www.digitalmars.com         C & C++   DMDScript  

digitalmars.D.learn - Question on SSE intrinsics

reply piotrekg2 <piotrekg2 gmail.com> writes:
Hi,
I'm trying to port some of my c++ code which uses sse2 
instructions into D. The code calls the following intrinsics:

- _mm256_loadu_si256
- _mm256_movemask_epi8

Do they have any equivalent intrinsics in D?

I'm compiling my c++ code using gcc.

Thanks,
Piotr
Jul 29
next sibling parent Eugene Wissner <belka caraus.de> writes:
On Saturday, 29 July 2017 at 16:01:07 UTC, piotrekg2 wrote:
 Hi,
 I'm trying to port some of my c++ code which uses sse2 
 instructions into D. The code calls the following intrinsics:

 - _mm256_loadu_si256
 - _mm256_movemask_epi8

 Do they have any equivalent intrinsics in D?

 I'm compiling my c++ code using gcc.

 Thanks,
 Piotr
https://stackoverflow.com/questions/14002946/explicit-simd-code-in-d I don't think something has changed since then.
Jul 29
prev sibling parent reply Johan Engelen <j j.nl> writes:
On Saturday, 29 July 2017 at 16:01:07 UTC, piotrekg2 wrote:
 Hi,
 I'm trying to port some of my c++ code which uses sse2 
 instructions into D. The code calls the following intrinsics:

 - _mm256_loadu_si256
 - _mm256_movemask_epi8

 Do they have any equivalent intrinsics in D?
Yes, with LDC (probably GDC too). But unfortunately we don't have the "_mm256" functions (yet?), instead we have GCC's "__builtin_ia32..." functions. The first one you mention I think is just an unaligned load? That can be done with the template `loadUnaligned` from module ldc.simd. The second one has a synonym, "__builtin_ia32_pmovmskb256". -Johan
Jul 29
parent reply piotrekg2 <piotrekg2 gmail.com> writes:
On Saturday, 29 July 2017 at 18:19:47 UTC, Johan Engelen wrote:
 On Saturday, 29 July 2017 at 16:01:07 UTC, piotrekg2 wrote:
 Hi,
 I'm trying to port some of my c++ code which uses sse2 
 instructions into D. The code calls the following intrinsics:

 - _mm256_loadu_si256
 - _mm256_movemask_epi8

 Do they have any equivalent intrinsics in D?
Yes, with LDC (probably GDC too). But unfortunately we don't have the "_mm256" functions (yet?), instead we have GCC's "__builtin_ia32..." functions. The first one you mention I think is just an unaligned load? That can be done with the template `loadUnaligned` from module ldc.simd. The second one has a synonym, "__builtin_ia32_pmovmskb256". -Johan
What about __builtin_ctz?
Jul 29
parent reply Nicholas Wilson <iamthewilsonator hotmail.com> writes:
On Saturday, 29 July 2017 at 22:45:12 UTC, piotrekg2 wrote:
 On Saturday, 29 July 2017 at 18:19:47 UTC, Johan Engelen wrote:
 On Saturday, 29 July 2017 at 16:01:07 UTC, piotrekg2 wrote:
 Hi,
 I'm trying to port some of my c++ code which uses sse2 
 instructions into D. The code calls the following intrinsics:

 - _mm256_loadu_si256
 - _mm256_movemask_epi8

 Do they have any equivalent intrinsics in D?
Yes, with LDC (probably GDC too). But unfortunately we don't have the "_mm256" functions (yet?), instead we have GCC's "__builtin_ia32..." functions. The first one you mention I think is just an unaligned load? That can be done with the template `loadUnaligned` from module ldc.simd. The second one has a synonym, "__builtin_ia32_pmovmskb256". -Johan
What about __builtin_ctz?
https://github.com/ldc-developers/druntime/blob/ldc/src/ldc/intrinsics.di#L325
Jul 29
parent Nicholas Wilson <iamthewilsonator hotmail.com> writes:
On Sunday, 30 July 2017 at 02:05:32 UTC, Nicholas Wilson wrote:
 On Saturday, 29 July 2017 at 22:45:12 UTC, piotrekg2 wrote:
 What about __builtin_ctz?
https://github.com/ldc-developers/druntime/blob/ldc/src/ldc/intrinsics.di#L325
you can also make it out of bsf or bsr (i can't remember which) from `core.bitop`
Jul 29