| | | | | | |

Core i5-3210M vs i5-4690K


Description
The i5-3210M is based on Ivy Bridge architecture while the i5-4690K is based on Haswell.

Using the multithread performance as a reference, the i5-3210M gets a score of 51.7 k points while the i5-4690K gets 117.4 k points.

Summarizing, the i5-4690K is 2.3 times faster than the i5-3210M . To get a proper comparison between both models, take a look to the data shown below.

Specs
CPUID
306a9
306c3
Core
Ivy Bridge
Haswell
Architecture
Base frecuency
2.5 GHz
3.5 GHz
Boost frecuency
3.1 GHz
3.9 GHz
Socket
Socket G2 (988B)
LGA 1150
Cores/Threads
2 /2
4/4
TDP
35 W
88 W
Cache L1 (d+i)
2x32+2x32 kB
4x32+4x32 kB
Cache L2
2x256 kB
4x256 kB
Cache L3
3072 kB
6144 kB
Date
June 2012
June 2014
Mean monothread perf.
24.9k points
34.37k points
Mean multithread perf.
51.73k points
117.37k points

Non-optimized benchmark
The benchmark in Mode 0 (FPU) measures cpu performance with non-optimized software. It uses the basic µinstructions from the i386 architecture with the i387 floating point unit. This mode is compatible with all CPUs so it's practical to compare very different CPUs
Monothread
i5-3210M
i5-4690K
Test#1 (Integers)
3.08k
4.39k (x1.42)
Test#2 (FP)
8.58k
10.93k (x1.27)
Test#3 (Generic, ZIP)
3.76k
4.82k (x1.28)
Test#1 (Memory)
3.99k
4.11k (x1.03)
TOTAL
19.42k
24.26k (x1.25)

Multithread

i5-3210M

i5-4690K
Test#1 (Integers)
5.79k
8.67k (x1.5)
Test#2 (FP)
18.77k
21.42k (x1.14)
Test#3 (Generic, ZIP)
8.74k
9.52k (x1.09)
Test#1 (Memory)
4.59k
4.18k (x0.91)
TOTAL
37.89k
43.79k (x1.16)

SSE3 optimized benchmark
The benchmark in mode I (SSE) is optimized for the use of SIMD instructions with 128 bits register and the SSE set up to version 3. Nearly every modern CPU has support for this mode.
Monothread
i5-3210M
i5-4690K
Test#1 (Integers)
8.59k
13.67k (x1.59)
Test#2 (FP)
8.88k
11.97k (x1.35)
Test#3 (Generic, ZIP)
3.59k
5.12k (x1.43)
Test#1 (Memory)
3.45k
4.4k (x1.27)
TOTAL
24.51k
35.17k (x1.43)

Multithread

i5-3210M

i5-4690K
Test#1 (Integers)
20.18k
51.76k (x2.57)
Test#2 (FP)
19.96k
43.26k (x2.17)
Test#3 (Generic, ZIP)
8.93k
19.32k (x2.16)
Test#1 (Memory)
4.6k
2.69k (x0.58)
TOTAL
53.67k
117.03k (x2.18)

AVX optimized benchmark
The benchmark in mode II (AVX) is optimized to used 256 bits registers beside the first version of the Advanced Vector Extensions (AVX). The first AVX compatible CPU was released in 2011.
Monothread
i5-3210M
i5-4690K
Test#1 (Integers)
9.11k
13.71k (x1.5)
Test#2 (FP)
8.88k
12.53k (x1.41)
Test#3 (Generic, ZIP)
3.46k
4.98k (x1.44)
Test#1 (Memory)
3.45k
3.15k (x0.91)
TOTAL
24.9k
34.37k (x1.38)

Multithread

i5-3210M

i5-4690K
Test#1 (Integers)
18.72k
50.91k (x2.72)
Test#2 (FP)
21.09k
45.46k (x2.16)
Test#3 (Generic, ZIP)
8.38k
18.55k (x2.21)
Test#1 (Memory)
3.54k
2.44k (x0.69)
TOTAL
51.73k
117.37k (x2.27)

Performance/W
i5-3210M
i5-4690K
Test#1 (Integers)
535 points/W
579 points/W
Test#2 (FP)
603 points/W
517 points/W
Test#3 (Generic, ZIP)
239 points/W
211 points/W
Test#1 (Memory)
101 points/W
28 points/W
TOTAL
1478 points/W
1334 points/W

Performance/GHz
i5-3210M
i5-4690K
Test#1 (Integers)
2939 points/GHz
3515 points/GHz
Test#2 (FP)
2863 points/GHz
3213 points/GHz
Test#3 (Generic, ZIP)
1117 points/GHz
1277 points/GHz
Test#1 (Memory)
1112 points/GHz
807 points/GHz
TOTAL
8032 points/GHz
8812 points/GHz

Monothread performance graph
Monothread performance graphics gives the performance vs time. They are useful to measure the time it takes to the CPU to reach the maximum performance.

Usually, CPU's performance will be steady during these tests but if it has a slow frequency strategy, the first samples will show a lower score.


Test#1 (Integers) [points vs time]

grafica bm.hardlimit.com


Test#2 (FP) [points vs time]

grafica bm.hardlimit.com


Test#3 (Generic, ZIP) [points vs time]

grafica bm.hardlimit.com


Test#1 (Memory) [points vs time]

grafica bm.hardlimit.com

Multithread performance graph
Multithread graphs measure the performance against a heavy load during certain time.

If CPU's TDP doesn't limit the frequency and the machine is properly cooled, performance should remain steady vs time. Otherwise, the performance score will oscillate or decrease over time.


Test#1 (Integers) [points vs time]

grafica bm.hardlimit.com


Test#2 (FP) [points vs time]

grafica bm.hardlimit.com


Test#3 (Generic, ZIP) [points vs time]

grafica bm.hardlimit.com


Test#1 (Memory) [points vs time]

grafica bm.hardlimit.com

Hardlimit Benchmark Central - Ver. 3.11.4