We came away from our revisit of the once-king Sandy Bridge 2600K and 2500K CPUs impressed by the staying power of products that came out in Q1 2011, considering Intel’s unimpressive gains since that time.
At the time of Sandy Bridge’s release, AMD’s flagship CPUs were 45nm K10-based Phenom IIs, designed to compete in price/performance with the 45nm Lynnfield (Nehalem i5) quad cores. Later that year, AMD’s underwhelming Bulldozer architecture would launch and inevitably replace the Phenom line. Given that we’ve already looked at Intel’s 1Q11 offerings, we decided to revisit AMD’s Phenom II CPUs in 2017, including the Phenom II X6 1090T (Black Edition) and Phenom II X6 1055T. These benchmarks look at AMD Phenom II performance in gaming and production workloads for the modern era, including comparisons to the equal-aged Sandy Bridge CPUs, modern Ryzen 5 & 7 CPUs, and modern Intel CPUs.
Historical Recap of the Phenom II Launch
Two Phenom II X6 CPUs launched in April of 2010: the 1090T (Black Edition) and the 1055T, which are the samples we’ll be revisiting. The 1090T was $295 and the 1055T was $199, but by December of 2011 (post-Bulldozer) it had dropped to $150 on Newegg, which is when we bought the 1055T sample used in this review. The 1055T may not have increased in price by 35% like the G.Skill 2x4GB kit that we bought with it, but it is still going for $60-70 used, and the 1090T purchased for this review was $100. Newegg may no longer be selling them new, but the ratings on the old product pages give a hint as to why they’ve held value: 90% of the 758 reviews for the 1055T and 91% of the 1,680 reviews for the 1090T are 5 eggs.
Anand Shimpi himself wrote a sort-of-maybe-positive review, which is a great indication of how they compared to Intel’s quad cores in 2010: better at production, worse at lightly threaded applications, i.e. gaming (sounds familiar). Price/performance isn’t really relevant to a part that can’t be purchased new, but Phenom II X6s do have six cores and a reputation for overclocking. At launch, a cheap hex-core CPU would have been a huge boon in production but largely irrelevant to older games limited to four threads; in modern games it could actually help, as it does with the 6C/12T 1600X in Watch_Dogs 2 and AOTS. There’s always speculation about higher core counts paying off in the future, and that’s what we’re interested in testing with this revisit: the longevity of the Phenom II X6s, as we saw the advantages held by the 2600K over the 2500K in our last revisit.
Throughout 2010, both faster and slower X6 processors were introduced: 1035T, 1045T, a different 1055T SKU, 1065T, 1075T, and the top-of-the-line 1100T Black Edition. That may seem like a lot of variety, but there’s barely any difference in specs outside of base/boost frequency, and a different TDP in the case of the two 1055T SKUs. The naming convention is simply higher number = faster, and T simply stands for Thuban. Even Black Edition CPUs aren’t necessarily “better,” but they do have an unlocked multiplier, making the process of overclocking much simpler. There were higher frequency Phenom II X4 processors around at launch, but the major advantages of the X6s were the higher core count and the reintroduction of Turbo Core technology, the now-familiar ability of a CPU to boost its frequency on a limited number of cores (three, in this case) while limiting others. This has interesting implications for overclocking: a primary reason for limited-core boosting is to keep temperatures and voltages within acceptable limits, but we have a modern Kraken X62 strapped to our bench, helping bypass thermal constraints.
CPU TESTING METHODOLOGY
GAME TEST METHODOLOGY
NVIDIA 376.33 drivers were used for benchmarking. Game settings were manually controlled for the DUT. All games were run at presets defined in their respective charts. All other game settings are defined in respective game benchmarks, which we publish separately from GPU and CPU reviews. Our test courses, in the event manual testing is executed, are also uploaded within that content. This allows others to replicate our results by studying our bench courses.
Windows 10-64 build 14393.1066 was used for testing.
Some benchmarks disable EIST, Turbo, and other features -- please check each section to learn if that is the case. Otherwise, for game benchmarks, assume stock settings (Turbo enabled). We always disable C-states.
Average FPS, 1% low, and 0.1% low times are measured. We do not report maximum or minimum FPS results as we consider these numbers to be pure outliers. Instead, we take an average of the lowest 1% of results (1% low) to show real-world, noticeable dips; we then take an average of the lowest 0.1% of results for severe spikes. GN originally coined the phrases “1% LOWs” and “0.1% LOWs” for these metrics.
EVGA Supernova 750 G2L 80+ Gold
HyperX Savage 32GB 2400MHz (4x8GB)
Corsair Force LE 240GB SSD
Open Air Test Bench
EVGA GeForce GTX 1080 FTW
Note: fan and pump settings are configured on a per-test basis.
970 (RD9x0) Platform:
-ASUS 970 PRO GAMING/AURA
-Phenom II X6 1055T (125W TDP)
-Phenom II X6 1090T
Core Components (Unchanging)
- NZXT 1200W Hale90v2
- For DDR4 platforms: Corsair Vengeance LPX 32GB 3200MHz
- For DDR3 platforms: HyperX Savage 32GB 2400MHz (note: only 2133MHz was supported on our SNB platform)
- Intel 730 480GB SSD
- Open Air Test Bench
- Cooler #1 (Air): Be Quiet! Dark Rock 3
- Cooler #2 (Cheap liquid): Asetek 570LC w/ Gentle Typhoon fan (this is the one we used for this particular article)
- Cooler #3 (High-end): Kraken X62
- Video Card: EVGA GTX 1080 FTW1
- Note: fan and pump settings are configured on a per-test basis.
- MSI Gaming Pro Carbon
- i7-7700K (x2) samples from motherboard vendors
- i5-7600K purchased by GN
- MSI Gaming M7
- i7-6700K retail
- Gigabyte Z97X G1 WIFI-BK
- MSI GD65 Z77
- i5 3570K
- ASUS Crosshair VI
Dx12 games are benchmarked using PresentMon onPresent, with further data analysis from GN-made tools.
First, a disclaimer: these processors are only spec’d for up to 1333MHz memory, but our BIOS allowed us to select 1600MHz as a desired speed, and therefore our “stock” scores technically include a minor memory overclock. Memory was run at CL11 1600MHz in both “stock” configurations (remember, this is DDR3).
We referred to Dolk’s Phenom II OC guide throughout the process, which offers both a comprehensive guide to overclocking and an overview of Deneb and Thuban. As previously mentioned, the 1090T Black Edition was relatively trivial to overclock, and we followed our usual “typical user’s basic overclock” model. We disabled the turbo core feature (unhelpful when raising the overall frequency) and increased the multiplier until the CPU was running at 4.0GHz, set the NB frequency to 2600MHz (as per the guide), and limited the HTT frequency to 1400MHz, which seemed to help with stability without impacting performance at all.
There are many more ways to fine-tune the overclock, and they were necessary with the 1055T. The multiplier can’t be increased beyond 14 (14 x 200MHz FSB = 2.8GHz base clock), so the FSB speed needs to be adjusted instead, which then requires adjusting several other numbers. Our maximum stable overclock was 3.85GHz, with the settings described below. As a consequence, although our overclocked 1090T was running about 100MHz faster, the changes to memory speed and other settings occasionally gave the advantage to the 1055T. Still, after all that fiddling around, the 1090T’s greater launch price felt nearly justified (nearly).
|FSB||CPU multiplier||CPU frequency||CPU/NB||HTT||Memory||Latency|
|1055T||200MHz||14 (16.5 boost)||2.8-3.3GHz||2000Mhz||2000MHz||1600MHz||CL11|
|1090T||200MHz||16 (18 boost)||3.2-3.6GHz||2000MHz||2000MHz||1600MHz||CL11|