The Ice Lake Benchmark Preview: Inside Intel's 10nm
by Dr. Ian Cutress on August 1, 2019 9:00 AM EST- Posted in
- CPUs
- Intel
- GPUs
- 10nm
- Core
- Ice Lake
- Cannon Lake
- Sunny Cove
- 10th Gen Core
Security Updates, Improved Instruction Performance and AVX-512 Updates
With every new microarchitecture update, there are goals on several fronts: add new instructions, decrease the latency of current instructions, increase the throughput of current instructions, and remove bugs. The big headline addition for Sunny Cove and Ice Lake is AVX-512, which hasn’t yet appeared on a mainstream widely distributed consumer processor – technically we saw it in Cannon Lake, but that was a limited run CPU. Nonetheless, a lot of what went into Cannon Lake also shows up in the Sunny Cove design. To complicate matters, AVX-512 comes in plenty of different flavors. But on top of that, Intel also made a significant number of improvements to a number of instructions throughout the design.
Big thanks to InstLatX64 for his help in analyzing the benchmark results.
Security
On security, almost all the documented hardware security fixes are in place with Sunny Cove. Through the CPUID results, we can determine that SSBD is enabled, as is IA32_ARCH_CAPABILITIES, L1D_FLUSH, STIBP, IBPB/IBRS and MD_CLEAR.
This aligns with Intel’s list of Sunny Cove security improvements:
Sunny Cove Security | |||
AnandTech | Description | Name | Solution |
BCB | Bound Check Bypass | Spectre V1 | Software |
BTI | Branch Target Injection | Spectre V2 | Hardware+OS |
RDCL | Rogue Data Cache Load | V3 | Hardware |
RSSR | Rogue System Register Read | V3a | Hardware |
SSB | Speculative Store Bypass | V4 | Hardware+OS |
L1TF | Level 1 Terminal Fault | Foreshadow | Hardware |
MFBDS | uArch Fill Buffer Data Sampling | RIDL | Hardware |
MSBDS | uArch Store Buffer Data Sampling | Fallout | Hardware |
MLPDS | uArch Load Port Data Sampling | - | Hardware |
MDSUM | uArch Data Sampling Uncachable Memory | - | Hardware |
Aside from Spectre V1, which has no suitable hardware solution, almost all of the rest have been solved through hardware/firmware (Intel won’t distinguish which, but to a certain extent it doesn’t matter for new hardware). This is a step in the right direction, but of course it may have a knock-on effect, plus for anything that gets performance improvements being moved from firmware to hardware will be rolled into any advertised IPC increase.
Also on the security side is SGX, or Intel’s Software Guard Instructions. Sunny Cove now becomes Intel’s first public processor to enable both AVX-512 and SGX in the same design. Technically the first chip with both SGX and AVX-512 should have been Skylake-X, however that feature was ultimately disabled due to failing some test validation cases. But it now comes together for Sunny Cove in Ice Lake-U, which is also a consumer processor.
Instruction Improvements and AVX-512
As mentioned, Sunny Cove pulls a number of key improvements from the Cannon Lake design, despite the Cannon Lake chip having the same cache configuration as Skylake. One of the key points here is the 64-bit division throughput, which goes from a 97-cycle latency to an 18-cycle latency, blowing past AMD’s 45-cycle latency. As an ex-researcher with no idea about instruction latency or compiler options, working on high-precision math code, this speedup would have been critical.
- IDIV -> 97-cycle to 18-cycle
For the general purpose registers, we see a lot of changes, and most of them quite sizable.
Sunny Cove GPR Changes | |||
AnandTech | Instruction | Skylake | Sunny Cove |
Complex LEA | Complex Load Effective Address | 3 cycle latency 1 per cycle |
1 cycle latency 2 per cycle |
SHL/SHR | Shift Left/Right | 2 cycle latency 0.5 per cycle |
1 cycle latency 1 per cycle |
ROL/ROR | Rotate Left/Right | 2 cycle latency 0.5 per cycle |
1 cycle latency 1 per cycle |
SHLD/SHRD | Double Precision Shift Left/Right | 4 cycle latency 0.5 per cycle |
4 cycle latency 1 per cycle |
4*MOV | Four repated string MOVS | Limited instructions | 104 bits/clock All MOVS* Instructions |
In the past we’ve seen x87 instructions being regressed, made slower, as they become obsolete. For whatever reason, Sunny Cove decreases the FMUL latency from 5 cycles to 4 cycles.
The SIMD units also go through some changes:
Sunny Cove SIMD | |||
AnandTech | Instruction | Skylake | Sunny Cove |
SIMD Packing | SIMD Packing now slower | 1 cycle latency 1 per cycle |
3 cycle latency 1 per cycle |
AES* | AES Crypto Instructions (for 128-bit / 256-bit) |
4 cycle latency 2 per cycle |
3 cycle latency 2 per cycle |
CLMUL | Carry-Less Multiplication | 7 cycle latency 1 per cycle |
6 cycle latency 1 per cycle |
PHADD/PHSUB | Packed Horizontal Add/Subtract and Saturate |
3 cycle latency 0.5 per cycle |
2 cycle latency 1 per cycle |
VPMOV* xmm | Vector Packed Move | 2 cycle latency 0.5 per cycle |
2 cycle latency 1 per cycle |
VPMOV* ymm | Vector Packed Move | 4 cycle latency 0.5 per cycle |
2 cycle latency 1 per cycle |
VPMOVZX/SX* xmm | Vector Packed Move | 1 cycle latency 1 per cycle |
1 cycle latency 2 per cycle |
POPCNT | Microcode 50% faster than SW (under L1-D size) | ||
REP STOS* | Repeated Store String | 62 bits/cycle | 54 bits/cycle |
VPCONFLICT | Still Microcode Only |
We’ve already gone through all of the new AVX-512 instructions in our Sunny Cove microarchitecture disclosure. These include the following families:
- AVX-512_VNNI (Vector Neural Network Instructions)
- AVX-512_VBMI (Vector Byte Manipulation Instructions)
- AVX-512_VBMI2 (second level VBMI)
- AVX-512_ BITALG (bit algorithms)
- AVX-512_IFMA (Integer Fused Multiply Add)
- AVX-512_VAES (Vector AES)
- AVX-512_VPCLMULQDQ (Carry-Less Multiplacation of Long Quad Words)
- AVX-512+GFNI (Galois Field New Instructions)
- SHA (not AVX-512, but still new)
- GNA (Gaussian Neural Accelerator)
(Intel also has the GMM (Gaussian Mixture Model) inside the core since Skylake, but I’ve yet to see any information on this outside a single line in the coding manual.)
For all these new AVX-512 instructions, it’s worth noting that they can be run in 128-bit, 256-bit, or 512-bit mode, depending on the data types passed to it. Each of these can have corresponding latencies and throughputs, which often get worse when going for the 512-bit mode, but overall assuming you can fill the register with a 512-bit data type, then the overall raw processing will be faster, even with the frequency differential. This doesn’t take into account any additional overhead for entering the 512-bit power state, it should be noted.
Most of these new instructions are relatively fast, with most of them only 1-3 cycles of latency. We observed the following:
Sunny Cove Vector Instructions | |||||
AnandTech | Instruction | XMM | YMM | ZMM | |
VNNI | Latency | Vector Neural Network Instructions | 5-cycle | 5-cycle | 5-cycle |
Throughput | 2/cycle | 2/cycle | 1/cycle | ||
VPOPCNT* | Latency | Return the number of bits set to 1 | 3-cycle | 3-cycle | 3-cycle |
Throughput | 1/cycle | 1/cycle | 1/cycle | ||
VPCOMPRESS* | Latency | Store Packed Data | 3-cycle | 3-cycle | 3-cycle |
Throughput | 0.5/cycle | 0.5/cycle | 0.5/cycle | ||
VPEXPAND* | Latency | Load Packed Data | 5-cycle | 5-cycle | 5-cycle |
Throughput | 0.5/cycle | 0.5/cycle | 0.5/cycle | ||
VPSHLD* | Latency | Vector Shift | 1-cycle | 1-cycle | 1-cycle |
Throughput | 2/cycle | 2/cycle | 1/cycle | ||
VAES* | Latency | Vector AES Instructions | 3-cycle | 3-cycle | 3-cycle |
Throughput | 2/cycle | 2/cycle | 1/cycle | ||
VPCLMUL | Latency | Vector Carry-Less Multiply | 6-cycle | 8-cycle | 8-cycle |
Throughput | 1/cycle | 0.5/cycle | 0.5/cycle | ||
GFNI | Latency | Galois Field New Instructions | 3-cycle | 3-cycle | 3-cycle |
Throughput | 2/cycle | 2/cycle | 1/cycle |
For all of the common AVX2 instructions, xmm/ymm latencies and throughputs are identical to Skylake, however zmm is often a few cycles slower for DIV/SQRT variants.
Other Noticeable Observations
From our testing, we were also able to prove some of the other parts of the core, such as the added store ports and shuffle units.
Our data shows that the second store port is not identical to the first, which explains the imbalance when it comes to writes: rather than supporting 2x64-bit with loads, it only supports either 1x64-bit write, or 1x32-bit write, or 2x16-bit writes. This means we mainly see speed ups with GPR/XMM data, and the result is only a small improvement for 512-bit SCATTER instructions. Otherwise, it seems not to work with any 256-bit or 512-bit operand (you can however use it with 64-bit AVX-512 mask registers). This is going to cause a slight headache for anyone currently limited by SCATTER stores.
The new shuffle unit is only 256-bit wide. It will handle a number of integer instructions (UNPCK, PSLLDQ, SHUF*, MOVSHDUP, but not PALIGNR or PACK), but only a couple of floating point instructions (SHUFPD, SHUFPS).
261 Comments
View All Comments
jcc5169 - Thursday, August 1, 2019 - link
It's like a long running Intel advertisement ......Ian Cutress - Thursday, August 1, 2019 - link
How so?jordanclock - Thursday, August 1, 2019 - link
Probably because you provided objective measurements instead of long winded conjecture.peevee - Friday, August 2, 2019 - link
"As for Ice Lake itself, our results lean towards Ice Lake outperforming Whiskey Lake, if only by a small margin."A laptop allowing more than 50W on a U chip and with cooler always running is certainly not representative of the real world performance a user would get from real systems. If Whiskey Lake results were obtained on a real system, then the results are not comparable enough that Ice Lake can actually be slower, especially in real world loads (note the performance on x264 and POV-Ray essentially has not changed).
But at least iGPU has improved nicely.
Samus - Saturday, August 3, 2019 - link
They have dedicated pages to 15w and 25w results. Not sure what you're on about about 'allowing more than 50W...' when they power limited the chip for specific-scenario benchmark results.Spunjji - Monday, August 5, 2019 - link
You may want to re-read that Power Results section - put simply, peevee's point still stands and your response is mistaken. At the 25W limit, the CPU spent more than 20 seconds operating between 50W and 35W before it finally dropped down. It's unlikely that the Coffee / Whiskey devices they tested allowed that sort of behaviour, as without a continuous 100% fan speed the thermals would have spiked and lowered the power limit far sooner. Even with the "power limits" you're talking about in place, the chip still boosts like that, so their benchmark results incorporate that behaviour. for any other company I might feel generously inclined, but Intel have already pulled a fast one multiple times by releasing CPUs that have nominally higher specifications but never reach their performance potential in shipping designs due to thermal constraints.Gondalf - Wednesday, January 8, 2020 - link
Spec suite (the reference) is a pretty loooong bench so the cpu stay at 15W all the time without your 50W. Your comment say a lot about you.yeeeeman - Wednesday, June 17, 2020 - link
Also, we not comparing power efficiency here but rather IPC of each core. And the bottom line is that Sunny Cove core has 5-10% better IPC than Zen 2.CSMR - Sunday, August 4, 2019 - link
There is no evidence that the iGPU has improved. We'd need a comparison against Iris Plus 655 to confirm that. We only know EUs have increased (64 vs 48) but EDRAM was removed.brakdoo - Thursday, August 1, 2019 - link
"First of all, I must say that Intel offering us to test a reference system in advance of a launch is a very good thing indeed"You are being played once again as a marketing tool for the Ice Lake launch. Don't tell me you don't see that.