derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
41 lines
1.2 KiB
Common Lisp
41 lines
1.2 KiB
Common Lisp
/*===--------------------------------------------------------------------------
|
|
* ROCm Device Libraries
|
|
*
|
|
* This file is distributed under the University of Illinois Open Source
|
|
* License. See LICENSE.TXT for details.
|
|
*===------------------------------------------------------------------------*/
|
|
|
|
#include "mathF.h"
|
|
#include "trigredF.h"
|
|
|
|
CONSTATTR float
|
|
MATH_PRIVATE(tanred)(float x, int i)
|
|
{
|
|
float s = x * x;
|
|
|
|
#if defined MORE_ACCURACY
|
|
float p = s * MATH_MAD(s, MATH_MAD(s, MATH_MAD(s, MATH_MAD(s,
|
|
MATH_MAD(s,
|
|
0x1.33d5e6p-7f, 0x1.9697f8p-9f), 0x1.907be2p-6f), 0x1.b581ap-5f),
|
|
0x1.112e2p-3f), 0x1.5554dcp-2f);
|
|
#else
|
|
float a = MATH_MAD(s, -0x1.19dba6p-6f, 0x1.8a8b0ep-2f);
|
|
float b = MATH_MAD(s, MATH_MAD(s, 0x1.2e2900p-6f, -0x1.07266ep-1f), 0x1.27e84ap+0f);
|
|
float p = s * MATH_FAST_DIV(a,b);
|
|
#endif
|
|
|
|
#if defined LESS_ACCURACY
|
|
float t = MATH_MAD(p, x, x);
|
|
float tr = -MATH_FAST_RCP(t);
|
|
#else
|
|
float t = BUILTIN_FMA_F32(p, x, x);
|
|
float tt = BUILTIN_FMA_F32(p, x, -(t - x));
|
|
float tr = -MATH_FAST_RCP(t);
|
|
float e = BUILTIN_FMA_F32(tt, tr, BUILTIN_FMA_F32(t, tr, 1.0f));
|
|
tr = BUILTIN_FMA_F32(e, tr, tr);
|
|
#endif
|
|
|
|
return i ? tr : t;
|
|
}
|
|
|