| Re: [eigen] Custom memory allocators with eigen |
[ Thread Index |
Date Index
| More lists.tuxfamily.org/eigen Archives
]
- To: eigen@xxxxxxxxxxxxxxxxxxx
- Subject: Re: [eigen] Custom memory allocators with eigen
- From: Alberto Luaces <eigen@xxxxxxxxxxxxxxxxxxxx>
- Date: Wed, 17 Mar 2021 09:09:54 +0100
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=fastmail.com; h= references:from:to:subject:in-reply-to:date:message-id :mime-version:content-type; s=fm2; bh=mVOdSLrqU7QvRLkyBjOsYL1guu vUizKp/HBsZtIXbQI=; b=WmlIn5Ct66fu7u+z8S0xmHGvXdzEi8ICiW1ak8s6a0 lYPNVvye3VPWloe5z0HxAWxr0YD+lBis4InIz8vUfYUnmUTOgfa1Sy0ucKPQbBsq Put7J4SbGNX3Jpx2bDTcsnkRIbbQl3IClsz9QyE2f8qscWKQWu94WJ1YJhKGa+hy ZZyrlUdNOyIBFodGH4GRy4ZnQZRETJN8nyMkG8xZc1VUWQpiat/4ZPDPcec0J6+Z sXYCK9jPp3MHkHDgwAcrwAh7XWgIEeFGcbWR6WRIe4SuITHUjS4i9Ew3T1GyHKB2 zjUJbcD0vOk6CxKdgu76W0/HEQYZ5Ocr0fKU/l9uXoww==
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to:x-me-proxy :x-me-proxy:x-me-sender:x-me-sender:x-sasl-enc; s=fm2; bh=mVOdSL rqU7QvRLkyBjOsYL1guuvUizKp/HBsZtIXbQI=; b=hIB/2cTQn8dY2F1QFkQh+v +imOZaT9xOkLT01m8BT4lzA7R2vigLHTOmzUrHCN1VkZP4Gt0sAJPtWJdIg8T1ZP aMc0CVpicZjPo4KX/dLTtOEoJu0hMeKtjd2KmjLKNCl3vWtzq+9pzsnYwnRNYrbU v58Fd6bfmQhEkZCXDbVJo8+eugmBawBRczuxDOWBl15f8lW70wSPo+q3NBPITUqq akiUCnC98uu/H4cIWjwk0mLVsPw/4k7tk8nubE7X7apd336uAgVEyr8EYdYw1zEW hfdeicuiEVCKKMezj7kBR2vTX8IyLcPJJzRPZQ1ztoxRRbLSROpzLdgPm+dYAZsQ ==
Edward Lam writes:
> On Mon, Mar 15, 2021 at 12:32 PM Rasmus Munk Larsen <rmlarsen@xxxxxxxxxx>
> wrote:
>
>> Have you considered using a more general purpose solution like tcmalloc or
>> jemalloc?
>>
>> https://github.com/google/tcmalloc
>> https://github.com/jemalloc/jemalloc
>>
I have considered it, but certainly not tried, since the allocator
looked like the most specific approach (and platform-independent). Of
course since I am a LD_PRELOAD away of trying, I will do.
>
> FWIW, on a side note, jemalloc required defining
> EIGEN_MALLOC_ALREADY_ALIGNED to 0 the last time I tried it because its
> allocator didn't guarantee always 16-byte aligned pointers. For really
> small allocations, it can return 8-byte aligned pointers.
>
Thanks for pointing that!. In the case the wrong alignment were used,
would I expect to have a SIGSEV (or similar) or just bogus results?