Displaying 7 results from an estimated 7 matches for "trmm".
Did you mean:
trim
2010 Sep 16
2
FTP Download
Hi,
I have problems downloading complete folders via ftp with R. Single files
work fine.
I tried Rcurl, but it does not work.
This is my code:
url =
"ftp://disc2.nascom.nasa.gov/data/TRMM/Gridded/Derived_Products/3B42_V6/Daily/2009/"
filenames = getURL(url, ftp.use.epsv = FALSE, ftplistonly = TRUE, crlf =
TRUE)
filenames = paste(url, strsplit(filenames, "\r*\n")[[1]], sep = "")
no problems until here, I get a list with the files I want. But then, when I
use...
2017 Sep 22
0
[RFC] Polly Status and Integration
...n if you argue this is a valid
"automatic optimization" it still is only one improvement shown five
times. Note also how matrix-matrix multiplications perform when there
are not matched:
MultiSource/Benchmarks/VersaBench/bmm/bmm
SingleSource/Benchmarks/Polybench/linear-algebra/kernels/trmm/trmm
Last time I checked the impact of Polly on the TSVC benchmarks I
realized that the effect was due to unrelated passes scheduled by Polly.
This might have changed by now but I doubt it. This leaves ten improved
Polybench benchmarks and whetstone. At least my local version of Polly
does not opt...
2015 Feb 26
5
[LLVMdev] [RFC] AArch64: Should we disable GlobalMerge?
Hi all,
I've started looking at the GlobalMerge pass, enabled by default on
ARM and AArch64. I think we should reconsider that, at least for
AArch64.
As is, the pass just merges all globals together, in groups of 4KB
(AArch64, 128B on ARM).
At the time it was enabled, the general thinking was "it's almost
free, it doesn't affect performance much, we might as well use it".
2017 Sep 22
4
[RFC] Polly Status and Integration
On 09/12/2017 10:26 PM, Gerolf Hoflehner wrote:
>
>
>> On Sep 11, 2017, at 10:47 PM, Hal Finkel via llvm-dev
>> <llvm-dev at lists.llvm.org <mailto:llvm-dev at lists.llvm.org>> wrote:
>>
>>
>> On 09/11/2017 12:26 PM, Adam Nemet wrote:
>>> Hi Hal, Tobias, Michael and others,
>>> *...*
>>>
>>> One thing that I’d
2018 Apr 26
0
Compare test-suite benchmarks performance complied without TBAA, with default TBAA and with new TBAA struct path
...9124600| 0|1.711381977| -0.13|14059124601| 0|
|SingleSource/Benchmarks/Polybench/linear-algebra/kernels/trisolv/trisolv.test | 225|0.103904759| 216435815|0.104026252| -0.12| 216435811| 0|0.104078778| -0.17| 216435811| 0|
|SingleSource/Benchmarks/Polybench/linear-algebra/kernels/trmm/trmm.test | 39|0.918241363| 7071633999|0.921063844| -0.31| 7071634004| 0|0.921306267| -0.33| 7071634004| 0|
|SingleSource/Benchmarks/Polybench/linear-algebra/solvers/durbin/durbin.test | 50|0.723007084| 462483129|0.722617922| 0.05| 462483134| 0|0.723354695| -0.05| 4624...
2014 Jan 28
3
[LLVMdev] MergeFunctions: reduce complexity to O(log(N))
Hi Stepan,
Sorry for the delay. It's great that you are working on MergeFunctions
as well and I agree, we should definitely try to combine our efforts to
improve MergeFunctions.
Just to give you some context, the pass (with the similar function
merging patch) is already being used in a production setting. From my
point of view, it would be better if we focus on improving its
capability
2014 Jan 30
3
[LLVMdev] MergeFunctions: reduce complexity to O(log(N))
...9 75173 0 0.02 75143 0 0.01 75143
Treesort.ll 8 20035 0 0.01 20016 0 0.01 20016
Triang.ll 4 30696 0 0.01 30674 0 0.01 30674
trie.ll 12 33266 0 0.01 33243 0 0.01 33243
trig.ll 9 38056 0 0.01 38033 0 0.01 38242
trim.ll 7 106745 0 0.02 106729 0 0.02 106729
trisolv.ll 12 21126 0 0.01 21075 0 0.01 21075
trmm.ll 12 21556 0 0.01 21508 0 0.01 21508
tsc.ll 16 903509 0 0.08 903481 0 0.09 903481
ts.ll 7 10154 0 0.01 10125 0 0.01 10125
tsp.ll 6 47043 0 0.01 47024 0 0.01 47024
tt.ll 8 20968 0 0.01 20939 0 0.01 20939
tu.ll 8 54279 0 0.02 54250 0 0.02 54250
tv.ll 4 33827 0 0.01 33798 0 0.01 33798
twstats.ll 1 91...