AMD Says Ryzen Will Be 10 Percent Smaller Than Comparable Intel Kaby Lake Processors
AMD has shared a spattering of technical details about its Ryzen architecture, though most of the information to this point has focused on technologies such as Precision Boost and Neural Net Prediction. More recently however, AMD released a paper with some finer grain details, one of which is that Ryzen processors will sport a 10 percent smaller die area than Intel's Kaby Lake processors.
Both Ryzen and Kaby Lake are manufactured on a 14nm node process, but the die area for Ryzen is 44mm2, compared to 49mm2 for Kaby Lake. No big deal, right? Perhaps not, though the theoretical advantage of having a smaller die size is being able to carve out more processors from a single wafer. That means a lower cost on the manufacturing side, which could be passed on to consumers.
Whether it actually plays out that way remains to be seen, though one thing is for sure, AMD is gunning for Intel in a big way. AMD views Ryzen as its path back to the enthusiast market. The hype surrounding Ryzen is high and it has certainly drawn the attention of Intel—rumor has it the Santa Clara chipmaker is readying new Kaby Lake Core i7 and Core i5 processors with aggressive pricing to steal some of the thunder away from Ryzen.
Getting back to the technical details, here are some other stats AMD revealed about Ryzen, along with how they stack up against Intel's Kaby Lake family:
Both Ryzen and Kaby Lake are manufactured on a 14nm node process, but the die area for Ryzen is 44mm2, compared to 49mm2 for Kaby Lake. No big deal, right? Perhaps not, though the theoretical advantage of having a smaller die size is being able to carve out more processors from a single wafer. That means a lower cost on the manufacturing side, which could be passed on to consumers.
Whether it actually plays out that way remains to be seen, though one thing is for sure, AMD is gunning for Intel in a big way. AMD views Ryzen as its path back to the enthusiast market. The hype surrounding Ryzen is high and it has certainly drawn the attention of Intel—rumor has it the Santa Clara chipmaker is readying new Kaby Lake Core i7 and Core i5 processors with aggressive pricing to steal some of the thunder away from Ryzen.
Getting back to the technical details, here are some other stats AMD revealed about Ryzen, along with how they stack up against Intel's Kaby Lake family:
| Ryzen | Kaby Lake | |
| Tech | 14nm | 14nm |
| Cores | 4 Cores, 8 Threads | 4 Cores, 8 Threads |
| Area | 44mm2 | 49mm2 |
| L2 | 512KB, 1.5mm2/core | 256KB, 0.9mm2/core |
| L3 | 8MB, 16mm2 | 8MB, 19.1mm2 |
| CPP (nm) | 78 | 70 |
| Fin Pitch (nm) | 48 | 42 |
| 1x Metal Pitch (nm) | 64 | 52 |
| Standard 6t SRAM (mm2) | 0.0806 | 0.0588 |
| Metal Layers | 12 2/ MiM | 13 2/ MiM |
AMD used various techniques on Ryzen to reduce switching capacitance by 15 percent compared to its current processors. One example is the use of a metal-insulator-metal-capacitor—a first for AMD—to help lower operating voltages while providing greater per-core voltage and frequency control. As AMD discussed previously, Ryzen offers high precision tuning with on-the-fly frequency adjustments in as little as 25MHz increments., as determined by the processor's workload and health data at the time.
More details may slip out between now and when Ryzen launches to retail early next month, though it all boils down to real-world performance and price.
More details may slip out between now and when Ryzen launches to retail early next month, though it all boils down to real-world performance and price.
