[Libclc-dev] [PATCH v2 1/1] math: Don't use llvm instrinsic for native_log

[Jan Vesely via Libclc-dev]

On Sun, 2017-10-08 at 12:48 +0000, Aaron Watry wrote:
> On Fri, Oct 6, 2017, 10:37 AM Jan Vesely via Libclc-dev <
> libclc-dev at lists.llvm.org> wrote:
> 
> > On Wed, 2017-09-27 at 18:34 -0400, Jan Vesely wrote:
> > > AMDGPU targets don't have insturction for it,
> > > so it'll be expanded to C * log2 anyway.
> > > 
> > > v2: use native_log2 instead of the more precise sw implementation
> > > 
> > > Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
> > 
> > ping. this is currently crashing.
> > even after https://reviews.llvm.org/D29942 lands, we'll need this for
> > older llvm versions.
> > 
> 
> Even with this, 'pow' crashes out llvm on me at the moment on my SI card.
> I've got family in town today yet ,but tonight or tomorrow I should have
> time to rebuild my stack and try again.

hi, I'm not sure what 'this' refers to. I assume it's D29942 since
native_log patch is not related to pow. Note that D29942 only addresses
f32 and f16 types, f64 still crashes. You'll need my other ('math:
Don't use llvm intrinsic for pow') patch to fix that.

I assume Matt would prefer to keep the default to use intrinsic, and
the expansion is not quite correct (it does not handle 0 or negative
input, in fact it's better suited for powr).
I'll be posting another version of that patch as well. I just have too
many patches in flight atm.

Jan

> 
> --Aaron
> 
> > 
> > Jan
> > 
> > > ---
> > >  generic/lib/math/native_log.cl  | 5 -----
> > >  generic/lib/math/native_log.inc | 2 +-
> > >  2 files changed, 1 insertion(+), 6 deletions(-)
> > > 
> > > diff --git a/generic/lib/math/native_log.cl b/generic/lib/math/
> > 
> > native_log.cl
> > > index f64f012..f8ba08f 100644
> > > --- a/generic/lib/math/native_log.cl
> > > +++ b/generic/lib/math/native_log.cl
> > > @@ -22,11 +22,6 @@
> > > 
> > >  #include <clc/clc.h>
> > > 
> > > -#define __CLC_FUNCTION __clc_native_log
> > > -#define __CLC_INTRINSIC "llvm.log"
> > > -#undef cl_khr_fp64
> > > -#include <clc/math/unary_intrin.inc>
> > > -
> > >  #define __CLC_BODY <native_log.inc>
> > >  #define __FLOAT_ONLY
> > >  #include <clc/math/gentype.inc>
> > > diff --git a/generic/lib/math/native_log.inc
> > 
> > b/generic/lib/math/native_log.inc
> > > index cb4db3f..d4950c2 100644
> > > --- a/generic/lib/math/native_log.inc
> > > +++ b/generic/lib/math/native_log.inc
> > > @@ -21,5 +21,5 @@
> > >   */
> > > 
> > >  _CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE native_log(__CLC_GENTYPE val) {
> > > -  return __clc_native_log(val);
> > > +  return native_log2(val) * (1.0f / M_LOG2E_F);
> > >  }
> > 
> > _______________________________________________
> > Libclc-dev mailing list
> > Libclc-dev at lists.llvm.org
> > http://lists.llvm.org/cgi-bin/mailman/listinfo/libclc-dev
> > 

-- 
Jan Vesely <jan.vesely at rutgers.edu>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 833 bytes
Desc: This is a digitally signed message part
URL: <http://lists.llvm.org/pipermail/libclc-dev/attachments/20171008/ddf599f1/attachment.sig>