AMD A10-5800K & A8-5600K Review: Trinity on the Desktop, Part 2
by Anand Lal Shimpi on October 2, 2012 1:45 AM EST
General Performance
SYSMark 2012
Although not the best indication of overall system performance, the SYSMark 2012 suite does give us a good idea of lighter workloads than we're used to testing.
AMD does surprisingly well here in SYSMark 2012. The Core i3 3220 manages a 12% advantage over the 5800K, but that's not as much as we'd normally expect given the significant single threaded performance deficit we pointed out earlier. Once again, whether or not Trinity makes sense for you depends on how much you value processor graphics performance.
174 Comments
View All Comments
Chipman1969 - Monday, October 08, 2012 - link
Please redo some of the Trinity benchmarks with 1866 or 2133 ddr3 ram.See http://www.phoronix.com/scan.php?page=article&...
There you can see that Trinity is doing much better with faster ram.
On Amazon G.Skill Ripjaws X DDR3-1600 is 42$ and 2166 is 52$. Reply
medi01 - Tuesday, October 09, 2012 - link
So:"Although likely not the target market for someone buying a Trinity APU, we looked at performance of AMD's latest APU when paired with a high-end discrete GPU. The end result is a total loss for Trinity."
brand new way to piss on AMD's cookies, by Anand The Shameless... Reply
sdoraisw - Friday, January 04, 2013 - link
If you want to compare the idle numbers you should disable the Gfx in IVB processor because trinity doesn't have integrated graphics.not just disable, you need some BIOS switch to power gate the Gfx engine completely. then you can do comparisons. Reply
x7y9 - Saturday, January 12, 2013 - link
I just got a Toshiba S875D-S7350 laptop with AMD A10-4600M processor and tried somesimple benchmarks -- the result was pretty disappointing. Running 4 identical processes
(Ubuntu 12.04) causes the completion time of each process to degrade substantially.
I do some work with generating graphs and analysing them, so basic integer performance
is the most important thing for me.
I ran this simple benchmark and the comments show the results I got:
#!/usr/local/bin/ruby -w
# M1 -- AMD Phenom 2 X4 945 Quad core desktop
# M2 -- Intel Core i3-2310M HP laptop
# M3 -- Toshiba S875D-S7350 laptop with AMD A10-4600M
# M4 -- HP AMD A6 3400M Quad core CPU 1.4-2.3 GHz
# Machine M1 M2 M3 M4
# -------------------------------
# Single run: 158 178 234 292
# 2 parallel: 169 195 283 313
# 4 parallel 205 241 642 354
# (All times in seconds; averaged over the parallel runs)
start = Process.times
a=(0..11).to_a
cnt = a.permutation.inject(0) { |m, _| m + 1 }
finish = Process.times
user = finish.utime - start.utime; sys = finish.stime - start.stime
puts "cnt = %d, user = %ds, sys = %ds" % [cnt, user, sys]
------------------------------
Needless to say, I returned the Toshiba.
. Reply