Raymond Knopp
a7bc282302
Testing on Neoverse N1 (Ampere 3GHz). Tested only on a subset of phy-simulators. - Changes: - use SIMDE consistently - adaptations of LDPC decoder generator for ARMv8 performance - SIMDe modifications of Intel CRC to allow for aarch64 build. optimizations for 128-bit to improve performance of LDPC encode/decode on aarch64 (Neoverse 1) - added BG2 files for 128-bit ldpc encoder (aarch64) - testing on Xeon - testing on x86 - minor changes to build/run on x86 - change in crc.h after returning to aarch64 - removed some warning in ldpc decoder generator for x86_64 - char - Delete irrelevant constants - Correctly declare variables - Define stdbool for all architectures - Remove definition of _MM_SHUFFLE and use SIMDE_MM_SHUFFLE - Remove commented code - Fix CMakeLists.txt - Include SIMDE avx2 functions in tools_defs.h
60 lines
2.8 KiB
C
60 lines
2.8 KiB
C
/*
|
|
* Licensed to the OpenAirInterface (OAI) Software Alliance under one or more
|
|
* contributor license agreements. See the NOTICE file distributed with
|
|
* this work for additional information regarding copyright ownership.
|
|
* The OpenAirInterface Software Alliance licenses this file to You under
|
|
* the OAI Public License, Version 1.1 (the "License"); you may not use this file
|
|
* except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.openairinterface.org/?page_id=698
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*-------------------------------------------------------------------------------
|
|
* For more information about the OpenAirInterface (OAI) Software Alliance:
|
|
* contact@openairinterface.org
|
|
*/
|
|
|
|
#include <simde/x86/avx2.h>
|
|
|
|
void simde_mm128_separate_real_imag_parts(simde__m128i *out_re, simde__m128i *out_im, simde__m128i in0, simde__m128i in1)
|
|
{
|
|
// Put in0 = [Re(0,1) Re(2,3) Im(0,1) Im(2,3)]
|
|
in0 = simde_mm_shufflelo_epi16(in0, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in0 = simde_mm_shufflehi_epi16(in0, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in0 = simde_mm_shuffle_epi32(in0, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
|
|
// Put xmm1 = [Re(4,5) Re(6,7) Im(4,5) Im(6,7)]
|
|
in1 = simde_mm_shufflelo_epi16(in1, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in1 = simde_mm_shufflehi_epi16(in1, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in1 = simde_mm_shuffle_epi32(in1, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
|
|
*out_re = simde_mm_unpacklo_epi64(in0, in1);
|
|
*out_im = simde_mm_unpackhi_epi64(in0, in1);
|
|
}
|
|
|
|
void simde_mm256_separate_real_imag_parts(simde__m256i *out_re, simde__m256i *out_im, simde__m256i in0, simde__m256i in1)
|
|
{
|
|
// Put in0 = [Re(0,1,2,3) Im(0,1,2,3) Re(4,5,6,7) Im(4,5,6,7)]
|
|
in0 = simde_mm256_shufflelo_epi16(in0, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in0 = simde_mm256_shufflehi_epi16(in0, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in0 = simde_mm256_shuffle_epi32(in0, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
|
|
// Put in1 = [Re(8,9,10,11) Im(8,9,10,11) Re(12,13,14,15) Im(12,13,14,15)]
|
|
in1 = simde_mm256_shufflelo_epi16(in1, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in1 = simde_mm256_shufflehi_epi16(in1, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
in1 = simde_mm256_shuffle_epi32(in1, 0xd8); //_MM_SHUFFLE(0,2,1,3));
|
|
|
|
// Put tmp0 =[Re(0,1,2,3) Re(8,9,10,11) Re(4,5,6,7) Re(12,13,14,15)]
|
|
simde__m256i tmp0 = simde_mm256_unpacklo_epi64(in0, in1);
|
|
|
|
// Put tmp1 = [Im(0,1,2,3) Im(8,9,10,11) Im(4,5,6,7) Im(12,13,14,15)]
|
|
simde__m256i tmp1 = simde_mm256_unpackhi_epi64(in0, in1);
|
|
|
|
*out_re = simde_mm256_permute4x64_epi64(tmp0, 0xd8);
|
|
*out_im = simde_mm256_permute4x64_epi64(tmp1, 0xd8);
|
|
} |