Excel speed test comparison against an FX-8350

[John Tauwhare]

NEW LINKS:
https://www.dropbox.com/sh/fly51y76kganoms/AABqlEMo7i2EbNTRyt90f1sta?dl=0
https://1drv.ms/x/s!AkoqLz2O_86Ngbs8CCbxcfkr0U-PMQ

I recently built a new rig inside an old Dell XPS 710 case, converted from BTX to ATX, with an FX-8350 in a Gigabyte 990FXA motherboard and 8Gb RAM. This is my main PC and I use it for many things but mostly for spreadsheet work. And I had high hopes that the latest CPU from AMD would would be much faster at running Excel macros than the 5 year old QX6700 that used to be in my Dell case.

But, though extremely quick at graphics based applications, it didn't seem any quicker at Excel. So, to compare its performance I wrote a timing macro into an old spreadsheet and timed my new machine, at 4GHz, at 60 seconds. Then I overclocked it to 4200-4400. No change, still 60 seconds.

I timed all the laptops I could get hold of. My work Lifebook P770 (i7-640UM @1200/2266) did 102 seconds and my ultra-mobile Lenovo U260 (i5-470UM @1333/1866) did 172 seconds. No wonder they frustrate me so much; and it's not like the battery life is so great despite the low voltage. I now know to avoid anything with a "U" in it.

I timed the Lenovo E320 (i3-2330M @2200/2400) I gave my daughter for Christmas, which I thought would be nothing special, and it did 54.6 seconds. But the star was my Samsung R780 (i5-480M @2666/2933) at 49 seconds. Even my trusty Intel QX6700 at stock speed of 2666 in an ASUS P5K with 4Gb DDR2 was faster than the FX-8350, at 59 seconds, and overclocking it to 3200 dropped its time to 53 seconds.

I'd love to know what's going on here and why AMD's flagship Piledriver CPU is no faster at running Excel macros than a 5 year old Intel Extreme CPU and is considerably slower than a 2 year old mid-range Intel based laptop, both at much lower clock speeds.

The test spreadsheet (v1) is here:
https://www.dropbox.com/sh/fly51y76kganoms/AABqlEMo7i2EbNTRyt90f1sta?dl=0
and https://1drv.ms/x/s!AkoqLz2O_86Ngbs8CCbxcfkr0U-PMQ

If anyone wants to have a go then click on the Stopwatch button and wait ~3 minutes. Please PM or post the elapsed time and I'll do a results table. And if anyone can beat 40 seconds then I'll know what to buy next.

Edit Feb/24: doh, I had my Lenovo U260 (i5-470UM @1333/1866) in power saving mode. Switching it to high performance locked the clock on 1866 and got a very respectable time of 87 seconds.

I've also since tested another ultra low voltage CPU; an Ivy Bridge i7-3517UM (1666/3000) in a Win8 Lenovo Yoga. With multi-threading switched off in Excel 2013 it clocked ~2850 and timed 38.26. That's 2.2x the relative performance of the FX-8350, up at the lower end of the K processors, using about 13 watts. Amazing.

RESULTS (v14):

Images moved from Photobucket to postimg.com 29 July 2017 and then readdressed to postimage.cc nd re-linked 16 February 2019.

 

[CHADBOGA]

Does your Benchmark go for 3 iterations and if so, are you wanting the time for the 3 iterations in total, or the time for a single iteration?

 

[Ventanni]

My Penryn 3.0ghz dual core did it in 158 seconds. 4gb of RAM, some processes running in the background, running Windows XP.

 

[Ventanni]

I think the admin Idontcare would be the best gentleman for comparing the two here, assuming he has Excel 2007. He's pretty awesome in his responses.

 

[TuxDave]

147.49s on an i5-2540M (2.6GHz)

Edit: Oh, I guess I was supposed to divide the number above my 3 to get the average run. 49.16 s

 

[Idontcare]

I recently built a new rig inside an old Dell XPS 710 case, converted from BTX to ATX, with an FX-8350 in a Gigabyte 990FXA motherboard and 8Gb RAM. This is my main PC and I use it for many things but mostly for spreadsheet work. And I had high hopes that the latest CPU from AMD would would be much faster at running Excel macros than the 5 year old QX6700 that used to be in my Dell case.

But, though extremely quick at graphics based applications, it didn't seem any quicker at Excel. So, to compare its performance I wrote a timing macro into an old spreadsheet and timed my new machine, at 4GHz, at 60 seconds. Then I overclocked it to 4200-4400. No change, still 60 seconds.

I timed all the laptops I could get hold of. My work Lifebook P770 (i7-640UM @1200/2266) did 102 seconds and my ultra-mobile Lenovo U260 (i5-470UM @1333/1866) did 172 seconds. No wonder they frustrate me so much; and it's not like the battery life is so great despite the low voltage. I now know to avoid anything with a "U" in it.

I timed the Lenovo E320 (i3-2330M @2200/2400) I gave my daughter for Christmas, which I thought would be nothing special, and it did 54.6 seconds. But the star was my Samsung R780 (i5-480M @2666/2933) at 49 seconds. Even my trusty Intel QX6700 at stock speed of 2666 in an ASUS P5K with 4Gb DDR2 was faster than the FX-8350, at 59 seconds, and overclocking it to 3200 dropped its time to 53 seconds.

I'd love to know what's going on here and why AMD's flagship Piledriver CPU is no faster at running Excel macros than a 5 year old Intel Extreme CPU and is considerably slower than a 2 year old mid-range Intel based laptop, both at much lower clock speeds.

The test spreadsheet is here:

http://dl.dropbox.com/u/87381454/EXCEL-SPEEDTEST-v1-(John-Tauwhare).xlsb

If anyone wants to have a go then click on the Stopwatch button and wait ~3 minutes. Please PM or post the elapsed time and I'll do a results table. And if anyone can beat 40 seconds then I'll know what to buy next.

I've got an FX8350 and an i7-3770k here, comparably configured, as well as a dated Q6600. So I can run the test and confirm your observations. I'll be back with results this evening

 

[Piroko]

I still remember some old Excel tests from a magazine where they concluded that it was fairly sensitive to memory speeds if my memory serves me right.

 

[John Tauwhare]

Does your Benchmark go for 3 iterations and if so, are you wanting the time for the 3 iterations in total, or the time for a single iteration?

Chadboga, it runs a set of 8 tests 3 times (because Excel slows as it runs) and shows the total time, and the average in the BMElapsed cell which is the benchmark.

 

[mrcmtl]

I'm at work and the i5-2400 3.1Ghz at work did one iteration in 43.81s.

 

[Skurge]

I think my 3570K at 4.5Ghz did it in my 29.95s. I don't really understand the benchmark.

 

[dbcooper1]

e8500 Win XP 64 8GB ave. 51.15 sec.
i5-2400 Win7 64 16GB ave. 34.03 sec.
i5-M560 Win XP 32 4GB ave 70.93 sec. Dell laptop

I've also read/heard that Excel spends as much time manipulating blocks of memory as it does calculating and is therefore quite sensitive to RAM speed as well as cache and CPU speed.

 

[guskline]

On a Bulldozer 8150 @ 4.2 Ghz= 78 sec and on a PileDriver 8350 @ 4.6Ghz =61.5 sec while on one of my 2500k rigs @ 4.5 Ghz it's 29 seconds!

 

[Tsavo]

i5 3570k @4.2GHz: 29.50 Office 2010
i5-2410M @2.9Ghz: 46.42 Office 2013

 

[SiliconWars]

So I'm guessing it's extremely single threaded?

 

[SolMiester]

I have IB i5 3470 w\ 16GB RAM and SSD, using asrock Non-k OC running the CPU at 4Ghz..

Wicked spreadsheet by the way!

 

[tweakboy]

Darn I dont have Excel, I would love to run this test. I think SSD and CPU horsepower matter in big excel stuff!,,,I also think windoz is windoz, and its going to be windows which means maybe you hit a wall with excel,, Your cpu is too fast, that is the fastest it can articulate the results. gl

 

[WiseUp216]

3570k @ 4.2
16GB @ 1866
Office 2010
30.51s

 

[mrcmtl]

Home PC Phenom II X6 4Ghz: 49.7s

 

[Vectronic]

i5 3570K @ 4.5 = 29.95 (Skurge, Office 2013?)
i5 3570K @ 4.2 = 29.50 (Tsavo, Office 2010)
i5 3570K @ 4.2 = 30.51 (WiseUp216, Office 2010)

Just pointing that out because it's interesting.

My results are as follows with i5 3570K, 8GB DDR3, Windows 8, Office 2013, closing Excel and re-opening with each run:

CPU: 4.5GHz, RAM: 2000 10-10-10-26-1
Run 1: 24.84
Run 2: 24.97

CPU: 4.5GHz, RAM: 1600 8-8-8-22-1
Run 1: 24.83
Run 2: 24.52

CPU: 4.2GHz, RAM: 2000 10-10-10-26-1
Run 1: 26.54
Run 2: 26.38

CPU: 4.2GHz, RAM: 1600 8-8-8-22-1
Run 1: 26.96
Run 2: 26.60

CPU: Stock, RAM: Stock (1600 9-9-9-24-2)
Run 1: 31.25
Run 2: 31.11

CPU: 1.6GHz, RAM: Stock (1600 9-9-9-24-2)
Run 1: 66.67
Run 2: 67.37

Edit: did a couple tests (I'm still at 1.6GHz) by opening the file from my SSD (was on my slowest HD before)... no noticeable difference.

Quick tally of them so far:
FX 8350 (4.0GHz) = 60.00

i7 640UM (2.3GHz) = 102.00
i5 470UM (1.9GHz) = 172.00
i3 2330M (2.4GHz) = 54.60
i5 480M (2.9GHz) = 49.00
C2E QX6700 (2.6GHz) = 59.00
C2E QX6700 (3.2GHz) = 53.00
C2D T9900 (3.0GHz) = 52.66
i5 2540 (3.3GHz) = 49.16
i5 2400 (3.4GHz) = 43.81
i5 3570K (4.5GHz) = 29.95
C2D E8500 (3.2GHz) = 51.15
i5 2400 (3.4GHz) = 34.03
i5 M560 (3.2GHz) = 70.93

FX 8150 (4.2GHz) = 78.00
FX 8350 (4.6GHz) = 61.50

i5 2500K (4.5GHz) = 29.00
i5 3570K (4.2GHz) = 29.50
i5 2410M (2.9GHz) = 46.42
i5 3470 (4.0GHz) = 35.61
i5 3570K (4.2GHz) = 30.51

X6 1100T (4.0GHz) = 49.70

i5 3570K (4.5GHz) = 24.97
i5 3570K (4.2GHz) = 26.96
i5 3570K (3.8GHz) = 31.25

Though highly lopsided, the consensus is Intel.

 

[felang]

2600K 4.5Ghz
2133 Mhz Ram
Office 2010

30.75

 

[Idontcare]

I tested a few different scenarios just to see what, if anything, impacted the performance of Excel running this app.

I varied the processor (i7-3770K vs FX-8350), the processor clockspeed (2GHz to 4GHz), ram speed (DDR3-800 vs DR3-1866), and tried two different versions of Excel (2007 vs 2010).

For the clockspeed tests I used Excel 2007 (fresh install and fully patched/updated on both systems):

Excepting for the Q6600 test, all tests were conducted with the exact same ram timings for both platforms: 10-10-10-28-CR2

The Clockspeed Scaling data are as follows:
i7-3770K 4.0GHz DDR3-1866 33.41s, 33.08s, 33.33s (repeated 3-times)
i7-3770K 3.5GHz DDR3-1866 37.52s
i7-3770K 3.0GHz DDR3-1866 43.99s
i7-3770K 2.5GHz DDR3-1866 52.15s
i7-3770K 2.0GHz DDR3-1866 65.30s

FX-8350 4.0GHz DDR3-1866 60.89s, 61.46s, 61.35s (repeated 3-times)
FX-8350 3.5GHz DDR3-1866 66.27s
FX-8350 3.0GHz DDR3-1866 75.96s
FX-8350 2.5GHz DDR3-1866 88.80s
FX-8350 2.0GHz DDR3-1866 109.02s

Q6600 3.5GHz DDR2-780 48.24s
i7-3770K 3.5GHz DDR3-1866 37.52s
FX-8350 3.5GHz DDR3-1866 66.27s

Conclusion: Piledriver just doesn't perform well in Excel with this macro.


The RAM bandwidth Scaling data are as follows:
i7-3770K 4.0GHz DDR3-1866 33.41s, 33.08s, 33.33s (repeated 3-times)
i7-3770K 4.0GHz DDR3-800 32.94

FX-8350 4.0GHz DDR3-1866 60.89s, 61.46s, 61.35s (repeated 3-times)
FX-8350 4.0GHz DDR3-800 60.86s

Conclusion: Ram bandwidth does not impact this Excel macro.


The Office 2010 vs Office 2007 results are as follows:

Office 2007 i7-3770K 4.0GHz DDR3-1866 33.41s, 33.08s, 33.33s (repeated 3-times) = 33.28s avg
Office 2010 i7-3770K 4.0GHz DDR3-1866 32.81s, 31.75s, 33.57s (repeated 3-times) = 32.71s avg


Office 2007 FX-8350 4.0GHz DDR3-1866 60.89s, 61.46s, 61.35s (repeated 3-times) = 61.23s avg
Office 2007 FX-8350 4.0GHz DDR3-1866 66.61s, 68.29s, 66.31s (repeated 3-times) = 67.07s avg

Conclusion: Office 2010 is neither faster nor slower with this macro when running on the Intel 3770k, but it takes 9.5% longer to finish on the AMD FX-8350 compared to running the same macro with Office 2007.

 

[CHADBOGA]

Well I experienced some interesting behaviour/results in running the benchmarks that I am wondering if anyone else got this too?

I found that for every time I ran the benchmark again(by pressing Stopwatch, with Excel already loaded from previous attempt) the results got progressively worse.

My best overall score was 29.68, but there is a bit of a story below with how it all went.

To start with, I did a reboot of my system and only had Excel running, with my MS Essentials A/V in the background as per normal and connection to Steam.

My Specs are:

i5 3750K @ 4.020Ghz
8gig RAM @ 1600Mhz
240gig Intel 520 SSD

All Results below with Excel 2007

1st Run Results

2nd Run Results

3rd Run Results

4th Run Results

5th Run Results

Now at this point, I decided to close down Excel, re-open it and run the benchmark again and once again I got a fast first up result, but it went slower on the second run again, so I stopped there, just assuming that the benchmark returns slower results if you keep running it, without restarting Excel.

1st Re-Run Results

2nd Re-Run Results

 

[Vectronic]

i7-3770K 4.0GHz DDR3-1866 33.41s

HT enabled? (trying to figure out why mine is so fast)

 

[CHADBOGA]

^- HT enabled? (trying to figure out why mine is so fast)

Maybe yours is fast because of Win 8?

I'm on Win 7.

 

[Idontcare]

Well I experienced some interesting behaviour/results in running the benchmarks that I am wondering if anyone else got this too?

I found that for every time I ran the benchmark again(by pressing Stopwatch, with Excel already loaded from previous attempt) the results got progressively worse.

My best overall score was 29.68, but there is a bit of a story below with how it all went.

Yeah I observed the same. You have to close the excel file and reopen it for each run. It is not necessary that you close the Excel program itself, you need merely close the file and re-open.

Here's the sequence I got from repetitive testing of the benchmark without closing and re-opening (except the last test, which I did close and re-open):

i7-3770K 4GHz DDR3-1866 33.41s
i7-3770K 4GHz DDR3-1866 36.66s
i7-3770K 4GHz DDR3-1866 42.07s
i7-3770K 4GHz DDR3-1866 46.04s
i7-3770K 4GHz DDR3-1866 33.08s (closed/re-opened)

Same thing with the FX-8350.

FX-8350 4GHz DDR3-1866 60.89s
FX-8350 4GHz DDR3-1866 67.06s
FX-8350 4GHz DDR3-1866 73.55s
FX-8350 4GHz DDR3-1866 61.46s (closed/re-opened)

(HT is enabled for my tests)