WEBVTT

00:00:00.399 --> 00:00:07.160
life used to be so simple when we wanted to know how computer a compared to

00:00:04.880 --> 00:00:11.320
computer B all we had to do was look at the little tag under it and if you know

00:00:09.120 --> 00:00:15.200
number a was 20% more than number B we knew that give or take computer a was

00:00:13.120 --> 00:00:20.840
going to be 20% faster than computer B but then as architectural designs of

00:00:17.720 --> 00:00:23.560
different processors diverged and a CPU

00:00:20.840 --> 00:00:28.279
that ran at 2 GHz could suddenly be as fast at performing a given real world

00:00:25.800 --> 00:00:34.360
task is another one that ran at 3 GHz we needed a new way to measure performance

00:00:31.840 --> 00:00:38.200
benchmarks no I'm not talking about those kinds of benchmarks I'm talking

00:00:35.879 --> 00:00:43.000
about software programs designed to evaluate the performance of PC

00:00:40.399 --> 00:00:48.680
components or complete systems they fall into two main categories the first main

00:00:45.719 --> 00:00:53.640
type is synthetic benchmarks examples of these include ID to 64's cach and memory

00:00:51.160 --> 00:00:58.879
speed testing module and super pie a small lightweight program that tests how

00:00:55.840 --> 00:01:01.199
quickly a processor can calculate pi to

00:00:58.879 --> 00:01:05.119
a predetermined number of decimal places now synthetic benchmarks are great for

00:01:03.120 --> 00:01:08.720
certain things because their creators are focused on obtaining results with

00:01:06.840 --> 00:01:12.479
maximum repeatability a key characteristic of any test that is to be

00:01:10.320 --> 00:01:17.400
used for scientific style comparisons and minimal potential bottlenecks

00:01:15.240 --> 00:01:21.560
elsewhere in the system to simplify comparisons across different test

00:01:19.479 --> 00:01:26.000
benches and prevent a situation where say you're trying to I don't know test

00:01:23.960 --> 00:01:31.439
the speed of your shiny new Lightning Fast SSD by copying data from a hard

00:01:29.280 --> 00:01:36.640
drive a much slower device in the first place which would make all ssds appear

00:01:34.200 --> 00:01:41.720
to perform identically to each other the same speed as a hard drive the problems

00:01:39.680 --> 00:01:46.399
with synthetic benchmarks are several though first up is that because they

00:01:43.759 --> 00:01:50.920
work to ignore system bottlenecks they often deliver results that don't reflect

00:01:48.520 --> 00:01:54.880
the end user's experience because just because one component is getting twice

00:01:53.200 --> 00:02:00.119
as fast doesn't mean that the rest of the system improved in any tangible way

00:01:57.399 --> 00:02:04.479
and second because benchmarks Run High specialized workloads they are

00:02:01.759 --> 00:02:09.640
notoriously misused by Hardware manufacturers who might manipulate their

00:02:06.759 --> 00:02:14.599
Hardware or drivers to perform better in Industry standard benchmarks even if

00:02:11.959 --> 00:02:19.800
this comes with no day-to-day benefit or even with reduced performance in real

00:02:17.160 --> 00:02:24.599
world tasks which leads us to the other main type of benchmarks realworld

00:02:22.319 --> 00:02:29.920
benchmarks simple versions of these like cinebench or The Benchmark drop down

00:02:26.840 --> 00:02:32.239
built into szip take a predetermined but

00:02:29.920 --> 00:02:36.319
otherwise totally real workload in these cases 3D rendering or file compression

00:02:34.239 --> 00:02:40.319
and decompression and have the computer process it as fast as possible then spit

00:02:38.879 --> 00:02:44.800
out a number to tell you how well it went while more complicated real world

00:02:42.879 --> 00:02:49.879
benchmarks often need to be custom developed by PC Hardware Publications

00:02:47.319 --> 00:02:54.159
like aanch with their storage Benchmark Suite that was created by recording the

00:02:52.239 --> 00:02:59.159
actions of a user performing everyday tasks on a computer than running that IO

00:02:56.959 --> 00:03:03.959
trace on every new drive that enters the lab but some benchmarks don't really

00:03:01.640 --> 00:03:09.519
fall cleanly into either of these two categories future marks PC Mark and 3D

00:03:06.920 --> 00:03:13.680
Mark series are great examples here they feature components that are purely

00:03:11.920 --> 00:03:18.799
synthetic like measurements of in-game physics performance on a CPU components

00:03:16.400 --> 00:03:23.400
that are real world based like webpage loading times and then they spit out a

00:03:20.959 --> 00:03:29.200
score that in theory quantifies the performance of the machine all right

00:03:26.080 --> 00:03:31.640
lonus then so which one should I believe

00:03:29.200 --> 00:03:37.000
synthetic or real world or like the hybrid model and the answer is kind of

00:03:34.159 --> 00:03:42.480
all three if a real world Benchmark is available for your exact given workload

00:03:39.519 --> 00:03:46.760
let's say 4K video editing then go with that first but if it's not available or

00:03:45.120 --> 00:03:51.239
you're planning for a future hypothetical workload a hybrid or

00:03:49.280 --> 00:03:55.319
synthetic Benchmark may be your only choice so just make sure that you

00:03:53.159 --> 00:03:59.840
educate yourself about what the numbers you're looking at mean before making a

00:03:57.720 --> 00:04:04.000
purchasing decision and speaking of educating yourself about numbers before

00:04:01.480 --> 00:04:08.040
making a purchasing decision dollarshaveclub.com you got to educate

00:04:05.879 --> 00:04:12.560
yourself about the numbers in this case price tags before you make a purchasing

00:04:10.040 --> 00:04:17.079
decision in this case razors Dollar Shave Club delivers high quality razors

00:04:14.560 --> 00:04:19.959
straight to your door for much less and it's amazing because they're actually

00:04:18.239 --> 00:04:24.400
like it includes shipping in the fact that they cost less than the ones that

00:04:21.959 --> 00:04:29.720
you actually have to get off your butt go to the store get them to unlock the

00:04:26.479 --> 00:04:31.199
stupid cabinet and buy in person I mean

00:04:29.720 --> 00:04:35.960
this is more work for you and you're spending more money great little program

00:04:33.520 --> 00:04:40.600
there save money and save time actually I think their slogan is shave time shave

00:04:38.320 --> 00:04:43.919
money which is very funny they're funny guys and those funny guys also have

00:04:42.560 --> 00:04:47.320
other products they've got their Dr Carver shave butter which goes on clear

00:04:45.800 --> 00:04:52.039
so you can see what you're doing while you're shaving they've got their one wipe Charlie which also help you see

00:04:50.479 --> 00:04:57.360
what you're doing when you're wiping your butt with peppermint scented wipes

00:04:54.800 --> 00:05:01.160
and uh get over to dollarshaveclub.com Linus to join the club and start looking

00:04:59.800 --> 00:05:04.680
good without having to go out of the house looking like a scrub in the first

00:05:02.880 --> 00:05:08.800
place to get the supplies you need to look good when you leave the house

00:05:07.400 --> 00:05:12.680
thanks for watching this episode as fast as possible guys like this video if you liked it dislike it if you disliked it

00:05:11.479 --> 00:05:18.080
leave a comment letting me know if you have suggestions for future fastest possibles and as always if you aren't

00:05:15.880 --> 00:05:22.840
already don't forget to subscribe and share this video if you thought it was

00:05:19.319 --> 00:05:22.840
helpful in somewhere