dump1090-fa/cpu_features/include/cpuinfo_aarch64.h

157 lines
5.3 KiB
C
Raw Normal View History

Move all converters to starch-based implementations (#97) * Switch all conversion routines to use starch. main user-visible changes: * ensure you check out submodules ('git clone --recurse-submodules") * --version shows the CPU features and DSP implementations in use * --wisdom allows overriding of the built-in architecture wisdom * --dcfilter no longer supported * "starch-benchmark" binary will benchmark all options on the current machine and can produce a wisdom file to feed to the --wisdom option If you have a usecase for --dcfilter, please get in touch and let me know - it's an edge case and for now there's no starch/DSP support for it, but support can be written if needed. In almost all cases the new conversion routines are slightly or substantially faster than the old conversion routines. The only case that is slower is SC16/SC16Q11 on a Pi 0, which is around 10% slower due to changing from heavily approximated lookup tables to higher quality results (but SC16 is probably already out of reach of a Pi 0) * No need to build with SC16Q11_TABLE_BITS any more * Add oneoff/uc8_capture_stats (reads a UC8 capture; measures min/max/mean I and Q) * Switch UC8 conversion to 127.4 center, 128 range. Looking at actual UC8 captures from a RTL2832, the mean I and Q are actually at 127.4, so use that as the zero point. This means that the resulting I/Q maximum values could be as large as 127.6. Switch to 128 for simplicity. * Switch to the new UC8 zero offset in benchmarks, fix some bugs * Fix some bugs in SC16/SC16Q11 validation, tighten the max error requirements * Ditch UC8 approximation path, add a NEON VRQSQRTE path. * Tweak the SC16 exact path, add a new impl that uses a mix of u32 & floats. * SC16Q11 impl tweaks: * add a u32->float exact path * ditch the approximation path * add a NEON VRSQRTE path * add a 12-bit table path (using the full signed I/Q value, not absolute value) * Ditch SC16 approximation path, add NEON vrsqrte path * Add oneoff/dsp_error_measurement This runs sample input through the DSP functions that are allowed to be inexact and dumps the results as a TSV suitable for feeding to gnuplot to look at the actual errors. * Update make clean, make wisdom targets * Update wisdom based on benchmarking * Preserve the raw wisdom benchmark data * Update to latest starch * Update .gitignore for new wisdom files * Update starch generated code * Build starch-benchmark as part of the 'all' target * Use wisdom from /etc/dump1090-fa/wisdom.local if present * Package starch-benchmark and a helper script to generate local wisdom data * Remove submodules in preparation for importing them directly * Import cpu_features v0.6.0 from https://github.com/google/cpu_features/releases/tag/v0.6.0 * Import starch at commit a725c8491dc33a321565d451b385131e589d8490 from https://github.com/flightaware/starch
2021-01-21 11:45:00 +00:00
// Copyright 2017 Google LLC
//
// Licensed under the Apache License, Version 2.0 (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.apache.org/licenses/LICENSE-2.0
//
// 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.
#ifndef CPU_FEATURES_INCLUDE_CPUINFO_AARCH64_H_
#define CPU_FEATURES_INCLUDE_CPUINFO_AARCH64_H_
#include "cpu_features_cache_info.h"
#include "cpu_features_macros.h"
CPU_FEATURES_START_CPP_NAMESPACE
typedef struct {
int fp : 1; // Floating-point.
int asimd : 1; // Advanced SIMD.
int evtstrm : 1; // Generic timer generated events.
int aes : 1; // Hardware-accelerated Advanced Encryption Standard.
int pmull : 1; // Polynomial multiply long.
int sha1 : 1; // Hardware-accelerated SHA1.
int sha2 : 1; // Hardware-accelerated SHA2-256.
int crc32 : 1; // Hardware-accelerated CRC-32.
int atomics : 1; // Armv8.1 atomic instructions.
int fphp : 1; // Half-precision floating point support.
int asimdhp : 1; // Advanced SIMD half-precision support.
int cpuid : 1; // Access to certain ID registers.
int asimdrdm : 1; // Rounding Double Multiply Accumulate/Subtract.
int jscvt : 1; // Support for JavaScript conversion.
int fcma : 1; // Floating point complex numbers.
int lrcpc : 1; // Support for weaker release consistency.
int dcpop : 1; // Data persistence writeback.
int sha3 : 1; // Hardware-accelerated SHA3.
int sm3 : 1; // Hardware-accelerated SM3.
int sm4 : 1; // Hardware-accelerated SM4.
int asimddp : 1; // Dot product instruction.
int sha512 : 1; // Hardware-accelerated SHA512.
int sve : 1; // Scalable Vector Extension.
int asimdfhm : 1; // Additional half-precision instructions.
int dit : 1; // Data independent timing.
int uscat : 1; // Unaligned atomics support.
int ilrcpc : 1; // Additional support for weaker release consistency.
int flagm : 1; // Flag manipulation instructions.
int ssbs : 1; // Speculative Store Bypass Safe PSTATE bit.
int sb : 1; // Speculation barrier.
int paca : 1; // Address authentication.
int pacg : 1; // Generic authentication.
int dcpodp : 1; // Data cache clean to point of persistence.
int sve2 : 1; // Scalable Vector Extension (version 2).
int sveaes : 1; // SVE AES instructions.
int svepmull : 1; // SVE polynomial multiply long instructions.
int svebitperm : 1; // SVE bit permute instructions.
int svesha3 : 1; // SVE SHA3 instructions.
int svesm4 : 1; // SVE SM4 instructions.
int flagm2 : 1; // Additional flag manipulation instructions.
int frint : 1; // Floating point to integer rounding.
int svei8mm : 1; // SVE Int8 matrix multiplication instructions.
int svef32mm : 1; // SVE FP32 matrix multiplication instruction.
int svef64mm : 1; // SVE FP64 matrix multiplication instructions.
int svebf16 : 1; // SVE BFloat16 instructions.
int i8mm : 1; // Int8 matrix multiplication instructions.
int bf16 : 1; // BFloat16 instructions.
int dgh : 1; // Data Gathering Hint instruction.
int rng : 1; // True random number generator support.
int bti : 1; // Branch target identification.
// Make sure to update Aarch64FeaturesEnum below if you add a field here.
} Aarch64Features;
typedef struct {
Aarch64Features features;
int implementer;
int variant;
int part;
int revision;
} Aarch64Info;
Aarch64Info GetAarch64Info(void);
////////////////////////////////////////////////////////////////////////////////
// Introspection functions
typedef enum {
AARCH64_FP,
AARCH64_ASIMD,
AARCH64_EVTSTRM,
AARCH64_AES,
AARCH64_PMULL,
AARCH64_SHA1,
AARCH64_SHA2,
AARCH64_CRC32,
AARCH64_ATOMICS,
AARCH64_FPHP,
AARCH64_ASIMDHP,
AARCH64_CPUID,
AARCH64_ASIMDRDM,
AARCH64_JSCVT,
AARCH64_FCMA,
AARCH64_LRCPC,
AARCH64_DCPOP,
AARCH64_SHA3,
AARCH64_SM3,
AARCH64_SM4,
AARCH64_ASIMDDP,
AARCH64_SHA512,
AARCH64_SVE,
AARCH64_ASIMDFHM,
AARCH64_DIT,
AARCH64_USCAT,
AARCH64_ILRCPC,
AARCH64_FLAGM,
AARCH64_SSBS,
AARCH64_SB,
AARCH64_PACA,
AARCH64_PACG,
AARCH64_DCPODP,
AARCH64_SVE2,
AARCH64_SVEAES,
AARCH64_SVEPMULL,
AARCH64_SVEBITPERM,
AARCH64_SVESHA3,
AARCH64_SVESM4,
AARCH64_FLAGM2,
AARCH64_FRINT,
AARCH64_SVEI8MM,
AARCH64_SVEF32MM,
AARCH64_SVEF64MM,
AARCH64_SVEBF16,
AARCH64_I8MM,
AARCH64_BF16,
AARCH64_DGH,
AARCH64_RNG,
AARCH64_BTI,
AARCH64_LAST_,
} Aarch64FeaturesEnum;
int GetAarch64FeaturesEnumValue(const Aarch64Features* features,
Aarch64FeaturesEnum value);
const char* GetAarch64FeaturesEnumName(Aarch64FeaturesEnum);
CPU_FEATURES_END_CPP_NAMESPACE
#if !defined(CPU_FEATURES_ARCH_AARCH64)
#error "Including cpuinfo_aarch64.h from a non-aarch64 target."
#endif
#endif // CPU_FEATURES_INCLUDE_CPUINFO_AARCH64_H_