; API OpenCL; no extra settings.

Game Effects

Advanced Compute

High Quality Computer Generated Imagery and Rendering

Computer Vision

SPECviewperf 2020

Test platform benchmark; API OpenGL and DirectX; no extra settings.

SPECworkstation 3

FLOPS, IOPS and memory speed tests

Test platform benchmark; app version 6.32.5600; no extra settings.

LuxMark

Test platform benchmark; API OpenCL; no extra settings.

Blender@Cycles

Test platform render BMW and Classroom; renderer Cycles, 12 tiles; extra settings OpenCL.

Blender@Radeon ProRender

Test platform render BMW and Classroom; renderer Radeon ProRender, 1024 samples; extra settings OpenCL.

Blender@Eevee

Test platform animation render Ember Forest; renderer Eevee, 350 images; extra settings OpenCL.

Photo editing

Adobe Photoshop: Test platform PugetBench; no extra settings.

Affinity Photo: Test platform built-in benchmark; no extra settings.

Adobe Lightroom: Test platform custom1-gigabyte archive of 42 raw photos (CR2) taken on DSLR; no extra settings.

Broadcasting

OBS Studio and XSplit: Test platform F1 2020 benchmark; extra settings: enabled encoders AMD VCE/Nvidia Nvenc (AVC/H.264), output resolution 2560 × 1440 px (60 fps), target bitrate 19,700 kbps.

Password cracking

Test platform Hashcat; no extra settings. You can easily try the tests yourself. Just download the binary and enter the cipher you are interested in using the numeric code on the command line.

GPU clock speed

GPU temperatures

Net graphics power draw

Performance per watt

Analysis of 12 V subcircuit power supply (higher load)

Analysis of 12 V subcircuit power supply (lower load)

Analysis of 3.3 V subcircuit power supply

A view of the in-between card for power draw measurement from the PCI Express slot. 3.3 V subcircuit

Noise level

Frequency response of sound

Measurements are performed in the TrueRTA application, which records sound in a range of 240 frequencies in the recorded range of 20–20,000 Hz. For the possibility of comparison across articles, we export the dominant frequency from the low (20–200 Hz), medium (201–2,000 Hz) and high (2,001–20,000 Hz) range to standard bar graphs. However, for an even more detailed analysis of the sound expression, it is important to perceive the overall shape of the graph and the intensity of all frequencies/tones.

The microphone we use to analyze the sound of coolers and coils


Graphics card	Dominant sound freq. and noise level in F1 2020@2160p	NF-F12 PWM		NF-A15 PWM
	Low range		Mid range		High range
	Frequency [Hz]	Noise level [dBu]	Frequency [Hz]	Noise level [-dBu]	Frequency [Hz]	Noise level [-dBu]
Sapphire RX 6700 XT Nitro+ (P), ReBAR on	100,794	-73,224	1076,347	-71,246	7034,643	-76,524
Sapphire RX 6700 XT Nitro+ (P), ReBAR off	100,794	-75,199	1076,347	-73,483	7034,643	-76,501
MSI RTX 3060 Ti Gaming X Trio, ReBAR off	100,794	-70,608	1107,887	-82,797	7034,643	-83,730
Gigabyte RTX 3060 Eagle OC 12G, ReBAR off	100,794	-71,611	213,574	-64,261	2031,873	-74,162
MSI RTX 3090 Gaming X Trio, ReBAR off	100,794	-72,330	1076,347	-75,992	4561,401	-81,229
MSI RTX 3070 Gaming X Trio, ReBAR off	100,794	-73,926	1076,347	-79,719	6267,154	-85,076
AMD Radeon RX 6800, ReBAR on	100,794	-71,019	1076,347	-66,494	9665,273	-81,252
AMD Radeon RX 6800, ReBAR off	100,794	-71,759	1107,887	-67,416	2091,412	-75,288
TUF RTX 3080 O10G Gaming, ReBAR off	100,794	-76,045	1107,887	-77,850	7034,643	-74,423
AMD Radeon RX 6800 XT, ReBAR on	100,794	-71,589	1107,887	-74,742	10848,902	-76,306
AMD Radeon RX 6800 XT, ReBAR off	100,794	-72,991	1107,887	-74,724	10848,902	-76,519

/* Here you can add custom CSS for the current table */ /* Lean more about CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets */ /* To prevent the use of styles to other tables use "#supsystic-table-854" as a base selector for example: #supsystic-table-854 { ... } #supsystic-table-854 tbody { ... } #supsystic-table-854 tbody tr { ... } */


Graphics card	Dominant sound freq. and noise level in SOTTR@2160p	NF-F12 PWM		NF-A15 PWM
	Low range		Mid range		High range
	Frequency [Hz]	Noise level [dBu]	Frequency [Hz]	Noise level [-dBu]	Frequency [Hz]	Noise level [-dBu]
Sapphire RX 6700 XT Nitro+ (P), ReBAR on	100,794	-73,918	1140,350	-75,427	5915,406	-77,227
Sapphire RX 6700 XT Nitro+ (P), ReBAR off	100,794	-75,137	1107,887	-75,221	5915,406	-76,482
MSI RTX 3060 Ti Gaming X Trio, ReBAR off	100,794	-70,764	1076,347	-83,630	7034,643	-81,871
Gigabyte RTX 3060 Eagle OC 12G, ReBAR off	100,794	-71,937	213,574	-64,455	2031,873	-73,841
MSI RTX 3090 Gaming X Trio, ReBAR off	106,787	-74,468	213,574	-71,307	4561,401	-79,260
MSI RTX 3070 Gaming X Trio, ReBAR off	100,794	-72,952	213,574	-72,275	6267,154	-84,919
AMD Radeon RX 6800, ReBAR on	100,794	-71,769	1140,350	-66,111	9948,487	-81,293
AMD Radeon RX 6800, ReBAR off	100,794	-71,603	1140,350	-67,765	9665,273	-80,642
TUF RTX 3080 O10G Gaming, ReBAR off	100,794	-75,410	1076,347	-72,321	7240,773	-74,199
AMD Radeon RX 6800 XT, ReBAR on	100,794	-73,222	1107,887	-73,892	10848,902	-76,328
AMD Radeon RX 6800 XT, ReBAR off	100,794	-73,170	1107,887	-75,262	10848,902	-75,397

/* Here you can add custom CSS for the current table */ /* Lean more about CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets */ /* To prevent the use of styles to other tables use "#supsystic-table-855" as a base selector for example: #supsystic-table-855 { ... } #supsystic-table-855 tbody { ... } #supsystic-table-855 tbody tr { ... } */


Graphics card	Dominant sound freq. and noise level in CS:GO@2160p	NF-F12 PWM		NF-A15 PWM
	Low range		Mid range		High range
	Frequency [Hz]	Noise level [dBu]	Frequency [Hz]	Noise level [-dBu]	Frequency [Hz]	Noise level [-dBu]
Sapphire RX 6700 XT Nitro+ (P), ReBAR on	100,794	-72,597	1173,765	-74,862	5915,406	-74,613
Sapphire RX 6700 XT Nitro+ (P), ReBAR off	100,794	-75,012	1107,887	-73,798	5747,006	-74,232
MSI RTX 3060 Ti Gaming X Trio, ReBAR off	100,794	-71,442	1107,887	-83,097	6267,154	-82,469
Gigabyte RTX 3060 Eagle OC 12G, ReBAR off	100,794	-72,601	213,574	-64,794	2031,873	-73,810
MSI RTX 3090 Gaming X Trio, ReBAR off	106,787	-75,721	213,574	-73,423	4695,061	-77,625
MSI RTX 3070 Gaming X Trio, ReBAR off	106,787	-75,721	213,574	-73,423	6267,154	-82,711
AMD Radeon RX 6800, ReBAR on	100,794	-71,162	1107,887	-66,232	9948,487	-77,428
AMD Radeon RX 6800, ReBAR off	100,794	-71,103	1076,347	-77,328	9665,273	-77,714
TUF RTX 3080 O10G Gaming, ReBAR off	100,794	-74,208	1076,347	-70,919	7240,773	-74,402
AMD Radeon RX 6800 XT, ReBAR on	100,794	-72,999	1107,887	-74,302	7671,332	-72,419
AMD Radeon RX 6800 XT, ReBAR off	100,794	-72,346	1107,887	-73,732	10848,902	-72,534

/* Here you can add custom CSS for the current table */ /* Lean more about CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets */ /* To prevent the use of styles to other tables use "#supsystic-table-856" as a base selector for example: #supsystic-table-856 { ... } #supsystic-table-856 tbody { ... } #supsystic-table-856 tbody tr { ... } */


Graphics card	Dominant sound freq. and noise level in Blender (Cycles), Classroom	NF-F12 PWM		NF-A15 PWM
	Low range		Mid range		High range
	Frequency [Hz]	Noise level [dBu]	Frequency [Hz]	Noise level [-dBu]	Frequency [Hz]	Noise level [-dBu]
Sapphire RX 6700 XT Nitro+ (P), ReBAR on	100,794	-72,645	1173,765	-86,606	5915,406	-82,388
Sapphire RX 6700 XT Nitro+ (P), ReBAR off	100,794	-75,786	1076,347	-87,229	5915,406	-82,066
MSI RTX 3060 Ti Gaming X Trio, ReBAR off	100,794	-70,442	987,015	-89,548	6450,796	-88,958
Gigabyte RTX 3060 Eagle OC 12G, ReBAR off	100,794	-72,605	213,574	-70,007	2031,873	-79,089
MSI RTX 3090 Gaming X Trio, ReBAR off	100,794	-71,224	1076,347	-85,314	5915,406	-91,953
MSI RTX 3070 Gaming X Trio, ReBAR off	100,794	-71,224	1076,347	-85,314	18245,606	-90,785
AMD Radeon RX 6800, ReBAR on	100,794	-71,913	987,015	-89,190	7452,944	-88,332
AMD Radeon RX 6800, ReBAR off	100,794	-71,136	987,015	-89,041	7452,944	-88,237
TUF RTX 3080 O10G Gaming, ReBAR off	106,787	-81,541	1659,995	-80,568	6834,380	-77,967
AMD Radeon RX 6800 XT, ReBAR on	97,924	-79,763	1208,159	-89,625	7671,332	-85,188
AMD Radeon RX 6800 XT, ReBAR off	100,794	-72,980	1243,561	-95,235	7671,332	-84,980

/* Here you can add custom CSS for the current table */ /* Lean more about CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets */ /* To prevent the use of styles to other tables use "#supsystic-table-857" as a base selector for example: #supsystic-table-857 { ... } #supsystic-table-857 tbody { ... } #supsystic-table-857 tbody tr { ... } */


Graphics card	Dominant sound freq. and noise level in CS:GO@1080p (coils only)	NF-F12 PWM		NF-A15 PWM
	Low range		Mid range		High range
	Frequency [Hz]	Noise level [dBu]	Frequency [Hz]	Noise level [-dBu]	Frequency [Hz]	Noise level [-dBu]
Sapphire RX 6700 XT Nitro+ (P), ReBAR on	100,794	-74,648	987,015	-84,777	5747,006	-69,614
Sapphire RX 6700 XT Nitro+ (P), ReBAR off	100,794	-74,670	1395,850	-88,408	5747,006	-70,289
MSI RTX 3060 Ti Gaming X Trio, ReBAR off	100,794	-73,006	2152,695	-86,379	6267,154	-83,576
Gigabyte RTX 3060 Eagle OC 12G, ReBAR off	100,794	-73,575	1974,030	-90,249	6088,740	-83,145
MSI RTX 3090 Gaming X Trio, ReBAR off	50,397	-76,126	987,015	-84,836	5915,406	-83,323
MSI RTX 3070 Gaming X Trio, ReBAR off	100,794	-74,662	1317,507	-81,448	6088,740	-84,631
AMD Radeon RX 6800, ReBAR on	100,794	-71,813	987,015	-87,658	7452,944	-80,420
AMD Radeon RX 6800, ReBAR off	100,794	-72,013	1659,955	-90,354	8863,094	-84,530
TUF RTX 3080 O10G Gaming, ReBAR off	100,794	-75,576	1140,350	-81,739	9948,487	-78,734
AMD Radeon RX 6800 XT, ReBAR on	100,794	-73,593	1659,955	-79,766	7452,944	-73,997
AMD Radeon RX 6800 XT, ReBAR off	100,794	-73,272	1659,955	-83,327	7452,944	-76,372

/* Here you can add custom CSS for the current table */ /* Lean more about CSS: https://en.wikipedia.org/wiki/Cascading_Style_Sheets */ /* To prevent the use of styles to other tables use "#supsystic-table-858" as a base selector for example: #supsystic-table-858 { ... } #supsystic-table-858 tbody { ... } #supsystic-table-858 tbody tr { ... } */

Conclusion

We have performed hundreds of comparative tests that give a clear picture of where active Resizable BAR takes the RX 6700 Nitro+. From a sample of 18 up-to-date games in FHD and QHD resolutions, you get an average of 9% fps boost. We’ve noticed significant performance boost in CS:GO – in FullHD up to 30 %. In UHD (4K) it’s ”only” 20% and for this resolution, we also have a remarkable intersection with power

draw, which has increased by 18.7 W, which represents a 9% increase. This means that with Resizable BAR, clearly higher efficiency is achieved here (performance per watt). Similarly, although not so significantly, it also applies to more challenging games F1 2020 and Shadow of The Tomb Raider.

In terms of modern AAA games, the most significant increase in performance is in Forza Horizon 4 (21–31 %), Borderlands 3 (7–14 %) or Assassin’s Creed: Valhalla (9–14 %), where it is always true that the higher percentage belongs to the lowest tested FHD resolution. At this point, we want to apologize to our readers for one misinformation from our previous test of the RX 6700 XT. Everything is fixed now, but at the end it was that in AC:V, the RX 6700 XT, for unclear reasons, significantly beat even more powerful cards. In the end, these results were incorrect, caused by the failure of the human factor and poor control of some tuned graphics settings after a game update. We therefore apologize once again for this error. Performance of the RX 6700 XT in Assassin’s Creed: Valhalla is 8 (FHD) to 17% (UHD) below the RX 6800.

We’ve also measured bonus fps in Battlefield V, but more than the fps without ray tracing (where the frame rate in the target resolution is still three-digit), results with RTX (DXR, Ultra) are more interesting. At values around 50 fps, we’re speaking about more and less comfortable playing. Anyway, we’re still at around the performance of otherwise a class slower RTX 3060.

In the optimal resolution of QHD (2560 × 1440 px) for the RX 6700 XT, there are some improvements in games like Cyberpunk 2077 (5%), Mafia: DE (4 %), Red Dead Redemption 2 (7 % using Vulkan, or 5 % using Dx12), SOTTR (6 %) or Total War Saga: Troy (6 %).

However, it is important to point out all the small downsides in application performance. The differences are usually negligible and are almost always slower times, you rarely come across a test where it would be the other way around. However, with Resizable BAR enabled, we measured significantly worse results in one of the subtasks in CompuBench, TV-L1 Optical Flow (-60 %) and -6 % FLOPS of Double-Precision performance is also stated in AIDA64. When ReBAR no longer can increase application performance, it will be interesting to see when (and if at all) it stops decreasing it. It is also possible that the differences are recognized as so small or rare that the developers will simply not bother with them, we’ll keep track of it and see what happens.

We’ve got the test games from Jama levova

Continue: Control with DXR