This is a place where people can discuss massiv and possibly other array libraries in Haskell.
The first time I tried it I could not believe that I am that good
I take it back. Compiling without an
openblas makes hmatrix just a little bit slower. I don't remember how I got "orders of magnitude" difference, but in my defence it has been a while since I looked at it:benchmarking HMatrix/MxM Double - (500x800 X 800x500)/Par
time 9.140 ms (4.980 ms .. 12.18 ms)
0.527 R² (0.349 R² .. 0.651 R²)
mean 4.794 ms (2.775 ms .. 6.977 ms)
std dev 5.082 ms (3.646 ms .. 5.969 ms)
variance introduced by outliers: 98% (severely inflated)
benchmarking HMatrix/MxM Float - (500x800 X 800x500)/Par
time 6.678 ms (4.953 ms .. 8.027 ms)
0.743 R² (0.519 R² .. 0.907 R²)
mean 6.208 ms (5.417 ms .. 6.890 ms)
std dev 1.838 ms (1.391 ms .. 2.718 ms)
variance introduced by outliers: 94% (severely inflated)
benchmarking Massiv/MxM P Double - (500x800 X 800x500)/Par
time 6.874 ms (6.559 ms .. 7.147 ms)
0.991 R² (0.987 R² .. 0.995 R²)
mean 7.485 ms (7.157 ms .. 8.063 ms)
std dev 1.246 ms (789.7 μs .. 1.867 ms)
variance introduced by outliers: 79% (severely inflated)
benchmarking Massiv/MxM P Float - (500x800 X 800x500)/Par
time 6.783 ms (6.671 ms .. 6.896 ms)
0.997 R² (0.993 R² .. 0.999 R²)
mean 6.832 ms (6.766 ms .. 6.933 ms)
std dev 238.9 μs (168.5 μs .. 365.5 μs)
variance introduced by outliers: 16% (moderately inflated)
almost 3 times slower, but you said previously it was on how many cores? 16? and this one is on a single core, I presume? a bit strange...
OTOH, "variance introduced by outliers: 98% (severely inflated)" makes it very suspect
98% (severely inflated)
taht's normal for multi core benchmarks
I think I was confused about multicore when run not with openblas, probably because I'm running with -N1 (actually, even without -threaded) --- that may be why it's single core for me
My pleasure. I just got this computer so it is really fun for me to see how much faster all of the benchmarks have gotten 😀
while, presumably, openblas can parallelize even with -N1 (not tested)
In the matter of fact hmatrix doesn't care about RTS flags like
-N since it uses parallelization on C side
well, that's strange then, because I swear my hmatrix doesn't use many cores
(not openblas flag set)
though it probably uses SIMD, etc.
From what I've seen online it is either controlled either by the env variable or som eruntime setting
Or even ENV variables it seems: https://stackoverflow.com/questions/45857566/run-openblas-on-multicore
I have an ancient Ubuntu, so probably the default flags are different
^^^ that link is openblas, though
Yeah, I don't really use any of that stuff aside from benchmarks for massiv. So I am no expert on openblas
Oh sorry, you are right
we are talking results without openblas now, right?
openblas or blas
Cause it seems hmatrix uses either or:
if flag(openblas)
if !flag(disable-default-paths)
extra-lib-dirs: /usr/lib/openblas/lib
extra-libraries: openblas
else
extra-libraries: blas lapack
I read in blas/lapack docs that they are strictly single core and my experience confirms it, but there must be other versions in new Ubuntus for which it doesn't apply any more or perhaps it stopped applying long ago, but now they have different default setting and run multicore
Yeah, I can definitely confirm that without
openblas flag in hmatrix it still uses all cores
man_of_letters:mozilla.org @man_of_letters:mozilla.org fixes his docs
I read in blas/lapack docs that they are strictly single core and my experience confirms it, but there must be other versions in new Ubuntus for which it doesn't apply any more or perhaps it stopped applying long ago, but now they have different default setting and run multicore
Ok, so this is exactly where I got my impression that massiv was much faster than hmatrix without an openblas flag on my older computer whre I used Ubuntu
I think I was comparing single core hmatrix to multicore massiv
back than I mean
Here is something I just learnt, adding more cores to Haskell RTS actually slows down
blas:$ stack bench :mult --ba '--match pattern Par +RTS -N1'
hmatrix-bench> benchmarks
Running 1 benchmarks...
Benchmark mult: RUNNING...
benchmarking HMatrix/MxM Double - (500x800 X 800x500)/Par
time 1.254 ms (1.124 ms .. 1.413 ms)
0.940 R² (0.914 R² .. 0.992 R²)
mean 1.238 ms (1.178 ms .. 1.358 ms)
std dev 267.3 μs (172.2 μs .. 436.6 μs)
variance introduced by outliers: 94% (severely inflated)
benchmarking HMatrix/MxM Float - (500x800 X 800x500)/Par
time 718.8 μs (673.9 μs .. 774.4 μs)
0.942 R² (0.903 R² .. 0.978 R²)
mean 772.8 μs (710.1 μs .. 991.5 μs)
std dev 339.4 μs (120.9 μs .. 675.6 μs)
variance introduced by outliers: 99% (severely inflated)
benchmarking Massiv/MxM P Double - (500x800 X 800x500)/Par
time 62.91 ms (62.26 ms .. 63.55 ms)
1.000 R² (1.000 R² .. 1.000 R²)
mean 63.97 ms (63.25 ms .. 66.65 ms)
std dev 2.304 ms (455.6 μs .. 4.013 ms)
benchmarking Massiv/MxM P Float - (500x800 X 800x500)/Par
time 79.19 ms (78.63 ms .. 79.77 ms)
1.000 R² (1.000 R² .. 1.000 R²)
mean 80.06 ms (79.75 ms .. 80.38 ms)
std dev 557.9 μs (372.2 μs .. 849.1 μs)
that's because the cores are busy and can't be used by blas?
What it means is that I should be comparing this massiv's performance:
benchmarking Massiv/MxM P Double - (500x800 X 800x500)/Par
time 6.887 ms (6.749 ms .. 7.048 ms)
0.993 R² (0.978 R² .. 0.999 R²)
mean 7.009 ms (6.888 ms .. 7.235 ms)
std dev 425.6 μs (220.2 μs .. 638.2 μs)
variance introduced by outliers: 33% (moderately inflated)To hmatrix as such:
benchmarking HMatrix/MxM Double - (500x800 X 800x500)/Par
time 1.254 ms (1.124 ms .. 1.413 ms)
0.940 R² (0.914 R² .. 0.992 R²)
mean 1.238 ms (1.178 ms .. 1.358 ms)
std dev 267.3 μs (172.2 μs .. 436.6 μs)
variance introduced by outliers: 94% (severely inflated)
so that's single-core RTS plus multicore blas/lapack vs multicore RTS?
No it is compared with multicore RTS massiv:
benchmarking Massiv/MxM P Double - (500x800 X 800x500)/Par
time 6.887 ms (6.749 ms .. 7.048 ms)
0.993 R² (0.978 R² .. 0.999 R²)
mean 7.009 ms (6.888 ms .. 7.235 ms)
std dev 425.6 μs (220.2 μs .. 638.2 μs)
variance introduced by outliers: 33% (moderately inflated)
multicore blas/lapack with multicore RTS
is this
is this
benchmarking HMatrix/MxM Double - (500x800 X 800x500)/Par
time 2.457 ms (1.275 ms .. 4.701 ms)
0.276 R² (0.256 R² .. 0.971 R²)
mean 1.716 ms (1.392 ms .. 3.427 ms)
std dev 1.666 ms (311.3 μs .. 3.915 ms)
variance introduced by outliers: 98% (severely inflated)
I ran into the following compilation error (macOS 12.5, ghc 8.10.7). Any help to resolve this greatly appreciated.
src/Data/Massiv/Array/Manifest/Unboxed.hs:147:33: error:
• Couldn't match type ‘m’ with ‘ST (PrimState m)’
‘m’ is a rigid type variable bound by
the type signature for:
initialize :: forall ix (m :: * -> *).
(Index ix, PrimMonad m) =>
MArray (PrimState m) U ix e -> m ()
at src/Data/Massiv/Array/Manifest/Unboxed.hs:147:3-12
Expected type: m ()
Actual type: ST (PrimState m) ()
• In the expression: VGM.basicInitialize marr
In an equation for ‘initialize’:
initialize (MUArray _ marr) = VGM.basicInitialize marr
In the instance declaration for ‘Manifest U e’
• Relevant bindings include
marr :: MVU.MVector (PrimState m) e
(bound at src/Data/Massiv/Array/Manifest/Unboxed.hs:147:25)
initialize :: MArray (PrimState m) U ix e -> m ()
(bound at src/Data/Massiv/Array/Manifest/Unboxed.hs:147:3)
|
147 | initialize (MUArray _ marr) = VGM.basicInitialize marr
| ^^^^^^^^^^^^^^^^^^^^^^^^
cabal: Failed to build massiv-1.0.1.1 (which is required by exe:massiv-stuff
3 replies
