dump1090-fa/cpu_features/scripts/test_integration.sh

107 lines
2.2 KiB
Bash
Raw Permalink 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
#!/usr/bin/env bash
source "$(dirname -- "$0")"/run_integration.sh
# Toolchains for little-endian, 64-bit ARMv8 for GNU/Linux systems
function set_aarch64-linux-gnu() {
TOOLCHAIN=LINARO
TARGET=aarch64-linux-gnu
QEMU_ARCH=aarch64
}
# Toolchains for little-endian, hard-float, 32-bit ARMv7 (and earlier) for GNU/Linux systems
function set_arm-linux-gnueabihf() {
TOOLCHAIN=LINARO
TARGET=arm-linux-gnueabihf
QEMU_ARCH=arm
}
# Toolchains for little-endian, 32-bit ARMv8 for GNU/Linux systems
function set_armv8l-linux-gnueabihf() {
TOOLCHAIN=LINARO
TARGET=armv8l-linux-gnueabihf
QEMU_ARCH=arm
}
# Toolchains for little-endian, soft-float, 32-bit ARMv7 (and earlier) for GNU/Linux systems
function set_arm-linux-gnueabi() {
TOOLCHAIN=LINARO
TARGET=arm-linux-gnueabi
QEMU_ARCH=arm
}
# Toolchains for big-endian, 64-bit ARMv8 for GNU/Linux systems
function set_aarch64_be-linux-gnu() {
TOOLCHAIN=LINARO
TARGET=aarch64_be-linux-gnu
QEMU_ARCH=DISABLED
}
# Toolchains for big-endian, hard-float, 32-bit ARMv7 (and earlier) for GNU/Linux systems
function set_armeb-linux-gnueabihf() {
TOOLCHAIN=LINARO
TARGET=armeb-linux-gnueabihf
QEMU_ARCH=DISABLED
}
# Toolchains for big-endian, soft-float, 32-bit ARMv7 (and earlier) for GNU/Linux systems
function set_armeb-linux-gnueabi() {
TOOLCHAIN=LINARO
TARGET=armeb-linux-gnueabi
QEMU_ARCH=DISABLED
}
function set_mips32() {
TOOLCHAIN=CODESCAPE
TARGET=mips32
QEMU_ARCH=mips
}
function set_mips32el() {
TOOLCHAIN=CODESCAPE
TARGET=mips32el
QEMU_ARCH=mipsel
}
function set_mips64() {
TOOLCHAIN=CODESCAPE
TARGET=mips64
QEMU_ARCH=mips64
}
function set_mips64el() {
TOOLCHAIN=CODESCAPE
TARGET=mips64el
QEMU_ARCH=mips64el
}
function set_native() {
TOOLCHAIN=NATIVE
TARGET=native
QEMU_ARCH=""
}
ENVIRONMENTS="
set_aarch64-linux-gnu
set_arm-linux-gnueabihf
set_armv8l-linux-gnueabihf
set_arm-linux-gnueabi
set_aarch64_be-linux-gnu
set_armeb-linux-gnueabihf
set_armeb-linux-gnueabi
set_mips32
set_mips32el
set_mips64
set_mips64el
set_native
"
set -e
CMAKE_GENERATOR="Ninja"
for SET_ENVIRONMENT in ${ENVIRONMENTS}; do
${SET_ENVIRONMENT}
expand_environment_and_integrate
done