I'm attaching perf measurements on SKX machine for avx2-i32x8, avx2-i32x16,
avx512skx-i32x8, and avx512skx-i32x16 targets.
Note, that some benchmarks behave better with "double pumped" targets (i.e.
avx2-i32x16), than with targets with native architecture width. So it makes
sense to have a closer look at individual benchmarks, rather than just
looks at geomean.
Also, don't put attention to "ISPC+tasks", as examples are not really tuned
for that wide machine (my machine has 2x28 cores with enabled HT, i.e. 112
virtual cores). So these runs basically don't have enough work for that
many cores.
Raw speedup geomean (against clang-8 compiler) is:
avx2-i32x8: 6.85
avx2-i32x16: 7.33
avx512skx-i32x8: 7.13
avx512skx-i32x16: 9.18
Dmitry.
On Wed, Sep 25, 2019 at 3:56 PM Dmitry Babokin <[email protected]> wrote:
> Hi,
>
> We haven't updated performance numbers for a while, thanks for pointing
> this out.
>
> I'll make measurements on the machine that I have and will post the
> results here. And we'll update the "official" numbers a bit later.
>
> AVX512 is indeed ideal target for ISPC. Though a few factors need to be
> taken into account. AVX512 triggers lower frequencies than AVX2, which
> contributes to less-than-expected scaling factor when going to 16 lanes.
>
> We also have AVX512 8-wide target, which doesn't triggers frequency
> problem.
>
> Right now the most common platform with AVX512 is server Skylake platform
> (Purley).
>
> AVX512 is also available on the client in Ice Like chips (since recently),
> but unfortunatelly I don't have such machines within my reach. It would be
> very interesting to experiment with their performance. But they are
> *client* chips, which means they have fewer AVX execution units, than
> server parts.
>
> I'll run tests on Skylake server and post it here.
>
> Dmitry.
>
> On Wed, Sep 25, 2019 at 3:43 PM bb3141 <[email protected]> wrote:
>
>> Hi,
>>
>> the speedup of ISPC-vectorized is very impressive and for SSE and AVX,
>> many of the examples show near ideal 4x and 8x scaling with the SIMD width.
>>
>> So I'm very interested in the results of the 16 wide AVX512 for the
>> common ISPC examples (like aobench and ray-tracer).
>> In theory, AVX512 should be the ideal hardware for ISPC with a potential
>> of sixteen times speedup. (the only limiting factor would be memory
>> bandwidth).
>>
>> Am I missing something or are the AVX512 results not reported in the
>> "performance" paper ?
>>
>> Does anyone have some numbers that comprae the speedup (esp. with respect
>> to 8 wide AVX2)
>> or build an run the examples on a AVX512 capable machine ?
>>
>> Thanks & Regards,
>> bb3141
>>
>>
>>
>>
>>
>>
>>
>>
>> --
>> You received this message because you are subscribed to the Google Groups
>> "Intel SPMD Program Compiler Users" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to [email protected].
>> To view this discussion on the web visit
>> https://groups.google.com/d/msgid/ispc-users/7405df17-7632-4b1e-bd8a-5da48ca8a8f9%40googlegroups.com
>> <https://groups.google.com/d/msgid/ispc-users/7405df17-7632-4b1e-bd8a-5da48ca8a8f9%40googlegroups.com?utm_medium=email&utm_source=footer>
>> .
>>
>
--
You received this message because you are subscribed to the Google Groups
"Intel SPMD Program Compiler Users" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/ispc-users/CACRFwuhTD-Xiz2GsuYq_mrO5mAF_eKtOuq0PL3uyUkd7yQKsCg%40mail.gmail.com.
Using test compiler: Intel(r) SPMD Program Compiler (ispc), 1.12.0 (build
commit 2a3fc60c1c60008d @ 20190816, LLVM 8.0.0)
Using C/C++ compiler: clang version 8.0.1
AOBench
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
8.16 / 237.11 / 9459.887 / 325.533 / 77186.992
8.09 / 400.3 / 9688.94 / 195.788 / 78373.627
7.93 / 409.1 / 9725.385 / 188.633 / 77169.791
Deferred Shading
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
79.42 / 15.948 / 1266.561
78.76 / 16.067 / 1265.473
78.75 / 16.088 / 1267.016
Mandelbrot Set
TEST COMPILER:
ISPC speedup / ISPC time / serial time
6.4 / 34.799 / 222.825
6.8 / 32.615 / 221.937
6.56 / 34.111 / 223.878
Mandelbrot Set
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
286.45 / 387.396 /110968.696
302.79 / 365.949 /110804.439
298.79 / 368.514 / 110108.88
Perlin Noise Function
TEST COMPILER:
ISPC speedup / ISPC time / serial time
6.91 / 1501.246 / 10379.055
7.07 / 1470.048 / 10386.769
7.09 / 1478.048 / 10484.93
Binomial Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
14.44 / 225.52 / 124.505 / 7.973 / 1797.931
14.35 / 315.08 / 124.393 / 5.667 / 1785.629
14.43 / 185.79 / 124.609 / 9.681 / 1798.671
Black-Scholes Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
14.52 / 56.92 / 1.618 / 0.413 / 23.5
14.08 / 50.77 / 1.669 / 0.463 / 23.503
13.74 / 53.98 / 1.658 / 0.422 / 22.773
Ray Tracer
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
8.68 / 78.09 / 5056.374 / 562.241 / 43906.972
8.58 / 78.9 / 5118.906 / 556.469 / 43905.806
8.6 / 77.4 / 5057.941 / 562.179 / 43511.338
3D Stencil
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.25 / 17.75 / 454.062 / 83.237 / 1477.561
3.31 / 17.89 / 448.462 / 83.068 / 1485.916
3.39 / 18.8 / 458.668 / 82.7 / 1555.018
Volume Rendering
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
4.14 / 103.88 / 6367.294 / 253.726 / 26357.288
4.49 / 114.98 / 6126.932 / 239.354 / 27519.95
4.21 / 112.43 / 6112.981 / 228.894 / 25733.764
Sort
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
2.96 / 6.29 / 3131.937 / 1470.962 / 9256.608
3.0 / 5.88 / 3076.009 / 1568.769 / 9225.253
3.03 / 7.35 / 3052.717 / 1258.886 / 9258.631
TEST COMPILER:
--------------------------------------------------------------------------
test name: ISPC speedup: ISPC + tasks speedup: | ISPC time:
ISPC + tasks time: serial:
AOBench:
max: 8.16 409.10 |min: 9459.89
188.63 77169.79
diff: 0.23 171.99 | 265.50
136.90 1203.84
Deferred Shading:
max: n/a 79.42 |min: n/a
15.95 1265.47
diff: n/a 0.67 | n/a
0.14 1.54
Mandelbrot Set:
max: 6.80 302.79 |min: 32.62
365.95 221.94
diff: 0.40 16.34 | 2.18
21.45 1.94
Perlin Noise Function:
max: 7.09 n/a |min: 1470.05
n/a 10379.06
diff: 0.18 n/a | 31.20
n/a 105.88
Binomial Options:
max: 14.44 315.08 |min: 124.39
5.67 1785.63
diff: 0.09 129.29 | 0.22
4.01 13.04
Black-Scholes Options:
max: 14.52 56.92 |min: 1.62
0.41 22.77
diff: 0.78 6.15 | 0.05
0.05 0.73
Ray Tracer:
max: 8.68 78.90 |min: 5056.37
556.47 43511.34
diff: 0.10 1.50 | 62.53
5.77 395.63
3D Stencil:
max: 3.39 18.80 |min: 448.46
82.70 1477.56
diff: 0.14 1.05 | 10.21
0.54 77.46
Volume Rendering:
max: 4.49 114.98 |min: 6112.98
228.89 25733.76
diff: 0.35 11.10 | 254.31
24.83 1786.19
Sort:
max: 3.03 7.35 |min: 3052.72
1258.89 9225.25
diff: 0.07 1.47 | 79.22
309.88 33.38
---------------------------------------------------------------------------------
Geomean: 6.85 84.57 | 539.36
68.72 3269.59
Using test compiler: Intel(r) SPMD Program Compiler (ispc), 1.12.0 (build
commit 2a3fc60c1c60008d @ 20190816, LLVM 8.0.0)
Using C/C++ compiler: clang version 8.0.1
AOBench
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
9.55 / 237.24 / 8299.657 / 334.217 / 79289.254
9.19 / 131.14 / 8577.204 / 601.193 / 78839.791
9.34 / 133.05 / 8331.638 / 584.617 / 77784.247
Deferred Shading
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
80.42 / 15.73 / 1265.011
78.0 / 16.224 / 1265.428
79.85 / 15.828 / 1263.806
Mandelbrot Set
TEST COMPILER:
ISPC speedup / ISPC time / serial time
10.87 / 21.555 / 234.373
10.7 / 20.869 / 223.294
10.72 / 20.716 / 222.038
Mandelbrot Set
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
394.11 / 281.381 /110896.213
355.05 / 310.229 /110146.554
573.76 / 192.937 /110699.577
Perlin Noise Function
TEST COMPILER:
ISPC speedup / ISPC time / serial time
6.4 / 1620.312 / 10363.103
6.67 / 1557.326 / 10386.689
6.47 / 1605.658 / 10383.198
Binomial Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
14.53 / 328.39 / 123.33 / 5.456 / 1791.647
13.78 / 329.97 / 130.519 / 5.449 / 1798.141
13.71 / 318.78 / 130.525 / 5.612 / 1789.115
Black-Scholes Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
17.37 / 54.39 / 1.326 / 0.423 / 23.023
18.36 / 50.99 / 1.28 / 0.461 / 23.497
18.41 / 56.93 / 1.277 / 0.413 / 23.502
Ray Tracer
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
7.33 / 76.51 / 6009.175 / 575.803 / 44052.169
7.3 / 77.12 / 6043.029 / 571.638 / 44085.02
7.26 / 74.77 / 5993.469 / 581.96 / 43515.321
3D Stencil
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.22 / 18.36 / 472.139 / 82.797 / 1519.824
3.2 / 17.93 / 466.93 / 83.324 / 1494.025
3.32 / 18.34 / 461.818 / 83.49 / 1531.584
Volume Rendering
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
4.15 / 104.97 / 6022.742 / 238.358 / 25020.097
4.14 / 105.72 / 6166.824 / 241.512 / 25532.61
4.19 / 102.64 / 6030.639 / 246.237 / 25274.927
Sort
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.25 / 5.71 / 2831.799 / 1611.209 / 9201.803
3.2 / 5.84 / 2874.285 / 1576.295 / 9203.074
3.19 / 7.43 / 2888.28 / 1238.716 / 9207.616
TEST COMPILER:
--------------------------------------------------------------------------
test name: ISPC speedup: ISPC + tasks speedup: | ISPC time:
ISPC + tasks time: serial:
AOBench:
max: 9.55 237.24 |min: 8299.66
334.22 77784.25
diff: 0.36 106.10 | 277.55
266.98 1505.01
Deferred Shading:
max: n/a 80.42 |min: n/a
15.73 1263.81
diff: n/a 2.42 | n/a
0.49 1.62
Mandelbrot Set:
max: 10.87 573.76 |min: 20.72
192.94 222.04
diff: 0.17 218.71 | 0.84
117.29 12.33
Perlin Noise Function:
max: 6.67 n/a |min: 1557.33
n/a 10363.10
diff: 0.27 n/a | 62.99
n/a 23.59
Binomial Options:
max: 14.53 329.97 |min: 123.33
5.45 1789.12
diff: 0.82 11.19 | 7.20
0.16 9.03
Black-Scholes Options:
max: 18.41 56.93 |min: 1.28
0.41 23.02
diff: 1.04 5.94 | 0.05
0.05 0.48
Ray Tracer:
max: 7.33 77.12 |min: 5993.47
571.64 43515.32
diff: 0.07 2.35 | 49.56
10.32 569.70
3D Stencil:
max: 3.32 18.36 |min: 461.82
82.80 1494.03
diff: 0.12 0.43 | 10.32
0.69 37.56
Volume Rendering:
max: 4.19 105.72 |min: 6022.74
238.36 25020.10
diff: 0.05 3.08 | 144.08
7.88 512.51
Sort:
max: 3.25 7.43 |min: 2831.80
1238.72 9201.80
diff: 0.06 1.72 | 56.48
372.49 5.81
---------------------------------------------------------------------------------
Geomean: 7.33 84.88 | 501.06
68.2 3269.23
Using test compiler: Intel(r) SPMD Program Compiler (ispc), 1.12.0 (build
commit 2a3fc60c1c60008d @ 20190816, LLVM 8.0.0)
Using C/C++ compiler: clang version 8.0.1
AOBench
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
12.97 / 179.92 / 6269.041 / 452.056 / 81334.532
12.91 / 211.34 / 6290.805 / 384.306 / 81217.598
12.55 / 165.19 / 6507.989 / 494.563 / 81699.029
Deferred Shading
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
73.59 / 17.248 / 1269.266
77.74 / 16.248 / 1263.044
76.73 / 16.544 / 1269.456
Mandelbrot Set
TEST COMPILER:
ISPC speedup / ISPC time / serial time
9.65 / 24.291 / 234.29
9.23 / 24.043 / 221.916
9.64 / 24.295 / 234.124
Mandelbrot Set
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
340.49 / 323.531 /110158.516
546.44 / 202.768 / 110800.66
326.47 / 337.272 /110108.103
Perlin Noise Function
TEST COMPILER:
ISPC speedup / ISPC time / serial time
11.45 / 916.18 / 10489.172
11.34 / 920.368 / 10433.638
11.65 / 898.636 / 10473.027
Binomial Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
14.83 / 279.54 / 120.609 / 6.4 / 1789.148
14.05 / 283.18 / 127.994 / 6.35 / 1798.307
14.9 / 168.11 / 120.788 / 10.709 / 1800.269
Black-Scholes Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
23.81 / 48.88 / 0.999 / 0.486 / 23.773
22.95 / 50.81 / 0.995 / 0.45 / 22.841
22.48 / 53.04 / 1.016 / 0.43 / 22.828
Ray Tracer
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
15.22 / 81.98 / 2894.449 / 537.434 / 44060.444
13.78 / 81.58 / 3164.304 / 534.371 / 43591.672
15.31 / 83.35 / 2882.475 / 529.547 / 44136.212
3D Stencil
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.26 / 17.89 / 456.956 / 83.22 / 1488.634
3.26 / 17.86 / 455.958 / 83.305 / 1487.999
3.25 / 17.69 / 455.331 / 83.587 / 1478.705
Volume Rendering
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
5.52 / 109.21 / 4592.725 / 232.267 / 25366.729
5.25 / 114.39 / 4788.693 / 219.675 / 25128.52
5.57 / 110.89 / 4625.763 / 232.26 / 25754.493
Sort
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.1 / 5.47 / 2976.26 / 1688.063 / 9239.611
3.22 / 6.0 / 2979.434 / 1598.567 / 9584.367
3.08 / 5.45 / 2997.197 / 1691.812 / 9228.335
TEST COMPILER:
--------------------------------------------------------------------------
test name: ISPC speedup: ISPC + tasks speedup: | ISPC time:
ISPC + tasks time: serial:
AOBench:
max: 12.97 211.34 |min: 6269.04
384.31 81217.60
diff: 0.42 46.15 | 238.95
110.26 481.43
Deferred Shading:
max: n/a 77.74 |min: n/a
16.25 1263.04
diff: n/a 4.15 | n/a
1.00 6.41
Mandelbrot Set:
max: 9.65 546.44 |min: 24.04
202.77 221.92
diff: 0.42 219.97 | 0.25
134.50 12.37
Perlin Noise Function:
max: 11.65 n/a |min: 898.64
n/a 10433.64
diff: 0.31 n/a | 21.73
n/a 55.53
Binomial Options:
max: 14.90 283.18 |min: 120.61
6.35 1789.15
diff: 0.85 115.07 | 7.39
4.36 11.12
Black-Scholes Options:
max: 23.81 53.04 |min: 0.99
0.43 22.83
diff: 1.33 4.16 | 0.02
0.06 0.95
Ray Tracer:
max: 15.31 83.35 |min: 2882.47
529.55 43591.67
diff: 1.53 1.77 | 281.83
7.89 544.54
3D Stencil:
max: 3.26 17.89 |min: 455.33
83.22 1478.70
diff: 0.01 0.20 | 1.62
0.37 9.93
Volume Rendering:
max: 5.57 114.39 |min: 4592.73
219.68 25128.52
diff: 0.32 5.18 | 195.97
12.59 625.97
Sort:
max: 3.22 6.00 |min: 2976.26
1598.57 9228.33
diff: 0.14 0.55 | 20.94
93.24 356.03
---------------------------------------------------------------------------------
Geomean: 9.18 80.25 | 404.76
72.23 3282.0
Using test compiler: Intel(r) SPMD Program Compiler (ispc), 1.12.0 (build
commit 2a3fc60c1c60008d @ 20190816, LLVM 8.0.0)
Using C/C++ compiler: clang version 8.0.1
AOBench
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
8.16 / 250.15 / 10096.1 / 329.242 / 82360.794
7.81 / 417.32 / 10480.85 / 196.137 / 81852.368
8.16 / 239.8 / 9709.325 / 330.318 / 79208.978
Deferred Shading
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
75.63 / 15.73 / 1189.681
80.26 / 15.81 / 1268.925
77.1 / 16.483 / 1270.897
Mandelbrot Set
TEST COMPILER:
ISPC speedup / ISPC time / serial time
5.66 / 42.074 / 238.099
5.59 / 39.686 / 221.857
5.26 / 42.301 / 222.314
Mandelbrot Set
TEST COMPILER:
ISPC + tasks speedup / ISPC + tasks time / serial time
220.88 / 504.63 /111463.963
390.86 / 282.037 /110238.336
248.38 / 446.8 /110974.917
Perlin Noise Function
TEST COMPILER:
ISPC speedup / ISPC time / serial time
8.33 / 1252.636 / 10433.825
10.03 / 1221.243 / 12247.605
7.83 / 1415.951 / 11089.805
Binomial Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
14.64 / 186.76 / 123.557 / 9.688 / 1809.321
14.2 / 322.46 / 127.131 / 5.598 / 1805.274
15.22 / 246.98 / 124.19 / 7.655 / 1890.572
Black-Scholes Options
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
14.9 / 53.17 / 1.452 / 0.407 / 21.636
14.88 / 49.02 / 1.454 / 0.441 / 21.63
14.75 / 57.22 / 1.548 / 0.399 / 22.828
Ray Tracer
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
8.7 / 79.32 / 5076.047 / 556.465 / 44139.074
8.35 / 80.77 / 5222.569 / 540.132 / 43628.77
8.71 / 78.91 / 5006.506 / 552.516 / 43598.934
3D Stencil
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.29 / 17.9 / 454.285 / 83.402 / 1492.478
3.28 / 17.85 / 452.151 / 83.096 / 1483.228
3.25 / 17.72 / 454.105 / 83.184 / 1473.719
Volume Rendering
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
4.49 / 112.17 / 5950.351 / 238.301 / 26731.297
4.3 / 105.8 / 5970.366 / 242.374 / 25643.371
4.28 / 104.5 / 5950.611 / 243.877 / 25485.511
Sort
TEST COMPILER:
ISPC speedup / ISPC + tasks speedup / ISPC time / ISPC + tasks time / serial
time
3.4 / 6.07 / 2718.454 / 1520.804 / 9238.692
3.34 / 6.42 / 2848.838 / 1481.134 / 9507.952
3.51 / 6.29 / 2634.548 / 1471.168 / 9256.901
TEST COMPILER:
--------------------------------------------------------------------------
test name: ISPC speedup: ISPC + tasks speedup: | ISPC time:
ISPC + tasks time: serial:
AOBench:
max: 8.16 417.32 |min: 9709.33
196.14 79208.98
diff: 0.35 177.52 | 771.52
134.18 3151.82
Deferred Shading:
max: n/a 80.26 |min: n/a
15.73 1189.68
diff: n/a 4.63 | n/a
0.75 81.22
Mandelbrot Set:
max: 5.66 390.86 |min: 39.69
282.04 221.86
diff: 0.40 169.98 | 2.62
222.59 16.24
Perlin Noise Function:
max: 10.03 n/a |min: 1221.24
n/a 10433.83
diff: 2.20 n/a | 194.71
n/a 1813.78
Binomial Options:
max: 15.22 322.46 |min: 123.56
5.60 1805.27
diff: 1.02 135.70 | 3.57
4.09 85.30
Black-Scholes Options:
max: 14.90 57.22 |min: 1.45
0.40 21.63
diff: 0.15 8.20 | 0.10
0.04 1.20
Ray Tracer:
max: 8.71 80.77 |min: 5006.51
540.13 43598.93
diff: 0.36 1.86 | 216.06
16.33 540.14
3D Stencil:
max: 3.29 17.90 |min: 452.15
83.10 1473.72
diff: 0.04 0.18 | 2.13
0.31 18.76
Volume Rendering:
max: 4.49 112.17 |min: 5950.35
238.30 25485.51
diff: 0.21 7.67 | 20.02
5.58 1245.79
Sort:
max: 3.51 6.42 |min: 2634.55
1471.17 9238.69
diff: 0.17 0.35 | 214.29
49.64 269.26
---------------------------------------------------------------------------------
Geomean: 7.13 85.78 | 524.34
67.88 3243.48
