Assessing IBM's POWER8, Part 1: A Low Level Look at Little Endian
by Johan De Gelas on July 21, 2016 8:45 AM ESTComparing with Intel's Best
Comparing CPUs in tables is always a very risky game: those simple numbers hide a lot of nuances and trade-offs. But if we approach with caution, we can still extract quite a bit of information out of it.
Feature | IBM POWER8 |
Intel Broadwell (Xeon E5 v4) |
Intel Skylake |
L1-I cache Associativity |
32 KB 8-way |
32 KB 8-way |
32 KB 8-way |
L1-D cache Associativity |
64 KB 8-way |
32 KB 8-way |
32 KB 8-way |
Outstanding L1-cache misses | 16 | 10 | 10 |
Fetch Width | 8 instructions | 16 bytes (+/- 4-5 x86) | 16 bytes (+/- 4-5 x86) |
Decode Width | 8 | 4 µops | 5-6* µops (*µop cache hit) |
Issue Queue | 64+15 branch+8 CR = 87 |
60 unified | 97 unified |
Issue Width/Cycle | 10 | 8 | 8 |
Instructions in Flight | 224 (GCT SMT-8 modus) | 192 (ROB) | 224 (ROB) |
Archi regs Rename regs |
32 (ST), 2x32 (SMT-2) 92 (ST), 2x92 (SMT-2) |
16 168 |
16 180 |
Load Bandwidth (per unit) Load Queue Size |
4 per cycle 16B/cycle 44 entries |
2 per cycle 32B/cycle 72 entries |
2 per cycle 32B/cycle 72 entries |
Store Bandwidth Store Queue Size |
2 per cycle 16B/cycle 40 entries |
1 per cycle 32B/cycle 42 entries |
1 per cycle 32B/cycle 56 entries |
Int. Pipeline Length |
18 stages |
19 stages |
19 stages 14 stage from µop cache |
TLB | 2048 4-way |
128I + 64D L1 1024 8-way |
128I + 64D L1 1536 8-way |
Page Support | 4 KB, 64 KB, 16 MB, 16 GB | 4 KB, 2/4 MB, 1 GB | 4 KB, 2/4 MB, 1 GB |
Both CPUs are very wide brawny Out of Order (OoO) designs, especially compared to the ARM server SoCs.
Despite the lower decode and issue width, Intel has gone a little bit further to optimize single threaded performance than IBM. Notice that the IBM has no loop stream detector nor µop cache to reduce branch misprediction. Furthermore the load buffers of the Intel microarchitecture are deeper and the total number of instructions in flight for one thread is higher. The TLB architecture of the IBM POWER8 has more entries while Intel favors speedy address translations by offering a small level one TLB and a L2 TLB. Such a small TLB is less effective if many threads are working on huge amounts of data, but it favors a single thread that needs fast virtual to physical address translation.
On the flip side of the coin, IBM has done its homework to make sure that 2-4 threads can really boost the performance of the chip, while Intel's choices may still lead to relatively small SMT related performance gains in quite a few applications. For example, the instruction TLB, µop cache (Decode Stream Buffer) and instruction issue queues are divided in 2 when 2 threads are active. This will reduced the hit rate in the micro-op cache, and the 16 byte fetch looks a little bit on the small side. Let us see what IBM did to make sure a second thread can result in a more significant performance boost.
124 Comments
View All Comments
JohanAnandtech - Thursday, July 21, 2016 - link
I don't think so, we just expressed it in ns so you can compare with IBM's numbers more easily. Can you elaborate why you think they are wrong?Taracta - Thursday, July 21, 2016 - link
Sorry, mixed up cycles with ns especially after reading the part about transition for the Intel from L3 to MEM.Sahrin - Thursday, July 21, 2016 - link
Yikes. Pictures without captions. Anandtech is terrible about this. ALWAYS caption your pictures, guys.djayjp - Thursday, July 21, 2016 - link
Are bar graphs not a thing anymore...?Drumsticks - Thursday, July 21, 2016 - link
Afaik, Anandtech has always used the chart when presenting things like SPEC. I'd guess it'd be for clutter reasons, but the exact reason is up to the editors to mention.JohanAnandtech - Thursday, July 21, 2016 - link
The reason for me is simply to give you the exact numbers and allow people to do their own comparisons.Drumsticks - Thursday, July 21, 2016 - link
Just to be clear, the Xeon CPU used today is 3 times more expensive than the Power8 CPU benchmarked? That's really impressive, isn't it? The Power8 has a pretty significant power increase, but if it's 43% faster, that cuts into the perf/w gap.I know we've only looked at SPEC so far in round 2, but this looks like a good showing for IBM. How big is the efficiency gap between 22nm SOI and 14nm FinFet? Any estimates?
Michael Bay - Thursday, July 21, 2016 - link
Selling at a loss is hardly impressive, especially in IBM`s case. This thing is literally their last chance.tipoo - Friday, July 22, 2016 - link
Is it at a loss, or is it just not at crazy Intel margins?Michael Bay - Saturday, July 23, 2016 - link
They`d have to have a healthy margin to offset all the R&D, plus IBM as a whole is not in a good financial position. Consider they sold their fab capability not so long ago.