power8 | Start menu replacer for Windows | Menu library

I want to convert a str number into a float or int numerical type. However, it is throwing an error that it can't, so I am removing the comma. The comma will not be removed, so I need to find a way of finding a way of designating the location in the number space like say fourth.

I am building a distributed spatial index in Python with a wrapped C++ extension. I am trying to use Dask (for the first time) instead of MPI. The current implementation works, but has several problems.

1. The critical part is the large overhead compared to serial execution. I would expect an almost linear speed-up from the algorithm.

2. Persist does not seem to do what I expect, as timings of the first query are much longer than in the second.

3. for my eyes the code looks unidiomatic, but as said, I am new to Dask. Is there a better way of doing this?

4. I need to to do some indexing into the delayed objects when using 2d chunks. That does not occur with 1d chunks and feels weird.

The algorithm builds sorts list of particles and then builds an octree, where nodes reference contiguous blocks of particles by in the sorted array by a pair of (start, end) indices. Queries take a boundary box and search overlapping nodes in the octree collect particles actually in the boundary box from the resulting candidates. Both building and queries are purely serial.

Parallelisation is done by randomly splitting up the particles, building tree on each subset. Queries are broadcast across all sub-indices and results are concatenated back together. Dask felt like a natural fit here. I use persist to generate the index once and keep it around as I expect many queries per index.

I tried map_blocks but this only seems to work for array to array transformations. Further, various permutations of persist/compute have been tried.

I have a stored procedure such as below :

I'm porting a application that uses AES encryption and decryption instructions to randomize some data from x86 to POWER8. I hit a wall with the _mm_aesdec_si128 instruction, it seems to do something different than the equivalent IBM __builtin_crypto_vncipher. The documentation at https://link.springer.com/content/pdf/10.1007/978-3-642-03317-9_4.pdf, pages 52-54, mention that it follows FIPS 197. The IBM documentation at https://ibm.ent.box.com/s/jd5w15gz301s5b5dt375mshpq9c3lh4u, page 305 also says that it follow FIPS197, the only difference is that the order of InvMixColumns and the xor with round key are flipped, but does that change the result?

How can they both say they follow the specification if the results are different?

The following C program works fine in x86, but will output the wrong result for aesdec in ppc64. The aesenc in ppc64 thankfully works as expected.

For now I solved the problem by using a software implementation of aesdec, but I want to do everything in hardware.

C program:

I got a dialog, which displays numbers. In the last row I want to display the sum of these 10 numbers, while the user changes these numbers. So for example if the user changes the 50 to 60 I want the last row to display 110. What is a good way to implement that? Following some html of the dialog:

I'm working on a simple JIT compiler for PowerPC, I followed the examples in https://github.com/spencertipping/jit-tutorial to get a hang of how to work with it.

The problem is that the identity function in the second example "jitproto.c" can't really be ported to powerpc as is, using the "LWA" and "BLR" instructions, it just causes segfaults when executed.

In the end I used the machine code output of the SLJIT compiler (https://github.com/linux-on-ibm-z/sljit) to see what I'm doing wrong, and I see it generates 12 instruction words before what I thought would be the function.

So what are those instructions doing? Why can't I just start the function directly like in x86?

Code can be compiled with a C99 compiler on PPC64 (tested in a powermac and a power8 server).

I'm catching an assembler error when using inline assembly and a local label. The compiler is GCC, and the machine is PowerPC running AIX. The code reads the timestamp (it is roughly equivalent to rdtsc):

I'm suffering GCC inline assembly on PowerPC. The program compiles fine with -g2 -O3, but fails to compile with -g3 -O0. The problem is, I need to observe it under the debugger so I need symbols without optimizations.

Here is the program:

I'm on GCC112, which is a little-endian Power8 machine running Linux. Power8 has in-core crypto providing AES, SHA and a few other useful features. I'm trying to determine the availability of the features at runtime using getauxval. The use case is distros building for a "minimum" capable machine, and we need to swap-in a faster function at runtime.

The dump of hwcaps.h is shown below, but it lacks specific bits for Power8, AES, SHA and others. However, I believe Power8 is ISA 2.07, and ISA 2.07 has the bit PPC_FEATURE2_ARCH_2_07.

The thing I am not clear on is, is Power8 in-core crypto optional like ARM's crypto under ARMv8. I can't find a document that clearly states the requirement, and I don't have a membership to OpenPower to access ISA documents. (Another possibility is, it is stated but I missed it in the docs).

Is it possible to use getauxval to query the runtime environment for the features? If not, then how do we determine feature availability at runtime? Is CPU probing the only alternative available?

Maybe more generally, how do we determine Power6, Power7 and Power8 runtime environments?

auxv.h is mostly empty. The header file includes hwcaps.h.