The Core i7-4770K Review: Haswell Is Faster; Desktop Enthusiasts Yawn
Intel's Haswell architecture is finally available in the flagship Core i7-4770K processor. Designed to drop into an LGA 1150 interface, does this new quad-core CPU warrant a complete platform replacement, or is your older Sandy Bridge-E system better?
Editor’s Note: Eager to show off what it's doing with Intel’s Haswell architecture, system builder CyberPower PC is offering the Tom’s Hardware audience an opportunity to win a new system based on Intel’s Core i7-4770K processor. Read through our review, and then check out the last page for more information on the system, plus a link to enter our giveaway!
Do you know what it’s like to be at the top of your game, the nearest competitor several strides behind? Well, maybe not. But Intel sure does. When it comes to desktop CPUs, the company’s top-end parts continue to stave off AMD's best efforts. That applies to raw performance andefficiency.
We love fast, and we love efficient. But we also like to see healthy competition driving innovation. And again, on the desktop, there’s not enough of that to push Intel. Ivy Bridge-based CPUs are generally a small step up from the generation prior. And although the Sandy Bridge architecture included a number of notable improvements, unprecedented integration gave away Intel’s growing focus on mobility. Even as we got our hands on great features like Quick Sync, Intel was chiseling away at its enthusiast equity by limiting overclocking to K-series SKUs.
Expect more of the same from Haswell. You're going to see notable per-clock performance improvements, faster graphics, and additional features able to accelerate specific workloads. But you’re also going to witness a clumsy handling of overclocking (again), some strange decisions on the graphics side (again), and incremental gains that’ll have some of us upgrading our desktops, but more folks looking for Haswell-powered mobile platforms.
That's entirely by design, by the way. An emphasis on power is front and center with Haswell. And as a result, this architecture is going to span the broadest range of devices Intel has ever touched with one design. But I’ll argue that enthusiasts on the desktop take a back seat to make it all possible.
Meet Haswell, Now Known As Intel’s Fourth-Gen Core Architecture
Intel is rolling out the details of its Haswell-based processors in a staggered launch. The company plans to ship multiple variations of the architecture across a number of different interfaces, from very low-power segments to very performance-sensitive ones. However, the only arrangement emerging today is the quad-core SoC. Technically, Intel is talking desktop and mobile, though we’re deliberately focusing on the Core i7-4770K desktop CPU. I published a preview of Core i7-4770K’s performance almost three months ago, and that story has some information about Intel’s plans as well.
Haswell-based quad-core processors will ship in two configurations to cover the mobile and desktop markets. Only one is ready today, though. That chip features the HD Graphics 4600 engine, also known as GT2. The second, with Iris Pro Graphics 5200 (or GT3e) is coming later. Intel's engineers claim that Iris Pro scales incredibly well given a lofty power ceiling and enough cooling. However, CPUs endowed with the higher-end graphics engine are BGA-only, meaning they’re soldered down. So, enthusiasts buying LGA 1150-equipped motherboards will only find Core i7 and Core i5 CPUs with four cores and HD Graphics 4600 (technically, there’s also a 35 W Core i5 with fewer cores, but it’s still under wraps).
This implementation of Haswell is composed of 1.6 billion transistors, up from a comparable Ivy Bridge configuration’s 1.4 billion. Optimized expressly for Intel’s 22 nm node, the die measures 177 square millimeters, just slightly larger than quad-core Ivy Bridge at 160 mm².
Put Ivy Bridge and Haswell right next to each other and you might have a difficult time telling them apart. After all, there’s “only” a 200 million-transistor delta separating the two. That 14% growth in transistor count largely comes from a 25% increase in graphics resources compared to last generation.
That’s not to say the processor cores go untouched. Intel says it put specific emphasis on speeding up both today’s legacy code as well as applications we’ll see in the future. To that end, larger buffers enlarge the out-of-order window, which means instructions that would have previously waited for execution can be located and processed sooner. Haswell’s window is 192 instructions. Sandy Bridge was 168. Nehalem was 128. The Haswell branch predictor is improved, too. This is something Intel manages to do every generation—and for good reason, since it simultaneously enables better performance and prevents the wasted work of a branch getting predicted incorrectly. Previously, Intel’s architecture was able to execute six operations per clock cycle. However, Haswell gets two additional ports (one integer ALU and one store), enabling up to eight operations per cycle. And workloads with large data sets should see a benefit from a larger L2 TLB.
All of those changes add up to significant improvement in Haswell’s IPC compared to Ivy Bridge. That’s where we expect most of the speed-up in general-purpose apps to come from this generation, since the top-end Core i7-4770K runs at the same 3.5 GHz as -3770K.
Sure enough, when we set five different processors (employing four different architectures) to the same constant 4 GHz, we see, first, how much more work Intel gets done compared to AMD and, second, a steady progression forward in Intel’s performance.
In addition to the two execution ports Intel adds to Haswell, ports one and two now feature 256-bit Fused Multiply-Add units, doubling the number of peak theoretical floating-point operations per cycle. Integer math gets a big boost as well from AVX2 instruction support.
Of course, multiplying the architecture’s compute potential means little if you can’t get data into the core fast enough. So, Intel also made a number of changes to its caches. Haswell’s L1 and L2 caches are the same size as they were in Ivy Bridge (there’s a 32 KB L1 data, 32 KB L1 instruction, and 256 KB L2 cache per core). Bandwidth to the caches is up to doubled, though, and we’ll see in our synthetic testing that the L1D is indeed quite a bit faster. Intel claims that it can do one read every cycle from the L2 (versus one read every other cycle in Ivy Bridge), but we aren’t able to replicate those figures in our own testing.
Cores / Threads | Base Freq. | Max. Turbo | L3 | HD Graphics | Graphics Max Freq. | TDP | Price | |
---|---|---|---|---|---|---|---|---|
Fourth-Gen Core i7 Family | ||||||||
4770T | 4/8 | 2.5 GHz | 3.7 GHz | 8 MB | 4600 | 1,200 MHz | 45 W | $303 |
4770S | 4/8 | 3.1 GHz | 3.9 GHz | 8 MB | 4600 | 1,200 MHz | 65 W | $303 |
4770 | 4/8 | 3.4 GHz | 3.9 GHz | 8 MB | 4600 | 1,200 MHz | 84 W | $303 |
4770K | 4/8 | 3.5 GHz | 3.9 GHz | 8 MB | 4600 | 1,250 MHz | 84 W | $339 |
4770R | 4/8 | 3.2 GHz | 3.9 GHz | 6 MB | Iris Pro 5200 | 1,300 MHz | 65 W | N/A |
4765T | 4/8 | 2.0 GHz | 3.0 GHz | 8 MB | 4600 | 1,200 MHz | 35 W | $303 |
Fourth-Gen Core i5 Family | ||||||||
4670T | 4/4 | 2.3 GHz | 3.3 GHz | 6 MB | 4600 | 1,200 MHz | 45 W | $213 |
4670S | 4/4 | 3.1 GHz | 3.8 GHz | 6 MB | 4600 | 1,200 MHz | 65 W | $213 |
4670K | 4/4 | 3.4 GHz | 3.8 GHz | 6 MB | 4600 | 1,200 MHz | 84 W | $242 |
4670 | 4/4 | 3.4 GHz | 3.8 GHz | 6 MB | 4600 | 1,200 MHz | 84 W | $213 |
4570 | 4/4 | 3.2 GHz | 3.6 GHz | 6 MB | 4600 | 1,150 MHz | 84 W | $192 |
4570S | 4/4 | 2.9 GHz | 3.6 GHz | 6 MB | 4600 | 1,150 MHz | 65 W | $192 |
The Core i7-4770K gives us an 8 MB shared L3 cache, similar to Core i7s before it. Although the Sandy and Ivy Bridge designs employed a single clock domain that kept the cores and L3 running at the same speed, Haswell decouples them. Our cache bandwidth benchmark reveals a slight hit to L3 throughput, though improvements elsewhere in the System Agent keep the results fairly even.
Haswell offers the same 16 lanes of PCI Express 3.0 connectivity as Ivy Bridge, and validated memory data rates up to 1,600 MT/s. The desktop line-up’s thermal targets are quite a bit different as a result of Intel’s fully-integrated voltage regulator, but an upper bound of 84 W isn’t extreme by any stretch and a floor of 35 W is pretty familiar.
All of Intel’s upgradable processors now drop into an LGA 1150 interface, meaning any decision to adopt Haswell is also going to require a motherboard purchase, at least. So, before you drop several hundred dollars on a brand new platform, let’s figure out if Core i7-4770K is worth the investment.
Test Hardware | |
---|---|
Processors | Intel Core i7-4770K (Haswell) 3.5 GHz (35 * 100 MHz), LGA 1150, 8 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled |
Intel Core i7-3770K (Ivy Bridge) 3.5 GHz (35 * 100 MHz), LGA 1155, 8 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
Intel Core i7-2700K (Sandy Bridge) 3.5 GHz (35 * 100 MHz), LGA 1155, 8 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
Intel Core i7-3930K (Sandy Bridge-E) 3.2 GHz (32 * 100 MHz), LGA 2011, 12 MB Shared L3, Hyper-Threading enabled, Turbo Boost enabled, Power-savings enabled | |
AMD FX-8350 (Vishera) 4.0 GHz (20 * 200 MHz), Socket AM3+, 8 MB Shared L3, Turbo Core enabled, Power-savings enabled | |
AMD A10-5800K (Trinity) 3.8 GHz (19 * 200 MHz), Socket FM2, 4 MB Total L2 Cache, Turbo Core enabled, Power-savings enabled | |
Motherboard | MSI Z87 Mpower Max (LGA 1150) Intel Z87 Express, BIOS 1.2B1 |
MSI Z77 Mpower (LGA 1155) Intel Z77 Express, BIOS 17.8 | |
MSI X79A-GD45 Plus (LGA 2011) Intel X79 Express, BIOS 17.2 | |
MSI 990FXA-GD80 (Socket AM3+) AMD 990FX/SB950, BIOS 13.2 | |
MSI FM2-A85XA-G65 (Socket FM2) AMD A85X, BIOS 2.0 | |
Memory | G.Skill 16 GB (4 x 4 GB) DDR3-1600, F3-12800CL9Q2-32GBZL @ DDR3-1600 at 1.5 V |
Hard Drive | Samsung 840 Pro 256 GB, SATA 6 Gb/s |
Graphics | Nvidia GeForce GTX Titan 6 GB |
Power Supply | Corsair AX860i, 80 PLUS Platinum, 860 W |
System Software And Drivers | |
Operating System | Windows 8 Professional x64 |
DirectX | DirectX 11 |
Graphics Driver | Nvidia GeForce Release 320.18 |
As we were planning out our test platforms, MSI responded to a call for vendor consistency across the motherboards we wanted to use. The company sent us one board for each of the processor interfaces we planned to compare, making it easy to tune each firmware exactly the same way. In this case, we wanted all power-saving features turned on and all automatic overclocking capabilities turned off (including settings that pushed all cores to the maximum Turbo Boost setting).
The first platform we set up centered on the 990FXA-GD80 board and FX-8350 processor. Four 4 GB DDR3-1600 memory modules from G.Skill populated the motherboard's slots, while a Samsung 840 Pro attached to its first SATA 6Gb/s port.
Next, we configured MSI's FM2-A85XA-G65 using the same drive image, complementing the platform with AMD's highest-end A10-5800K APU. While a number of our earlier benchmarks exploited the chip's on-die Radeon HD 7660D, everything from here on out leverages an Nvidia GeForce GTX Titan.
With the AMD testing out of the way, we were able to start configuring Intel-based systems. We started with the Z87 Mpower Max, which glows yellow up top and white underneath. To be quite honest, I haven't been so impressed with an MSI motherboard in a long time. The company appears to have really stepped up its game for the 8-series generation.
The Z77 Mpower board serves our LGA 1155 needs, hosting Intel's Core i7-3770K and -2700K, yielding comparisons to two prior-generation architectures.
I want to point out something MSI did for us leading into this launch. Like pretty much every motherboard vendor out there, it has a setting in its BIOS called Enhanced Turbo. This sets all four cores to operate at the processor's maximum single-core Turbo Boost ratio as a sort of sneaky overclock. At our request, MSI turned this off by default with its 8-series boards so that Haswell-based CPUs operate according to Intel's specification.
We had to turn this quiet "cheat" off manually on the Z77 Mpower and Z79A-GD45 Plus, below. However, we appreciated that MSI was willing to get back to Intel's spec for this generation. We prefer control over this, and to not have it be a default setting.
Finally, theX79A-GD45 Plus hosted our venerable Core i7-3930K processor. Old though it might be, this is still one of our favorite CPUs around. And as you'll see, the old timer has no trouble beating Haswell down in threaded apps able to exploit its six cores.
Noctua sent over its LGA 1150-compatible NH-U14S to help with testing, too. We used an NF-F12 fan to blow over our memory modules. This seemed to help put a stop to the errors we were getting in our long, taxing Visual Studio compile workload.
Corsair also sent over some hardware for us to use. We leaned on its AX860i power supply for its promised compatibility with Haswell's low-power states. We also used its CMY16GX3M2A2400C10R memory kit for our overclocking efforts.
Benchmark Configuration | |
---|---|
3D Games | |
Battlefield 3 | Campaign Mode, "Going Hunting" 90-Second Fraps, Low-Quality Preset, 1280x720 and 1920x1080 |
BioShock Infinite | Built-in Benchmark Utility, Fraps, Low-Quality Preset, 1280x720 and 1920x1080 |
Hitman: Absolution | Built-in Benchmark Utility, Fraps, Lowest-Quality Preset, 1280x720 and 1920x1080 |
The Elder Scrolls V: Skyrim | Update 1.5.26, Celedon Aethirborn Level 6, 25-Second Fraps, Medium-Quality Preset, 1280x720 and 1920x1080 |
World of Warcraft: Mists of Pandaria | Flight Point Benchmark, Fraps, Good Quality Preset, 1280x720 and 1920x1080 |
Adobe Creative Suite | |
Adobe After Effects CS6 | Version 11.0.0.378 x64: Create Video which includes three Streams, 210 Frames, Render Multiple Frames Simultaneosly |
Adobe Photoshop CS6 | Version 13 x64: Filter 15.7 MB TIF Image: Radial Blur, Shape Blur, Median, Polar Coordinates |
Adobe Premeire Pro CS6 | Version 6.0.0.0, 6.61 GB MXF Project to H.264 to H.264 Blu-ray, Output 1920x1080, Maximum Quality |
Audio/Video Encoding | |
iTunes | Version 10.4.1.10 x64: Audio CD (Terminator II SE), 53 minutes, default AAC format |
Lame MP3 | Version 3.98.3: Audio CD "Terminator II SE", 53 min, convert WAV to MP3 audio format, Command: -b 160 --nores (160 Kb/s) |
HandBrake CLI | Version: 0.98: Video from Canon Eos 7D (1920x1080, 25 FPS) 1 Minutes 22 Seconds Audio: PCM-S16, 48,000 Hz, Two-Channel, to Video: AVC1 Audio: AAC (High Profile) |
TotalCode Studio 2.5 | Version: 2.5.0.10677: MPEG-2 to H.264, MainConcept H.264/AVC Codec, 28 sec HDTV 1920x1080 (MPEG-2), Audio: MPEG-2 (44.1 kHz, 2 Channel, 16-Bit, 224 Kb/s), Codec: H.264 Pro, Mode: PAL 50i (25 FPS), Profile: H.264 BD HDMV |
Productivity | |
ABBYY FineReader | Version 10.0.102.95: Read PDF save to Doc, Source: Political Economy (J. Broadhurst 1842) 111 Pages |
Adobe Acrobat X | Version 10.0.0.396: Print PDF from 115 Page PowerPoint, 128-bit RC4 Encryption |
Autodesk 3ds Max 2012 and 2013 | Version 14.0 x64: Space Flyby Mentalray, 248 Frames, 1440x1080 |
Blender | Version: 2.64a, Cycles Engine, Syntax blender -b thg.blend -f 1, 1920x1080, 8x Anti-Aliasing, Render THG.blend frame 1 |
Visual Studio 2010 | Version 10.0, Compile Google Chrome, Scripted |
File Compression | |
WinZip | Version 17.0 Pro: THG-Workload (1.3 GB) to ZIP, command line switches "-a -ez -p -r" |
WinRAR | Version 4.2: THG-Workload (1.3 GB) to RAR, command line switches "winrar a -r -m3" |
7-Zip | Version 9.28: THG-Workload (1.3 GB) to .7z, command line switches "a -t7z -r -m0=LZMA2 -mx=5" |
Synthetic Benchmarks and Settings | |
3DMark 11 | Version: 1.0.1.0, Benchmark Only |
PCMark 7 | Version: 1.0.4 x64, System, Productivity, Hard Disk Drive benchmarks |
SiSoftware Sandra 2013 | Version 2013.01.19.11, CPU Test = CPU Arithmetic / Multimedia / Cryptography / Memory Bandwidth / Cache Bandwidth |