search for: __cos

...backend should codegen math with respect to accuracy settings, specified either as backend options, or as functions attributes (quiet recent addition of LLVM). Accuracy settings should be: 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) 2) Use or not GPU-specific low-precision functions (__sin, __cos, etc.) Following latter approach, math handling of NVPTX will conform the rest of LLVM, and no host-dependant tweaks will be needed. I'm also interested to contribute into this developments at reasonable depth. Moving this part only on our own would slow down the progess with main targets too...

...ath > with respect to accuracy settings, specified either as backend options, or > as functions attributes (quiet recent addition of LLVM). Accuracy settings > should be: > 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) > 2) Use or not GPU-specific low-precision functions (__sin, __cos, etc.) > > Following latter approach, math handling of NVPTX will conform the rest of > LLVM, and no host-dependant tweaks will be needed. > > I'm also interested to contribute into this developments at reasonable > depth. Moving this part only on our own would slow down the p...

...spect to accuracy settings, specified either as backend options, or >> as functions attributes (quiet recent addition of LLVM). Accuracy settings >> should be: >> 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) >> 2) Use or not GPU-specific low-precision functions (__sin, __cos, etc.) >> >> Following latter approach, math handling of NVPTX will conform the rest >> of LLVM, and no host-dependant tweaks will be needed. >> >> I'm also interested to contribute into this developments at reasonable >> depth. Moving this part only on our o...

...y settings, specified either as backend options, or >>> as functions attributes (quiet recent addition of LLVM). Accuracy settings >>> should be: >>> 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) >>> 2) Use or not GPU-specific low-precision functions (__sin, __cos, etc.) >>> >>> Following latter approach, math handling of NVPTX will conform the rest >>> of LLVM, and no host-dependant tweaks will be needed. >>> >>> I'm also interested to contribute into this developments at reasonable >>> depth. Moving...

...ified either as backend options, or >>>> as functions attributes (quiet recent addition of LLVM). Accuracy settings >>>> should be: >>>> 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) >>>> 2) Use or not GPU-specific low-precision functions (__sin, __cos, etc.) >>>> >>>> Following latter approach, math handling of NVPTX will conform the rest >>>> of LLVM, and no host-dependant tweaks will be needed. >>>> >>>> I'm also interested to contribute into this developments at reasonable >&g...

...backend >>>>> options, or as functions attributes (quiet recent addition of LLVM). >>>>> Accuracy settings should be: >>>>> 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) >>>>> 2) Use or not GPU-specific low-precision functions (__sin, __cos, etc.) >>>>> >>>>> Following latter approach, math handling of NVPTX will conform the >>>>> rest of LLVM, and no host-dependant tweaks will be needed. >>>>> >>>>> I'm also interested to contribute into this developments...

...>>>> options, or as functions attributes (quiet recent addition of LLVM). >>>>>> Accuracy settings should be: >>>>>> 1) fast-math (ftz, prec-div, prec-sqrt, fma, etc.) >>>>>> 2) Use or not GPU-specific low-precision functions (__sin, __cos, >>>>>> etc.) >>>>>> >>>>>> Following latter approach, math handling of NVPTX will conform the >>>>>> rest of LLVM, and no host-dependant tweaks will be needed. >>>>>> >>>>>> I'm also int...

Yes, it helps a lot and we are working on it. A few questions, 1) What will be your use model of this library? Will you run optimization phases after linking with the library? If so, what are they? 2) Do you care if the names of functions differ from those in libm? For example, it would be gpusin() instead of sin(). 3) Do you need a different library for different host

Hi Justin, gentlemen, I'm afraid I have to escalate this issue at this point. Since it was discussed for the first time last summer, it was sufficient for us for a while to have lowering of math calls into intrinsics disabled at DragonEgg level, and link them against CUDA math functions at LLVM IR level. Now I can say: this is not sufficient any longer, and we need NVPTX backend to deal with

...dlPvRKSt9nothrow_t 1 generic_start_main __pow_finite 1 generic_start_main __log_finite 1 generic_start_main __exp_finite 1 generic_start_main __atan2_finite 1 generic_start_main __asin_finite 1 generic_start_main __acos_finite 1 generic_start_main tan 1 generic_start_main __sin 1 generic_start_main __cos 1 generic_start_main __floor 1 generic_start_main __ceil 1 generic_start_main atan 1 __libc_csu_init _GLOBAL__sub_I_Verifier.cpp 1 _ZN4llvm12PassRegistryD2Ev _ZN4llvm3sys11RWMutexImplD2Ev 1 _ZN4llvm14object_creatorINS_12PassRegistryEE4callEv _ZN4llvm3sys11RWMutexImplC2Ev 1 _ZN4llvm13llvm_shutdownEv...

A rebased version of the lld patch is attached. Cheers, Rafael On 31 July 2017 at 15:11, Rafael Avila de Espindola <rafael.espindola at gmail.com> wrote: > Tobias Edler von Koch <tobias at codeaurora.org> writes: > >> Hi Rafael, >> >> On 07/31/2017 04:20 PM, Rafael Avila de Espindola via llvm-dev wrote: >>> However, do we need to start with