아부지 카메라 니콘 p900s 배터리랑 충전기 4달라! 외치셔서 대리 지름
아니.. 링크까지 찾을줄 아시면 이제 구매만 누르면 되는데!!!!!!!!
'개소리 왈왈 > 직딩의 비애' 카테고리의 다른 글
| 블루투스 사운드 바 LP-S09 분해 (0) | 2021.07.20 |
|---|---|
| 당근 무료나눔 받아옴 (2) | 2021.07.20 |
| 지를까 말까 고민 중 (0) | 2021.06.07 |
| 월 초 = 지름 (2) | 2021.06.01 |
| 월 말 (2) | 2021.05.31 |
'잡동사니'에 해당되는 글 13786건
- 2021.07.01 7월 시작과 지름
- 2021.07.01 tensorflow cross compile
- 2021.06.30 aarch, armv8 asimd build (neon)
- 2021.06.30 rpi 4b 32bit vs 64bit?
- 2021.06.30 tensorflow lite on rpi4 64bit
- 2021.06.30 tensorflow delegate
- 2021.06.30 rpi 4 32bit / 64bit cpuinfo
- 2021.06.30 AArch64 linux cpu features
- 2021.06.30 gcc vectorized loop
- 2021.06.29 AVR FFB(force feedback)
개소리 왈왈/직딩의 비애2021. 7. 1. 13:55
프로그램 사용/yolo_tensorflow2021. 7. 1. 11:32
아따 빡세다 -_-
컴파일 하는데 libz.so.1이 없다고 하는데
아마도.. 64bit ubuntu라 32bit 용 libz가 없다고 배쨰는 듯
| /home/minimonk/work/tools/arm-bcm2708/gcc-linaro-arm-linux-gnueabihf-raspbian/bin/../libexec/gcc/arm-linux-gnueabihf/4.8.3/cc1plus: error while loading shared libraries: libz.so.1: cannot open shared object file: No such file or directory $sudo apt-get install lib32z1 |
[링크 : https://damedame.tistory.com/entry/libzso1-파일을-찾을수-없을때]
std::is_trivially_copyable은 c++11 표준이라 gcc 5.x 이상부터 지원하기 때문이라고
| In file included from /home/minimonk/work/tensorflow/tensorflow/lite/tools/make/downloads/ruy/ruy/frontend.h:30:0, from /home/minimonk/work/tensorflow/tensorflow/lite/tools/make/downloads/ruy/ruy/ruy.h:23, from ./tensorflow/lite/kernels/cpu_backend_gemm_ruy.h:21, from ./tensorflow/lite/kernels/cpu_backend_gemm.h:25, from ./tensorflow/lite/kernels/internal/optimized/optimized_ops.h:45, from tensorflow/lite/kernels/audio_spectrogram.cc:24: /home/minimonk/work/tensorflow/tensorflow/lite/tools/make/downloads/ruy/ruy/create_trmul_params.h: In function ‘void ruy::detail::FinalizeMulParams(const ruy::MulParams<AccumScalar, DstScalar>&, ruy::ChannelDimension, ruy::Ctx*, ruy::TrMulParams*)’: /home/minimonk/work/tensorflow/tensorflow/lite/tools/make/downloads/ruy/ruy/create_trmul_params.h:388:17: error: ‘is_trivially_copyable’ is not a member of ‘std’ static_assert(std::is_trivially_copyable<MulParamsType>::value, ""); ^ /home/minimonk/work/tensorflow/tensorflow/lite/tools/make/downloads/ruy/ruy/create_trmul_params.h:388:57: error: expected primary-expression before ‘>’ token static_assert(std::is_trivially_copyable<MulParamsType>::value, ""); ^ /home/minimonk/work/tensorflow/tensorflow/lite/tools/make/downloads/ruy/ruy/create_trmul_params.h:388:58: error: ‘::value’ has not been declared static_assert(std::is_trivially_copyable<MulParamsType>::value, ""); ^ |
[링크 : https://stackoverflow.com/questions/25123458/is-trivially-copyable-is-not-a-member-of-std]
예라이... -_-
| $ arm-linux-gnueabihf-g++ --version arm-linux-gnueabihf-g++ (crosstool-NG linaro-1.13.1-4.8-2014.01 - Linaro GCC 2013.11) 4.8.3 20140106 (prerelease) Copyright (C) 2013 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. |
| $ sudo apt-get install gcc-arm-linux-gnueabihf g++-arm-linux-gnueabihf |
'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글
| tflite gpu openCL support build fail (0) | 2021.08.31 |
|---|---|
| tf lite cmake (0) | 2021.08.27 |
| tensorflow lite on rpi4 64bit (0) | 2021.06.30 |
| tensorflow delegate (0) | 2021.06.30 |
| tflite typed_tensor(), tensor() (0) | 2021.06.25 |
embeded/raspberry pi2021. 6. 30. 18:25
| 5.7.2 Advanced SIMD Mnemonics Although derived from the AArch32 Advanced SIMD syntax, a number of changes have been made to harmonise with the AArch64 core integer and floating point instruction set syntax, and to unify AArch32’s divergent “architectural” and “programmers’” notations: • The ‘V’ mnemonic prefix has been removed, and S/U/F/P added to indicate signed/unsigned/floatingpoint/polynomial data type. The mnemonic always indicates the data type(s) of the operation. • The vector organisation (element size and number of lanes) is described by the register qualifiers and never by a mnemonic qualifier. See the description of the vector register syntax in §4.4.2 above. • The ‘P’ prefix for “pairwise” operations becomes a suffix. • A ‘V’ suffix has been added for the new reduction (across-all-lanes) operations • A ‘2’ suffix has been added for the new widening/narrowing “second part” instructions, described below. • Vector compares now use the integer condition code names to indicate whether an integer comparison is signed or unsigned (e.g. CMLT, CMLO, CMGE, CMHI, etc) • Some mnemonics have been renamed where the removal of the V prefix caused clash with the core instruction set mnemonics. ADD Vd.<T>, Vn.<T>, Vm.<T> Integer add (vector). Where <T> is 8B, 16B, 4H, 8H, 2S, 4S or 2D |
| $ gcc neon.c -fopt-info-vec -O3 neon.c:10:9: note: loop vectorized |
vadd 이런게 안보이네?
| $ objdump -d a.out a.out: file format elf64-littleaarch64 Disassembly of section .init: 00000000000005d0 <_init>: 5d0: a9bf7bfd stp x29, x30, [sp, #-16]! 5d4: 910003fd mov x29, sp 5d8: 94000043 bl 6e4 <call_weak_fn> 5dc: a8c17bfd ldp x29, x30, [sp], #16 5e0: d65f03c0 ret Disassembly of section .plt: 00000000000005f0 <.plt>: 5f0: a9bf7bf0 stp x16, x30, [sp, #-16]! 5f4: 90000090 adrp x16, 10000 <__FRAME_END__+0xf680> 5f8: f947fe11 ldr x17, [x16, #4088] 5fc: 913fe210 add x16, x16, #0xff8 600: d61f0220 br x17 604: d503201f nop 608: d503201f nop 60c: d503201f nop 0000000000000610 <__cxa_finalize@plt>: 610: b0000090 adrp x16, 11000 <__cxa_finalize@GLIBC_2.17> 614: f9400211 ldr x17, [x16] 618: 91000210 add x16, x16, #0x0 61c: d61f0220 br x17 0000000000000620 <__libc_start_main@plt>: 620: b0000090 adrp x16, 11000 <__cxa_finalize@GLIBC_2.17> 624: f9400611 ldr x17, [x16, #8] 628: 91002210 add x16, x16, #0x8 62c: d61f0220 br x17 0000000000000630 <__gmon_start__@plt>: 630: b0000090 adrp x16, 11000 <__cxa_finalize@GLIBC_2.17> 634: f9400a11 ldr x17, [x16, #16] 638: 91004210 add x16, x16, #0x10 63c: d61f0220 br x17 0000000000000640 <abort@plt>: 640: b0000090 adrp x16, 11000 <__cxa_finalize@GLIBC_2.17> 644: f9400e11 ldr x17, [x16, #24] 648: 91006210 add x16, x16, #0x18 64c: d61f0220 br x17 0000000000000650 <printf@plt>: 650: b0000090 adrp x16, 11000 <__cxa_finalize@GLIBC_2.17> 654: f9401211 ldr x17, [x16, #32] 658: 91008210 add x16, x16, #0x20 65c: d61f0220 br x17 Disassembly of section .text: 0000000000000660 <main>: 660: d13003ff sub sp, sp, #0xc00 664: 912003e0 add x0, sp, #0x800 668: 911003e2 add x2, sp, #0x400 66c: 910003e1 mov x1, sp 670: 913003e3 add x3, sp, #0xc00 674: d503201f nop 678: 3cc10401 ldr q1, [x0], #16 67c: 3cc10440 ldr q0, [x2], #16 680: eb03001f cmp x0, x3 684: 4ea18400 add v0.4s, v0.4s, v1.4s 688: 3c810420 str q0, [x1], #16 68c: 54ffff61 b.ne 678 <main+0x18> // b.any 690: b94003e1 ldr w1, [sp] 694: 90000000 adrp x0, 0 <_init-0x5d0> 698: b94403e2 ldr w2, [sp, #1024] 69c: 91214000 add x0, x0, #0x850 6a0: b94803e3 ldr w3, [sp, #2048] 6a4: 913003ff add sp, sp, #0xc00 6a8: 17ffffea b 650 <printf@plt> 00000000000006ac <_start>: 6ac: d280001d mov x29, #0x0 // #0 6b0: d280001e mov x30, #0x0 // #0 6b4: aa0003e5 mov x5, x0 6b8: f94003e1 ldr x1, [sp] 6bc: 910023e2 add x2, sp, #0x8 6c0: 910003e6 mov x6, sp 6c4: 90000080 adrp x0, 10000 <__FRAME_END__+0xf680> 6c8: f947ec00 ldr x0, [x0, #4056] 6cc: 90000083 adrp x3, 10000 <__FRAME_END__+0xf680> 6d0: f947e863 ldr x3, [x3, #4048] 6d4: 90000084 adrp x4, 10000 <__FRAME_END__+0xf680> 6d8: f947d884 ldr x4, [x4, #4016] 6dc: 97ffffd1 bl 620 <__libc_start_main@plt> 6e0: 97ffffd8 bl 640 <abort@plt> 00000000000006e4 <call_weak_fn>: 6e4: 90000080 adrp x0, 10000 <__FRAME_END__+0xf680> 6e8: f947e400 ldr x0, [x0, #4040] 6ec: b4000040 cbz x0, 6f4 <call_weak_fn+0x10> 6f0: 17ffffd0 b 630 <__gmon_start__@plt> 6f4: d65f03c0 ret 00000000000006f8 <deregister_tm_clones>: 6f8: b0000080 adrp x0, 11000 <__cxa_finalize@GLIBC_2.17> 6fc: 9100e000 add x0, x0, #0x38 700: b0000081 adrp x1, 11000 <__cxa_finalize@GLIBC_2.17> 704: 9100e021 add x1, x1, #0x38 708: eb00003f cmp x1, x0 70c: 540000a0 b.eq 720 <deregister_tm_clones+0x28> // b.none 710: 90000081 adrp x1, 10000 <__FRAME_END__+0xf680> 714: f947dc21 ldr x1, [x1, #4024] 718: b4000041 cbz x1, 720 <deregister_tm_clones+0x28> 71c: d61f0020 br x1 720: d65f03c0 ret 724: d503201f nop 0000000000000728 <register_tm_clones>: 728: b0000080 adrp x0, 11000 <__cxa_finalize@GLIBC_2.17> 72c: 9100e000 add x0, x0, #0x38 730: b0000081 adrp x1, 11000 <__cxa_finalize@GLIBC_2.17> 734: 9100e021 add x1, x1, #0x38 738: cb000021 sub x1, x1, x0 73c: 9343fc21 asr x1, x1, #3 740: 8b41fc21 add x1, x1, x1, lsr #63 744: 9341fc21 asr x1, x1, #1 748: b40000a1 cbz x1, 75c <register_tm_clones+0x34> 74c: 90000082 adrp x2, 10000 <__FRAME_END__+0xf680> 750: f947f042 ldr x2, [x2, #4064] 754: b4000042 cbz x2, 75c <register_tm_clones+0x34> 758: d61f0040 br x2 75c: d65f03c0 ret 0000000000000760 <__do_global_dtors_aux>: 760: a9be7bfd stp x29, x30, [sp, #-32]! 764: 910003fd mov x29, sp 768: f9000bf3 str x19, [sp, #16] 76c: b0000093 adrp x19, 11000 <__cxa_finalize@GLIBC_2.17> 770: 3940e260 ldrb w0, [x19, #56] 774: 35000140 cbnz w0, 79c <__do_global_dtors_aux+0x3c> 778: 90000080 adrp x0, 10000 <__FRAME_END__+0xf680> 77c: f947e000 ldr x0, [x0, #4032] 780: b4000080 cbz x0, 790 <__do_global_dtors_aux+0x30> 784: b0000080 adrp x0, 11000 <__cxa_finalize@GLIBC_2.17> 788: f9401800 ldr x0, [x0, #48] 78c: 97ffffa1 bl 610 <__cxa_finalize@plt> 790: 97ffffda bl 6f8 <deregister_tm_clones> 794: 52800020 mov w0, #0x1 // #1 798: 3900e260 strb w0, [x19, #56] 79c: f9400bf3 ldr x19, [sp, #16] 7a0: a8c27bfd ldp x29, x30, [sp], #32 7a4: d65f03c0 ret 00000000000007a8 <frame_dummy>: 7a8: 17ffffe0 b 728 <register_tm_clones> 7ac: d503201f nop 00000000000007b0 <__libc_csu_init>: 7b0: a9bc7bfd stp x29, x30, [sp, #-64]! 7b4: 910003fd mov x29, sp 7b8: a90153f3 stp x19, x20, [sp, #16] 7bc: 90000094 adrp x20, 10000 <__FRAME_END__+0xf680> 7c0: 91370294 add x20, x20, #0xdc0 7c4: a9025bf5 stp x21, x22, [sp, #32] 7c8: 90000095 adrp x21, 10000 <__FRAME_END__+0xf680> 7cc: 9136e2b5 add x21, x21, #0xdb8 7d0: cb150294 sub x20, x20, x21 7d4: 2a0003f6 mov w22, w0 7d8: a90363f7 stp x23, x24, [sp, #48] 7dc: aa0103f7 mov x23, x1 7e0: aa0203f8 mov x24, x2 7e4: 9343fe94 asr x20, x20, #3 7e8: 97ffff7a bl 5d0 <_init> 7ec: b4000174 cbz x20, 818 <__libc_csu_init+0x68> 7f0: d2800013 mov x19, #0x0 // #0 7f4: d503201f nop 7f8: f8737aa3 ldr x3, [x21, x19, lsl #3] 7fc: aa1803e2 mov x2, x24 800: 91000673 add x19, x19, #0x1 804: aa1703e1 mov x1, x23 808: 2a1603e0 mov w0, w22 80c: d63f0060 blr x3 810: eb13029f cmp x20, x19 814: 54ffff21 b.ne 7f8 <__libc_csu_init+0x48> // b.any 818: a94153f3 ldp x19, x20, [sp, #16] 81c: a9425bf5 ldp x21, x22, [sp, #32] 820: a94363f7 ldp x23, x24, [sp, #48] 824: a8c47bfd ldp x29, x30, [sp], #64 828: d65f03c0 ret 82c: d503201f nop 0000000000000830 <__libc_csu_fini>: 830: d65f03c0 ret Disassembly of section .fini: 0000000000000834 <_fini>: 834: a9bf7bfd stp x29, x30, [sp, #-16]! 838: 910003fd mov x29, sp 83c: a8c17bfd ldp x29, x30, [sp], #16 840: d65f03c0 ret |
'embeded > raspberry pi' 카테고리의 다른 글
| 조향장치 완성 (0) | 2021.07.24 |
|---|---|
| rpi 2b pxe (0) | 2021.07.12 |
| rpi 4b 32bit vs 64bit? (0) | 2021.06.30 |
| rpi 4 32bit / 64bit cpuinfo (0) | 2021.06.30 |
| AArch64 linux cpu features (0) | 2021.06.30 |
embeded/raspberry pi2021. 6. 30. 18:12
라고 적기에는 좀 애매한데
아무튼 NEON 가속을 통해 동일한 프로그램을 돌리는데
32bit 에서는 초당 7.5 프레임
64bit 에서는 초당 11 프레임까지 연산이 가능해지는게 신기해서 찾아보는 중
다른분에게 여쭤보니
메모리 대역폭이 늘어나거나 neon bit width 영향이 아닐까 라고 말씀하셔서 찾아보는데
보기에는 어짜피 float 변수라 single precision으로 차이가 없고
int 형이 연산에 시간을 많이 빼앗길 부분이라 up to 16x8bit operations per instruction 이라
속도에 영향을 주는건 그럼.. 전송 대역폭 혹은 메모리 복사에 다른 속도 차이 정도 이려나?
'embeded > raspberry pi' 카테고리의 다른 글
| rpi 2b pxe (0) | 2021.07.12 |
|---|---|
| aarch, armv8 asimd build (neon) (0) | 2021.06.30 |
| rpi 4 32bit / 64bit cpuinfo (0) | 2021.06.30 |
| AArch64 linux cpu features (0) | 2021.06.30 |
| citcuitpyrhon joystick (0) | 2021.06.28 |
프로그램 사용/yolo_tensorflow2021. 6. 30. 17:10
build_rpi_lib.sh를 통해 빌드 하려는데 에러 뿜뿜 -_-
그래서 makefile을 고쳐야 하나 멘붕이 와서 다시 찾아 보는데
| /bin/bash: arm-linux-gnueabihf-g++: command not found |
| ./tensorflow/lite/tools/make/build_aarch64_lib.sh |
[링크 : https://www.tensorflow.org/lite/guide/build_arm64?hl=ko]
'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글
| tf lite cmake (0) | 2021.08.27 |
|---|---|
| tensorflow cross compile (0) | 2021.07.01 |
| tensorflow delegate (0) | 2021.06.30 |
| tflite typed_tensor(), tensor() (0) | 2021.06.25 |
| tflite yolov4 (0) | 2021.06.14 |
프로그램 사용/yolo_tensorflow2021. 6. 30. 17:08
전에 찾아볼때 대리자 이런게 있길래 그냥 넘겼는데
그래프 실행의 "일부" 또는 "전체"를 다른 실행자에게 넘기는 방법
오.. 그러면 전체 연산중에 일부만을 넘길수 있다면.. delegate를 이용해 분산 처리도 가능할지도?
| TensorFlow Lite 대리자는 그래프 실행의 일부 또는 전체를 다른 executor에 위임하는 방법입니다. |
NPU도 지원이 가능하다는데
|
[링크 : https://www.tensorflow.org/lite/performance/delegates?hl=ko]
cpp 로는 안되나.. android 8.1 이상 기기에서 쓸 수 있다고만 나오네
Android Neural Networks API(NNAPI)는 Android 8.1(API 레벨 27) 이상을 실행하는 모든 Android 기기에서 사용할 수 있습니다. 다음과 같은 하드웨어 가속기를 지원하는 Android 기기의 TensorFlow Lite 모델을 속도를 향상합니다.
|
[링크 : https://www.tensorflow.org/lite/performance/nnapi?hl=ko]
'프로그램 사용 > yolo_tensorflow' 카테고리의 다른 글
| tensorflow cross compile (0) | 2021.07.01 |
|---|---|
| tensorflow lite on rpi4 64bit (0) | 2021.06.30 |
| tflite typed_tensor(), tensor() (0) | 2021.06.25 |
| tflite yolov4 (0) | 2021.06.14 |
| tensorflow lite yolov4 (0) | 2021.06.10 |
embeded/raspberry pi2021. 6. 30. 16:30
32bit kernel info
| $ cat /proc/cpuinfo processor : 3 model name : ARMv7 Processor rev 3 (v7l) BogoMIPS : 108.00 Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm crc32 CPU implementer : 0x41 CPU architecture: 7 CPU variant : 0x0 CPU part : 0xd08 CPU revision : 3 Hardware : BCM2711 Revision : c03112 Serial : 100000003e728750 Model : Raspberry Pi 4 Model B Rev 1.2 $ uname -a Linux raspberrypi 5.10.17-v7l+ #1403 SMP Mon Feb 22 11:33:35 GMT 2021 armv7l GNU/Linux |
64bit kernel info
| $ cat /proc/cpuinfo processor : 3 BogoMIPS : 108.00 Features : fp asimd evtstrm crc32 cpuid CPU implementer : 0x41 CPU architecture: 8 CPU variant : 0x0 CPU part : 0xd08 CPU revision : 3 Hardware : BCM2835 Revision : c03112 Serial : 100000003e728750 Model : Raspberry Pi 4 Model B Rev 1.2 $ uname -a Linux raspberrypi 5.10.17-v8+ #1403 SMP PREEMPT Mon Feb 22 11:37:54 GMT 2021 aarch64 GNU/Linux |
'embeded > raspberry pi' 카테고리의 다른 글
| aarch, armv8 asimd build (neon) (0) | 2021.06.30 |
|---|---|
| rpi 4b 32bit vs 64bit? (0) | 2021.06.30 |
| AArch64 linux cpu features (0) | 2021.06.30 |
| citcuitpyrhon joystick (0) | 2021.06.28 |
| rpi 3b+ with bt / uart (0) | 2021.06.28 |
embeded/raspberry pi2021. 6. 30. 16:23
cpuinfo 플래그가 희한하게 떠서 찾아보니 aarch64 에서는 명칭들이 죄다 바뀐 듯
asimd는 Advanced SIMD 줄여서 표현한건데 기존의 neon을 대체하고
fp는 vfp이런걸 전부 다 대체하는건가?
| Features : fp asimd evtstrm aes pmull sha1 sha2 crc32 cpuid |
[링크 : https://unix.stackexchange.com/questions/43539/what-do-the-flags-in-proc-cpuinfo-mean]
[링크 : https://stackoverflow.com/questions/59379848/]
[링크 : http://javathunderx.blogspot.com/2018/11/cheat-sheet-for-cpuinfo-features-on.html]
'embeded > raspberry pi' 카테고리의 다른 글
| rpi 4b 32bit vs 64bit? (0) | 2021.06.30 |
|---|---|
| rpi 4 32bit / 64bit cpuinfo (0) | 2021.06.30 |
| citcuitpyrhon joystick (0) | 2021.06.28 |
| rpi 3b+ with bt / uart (0) | 2021.06.28 |
| uf2 - USB Flash Format (0) | 2021.06.23 |
프로그램 사용/gcc2021. 6. 30. 11:43
-O3 하면 자동으로 -ftree-vectorize가 추가되었다고.
아무튼 연산만 하고 출력을 안하니 사용하지 않는 코드로 해서 vadd가 안나와서 한참을 헤맸네..
| $ g++ -O3 -mavx autovector.cpp -fopt-info-vec-all autovector.cpp:22:22: missed: couldn't vectorize loop autovector.cpp:25:19: missed: not vectorized: complicated access pattern. autovector.cpp:23:21: missed: couldn't vectorize loop autovector.cpp:25:14: missed: not vectorized: complicated access pattern. autovector.cpp:16:23: optimized: loop vectorized using 32 byte vectors autovector.cpp:10:5: note: vectorized 1 loops in function. autovector.cpp:15:43: missed: statement clobbers memory: now = std::chrono::_V2::system_clock::now (); autovector.cpp:27:77: missed: statement clobbers memory: D.189348 = std::chrono::_V2::system_clock::now (); autovector.cpp:28:2: missed: statement clobbers memory: __assert_fail ("result[2] == ( 2.0f + 0.1335f)+( 1.50f*2.0f + 0.9383f)-(0.33f*2.0f+0.1172f)+3*(float)(noTests-1)", "autovector.cpp", 28, "int main()"); /usr/include/c++/9/ostream:570:18: missed: statement clobbers memory: std::__ostream_insert<char, std::char_traits<char> > (&cout, "CG> message -channel \"exercise results\" Time used: ", 51); /usr/include/c++/9/ostream:221:29: missed: statement clobbers memory: _46 = std::basic_ostream<char>::_M_insert<double> (&cout, _42); /usr/include/c++/9/ostream:570:18: missed: statement clobbers memory: std::__ostream_insert<char, std::char_traits<char> > (_46, "s, N * noTests=", 15); autovector.cpp:29:112: missed: statement clobbers memory: _35 = std::basic_ostream<char>::operator<< (_46, 2000000000); /usr/include/c++/9/ostream:113:13: missed: statement clobbers memory: std::endl<char, std::char_traits<char> > (_35); /usr/include/c++/9/iostream:74:25: missed: statement clobbers memory: std::ios_base::Init::Init (&__ioinit); /usr/include/c++/9/iostream:74:25: missed: statement clobbers memory: __cxa_atexit (__dt_comp , &__ioinit, &__dso_handle); |
| $ gcc -mcpu=native -march=native -Q --help=target The following options are target specific: -mabi= aapcs-linux -mabort-on-noreturn [disabled] -mandroid [disabled] -mapcs [disabled] -mapcs-frame [disabled] -mapcs-reentrant [disabled] -mapcs-stack-check [disabled] -march= armv7ve+vfpv3-d16 -marm [enabled] -masm-syntax-unified [disabled] -mbe32 [enabled] -mbe8 [disabled] -mbig-endian [disabled] -mbionic [disabled] -mbranch-cost= -1 -mcallee-super-interworking [disabled] -mcaller-super-interworking [disabled] -mcmse [disabled] -mcpu= cortex-a7 -mfix-cortex-m3-ldrd [disabled] -mflip-thumb [disabled] -mfloat-abi= hard -mfp16-format= none -mfpu= vfp -mglibc [enabled] -mhard-float -mlittle-endian [enabled] -mlong-calls [disabled] -mmusl [disabled] -mneon-for-64bits [disabled] -mpic-data-is-text-relative [enabled] -mpic-register= -mpoke-function-name [disabled] -mprint-tune-info [disabled] -mpure-code [disabled] -mrestrict-it [disabled] -msched-prolog [enabled] -msingle-pic-base [disabled] -mslow-flash-data [disabled] -msoft-float -mstructure-size-boundary= 8 -mthumb [disabled] -mthumb-interwork [disabled] -mtls-dialect= gnu -mtp= cp15 -mtpcs-frame [disabled] -mtpcs-leaf-frame [disabled] -mtune= -muclibc [disabled] -munaligned-access [enabled] -mvectorize-with-neon-double [disabled] -mvectorize-with-neon-quad [enabled] -mword-relocations [disabled] Known ARM ABIs (for use with the -mabi= option): aapcs aapcs-linux apcs-gnu atpcs iwmmxt Known __fp16 formats (for use with the -mfp16-format= option): alternative ieee none Known ARM FPUs (for use with the -mfpu= option): auto crypto-neon-fp-armv8 fp-armv8 fpv4-sp-d16 fpv5-d16 fpv5-sp-d16 neon neon-fp-armv8 neon-fp16 neon-vfpv3 neon-vfpv4 vfp vfp3 vfpv2 vfpv3 vfpv3-d16 vfpv3-d16-fp16 vfpv3-fp16 vfpv3xd vfpv3xd-fp16 vfpv4 vfpv4-d16 Valid arguments to -mtp=: auto cp15 soft Known floating-point ABIs (for use with the -mfloat-abi= option): hard soft softfp TLS dialect to use: gnu gnu2 |
[링크 : https://www.raspberrypi.org/forums/viewtopic.php?t=155461]
[링크 : https://www.codingame.com/playgrounds/283/sse-avx-vectorization/autovectorization]
+
| $ cat neon.c #include <stdio.h> void main() { int a[256]; int b[256]; int c[256]; int i; for(i = 0; i < 256; i++) { a[i] = b[i] + c[i]; } printf("%d %d %d\n", a[0], b[0], c[0]); } |
| $ gcc -O3 neon.c -mfpu=neon $ objdump -d a.out | grep v 10320: e1a01000 mov r1, r0 10328: e1a0300d mov r3, sp 1032c: f4610add vld1.64 {d16-d17}, [r1 :64]! 10330: f4622add vld1.64 {d18-d19}, [r2 :64]! 10334: f26008e2 vadd.i32 q8, q8, q9 10338: f4430add vst1.64 {d16-d17}, [r3 :64]! 10360: e3a0b000 mov fp, #0 10364: e3a0e000 mov lr, #0 1036c: e1a0200d mov r2, sp 1043c: e3a03001 mov r3, #1 10454: e1a07000 mov r7, r0 1046c: e1a08001 mov r8, r1 10470: e1a09002 mov r9, r2 10480: e3a04000 mov r4, #0 1048c: e1a02009 mov r2, r9 10490: e1a01008 mov r1, r8 10494: e1a00007 mov r0, r7 |
| $ gcc neon.c -mfpu=neon $ objdump -d a.out | grep v 10318: e3a0b000 mov fp, #0 1031c: e3a0e000 mov lr, #0 10324: e1a0200d mov r2, sp 103f4: e3a03001 mov r3, #1 10418: e3a03000 mov r3, #0 10490: e1a00000 nop ; (mov r0, r0) 104a4: e1a07000 mov r7, r0 104bc: e1a08001 mov r8, r1 104c0: e1a09002 mov r9, r2 104d0: e3a04000 mov r4, #0 104dc: e1a02009 mov r2, r9 104e0: e1a01008 mov r1, r8 104e4: e1a00007 mov r0, r7 |
-fopt-info-vec-all 추가. -all 때문인지 어마어마하게 나오네
-fopt-info-vec 으로만 하니 깔끔하게 vectorized 라고 뜬다.
| $ gcc neon.c -mfpu=neon -fopt-info-vec -O3 neon.c:10:2: note: loop vectorized |
'프로그램 사용 > gcc' 카테고리의 다른 글
| 구조체 타입과 변수명은 구분된다? (0) | 2021.11.18 |
|---|---|
| gcc unsigned to signed upcast 테스트 (0) | 2021.07.08 |
| gcc unsigned to signed cast (0) | 2021.06.22 |
| gcc %p (nil) (0) | 2021.05.07 |
| gcc -D 옵션 인자를 printf로 출력하기 (0) | 2021.04.08 |
모종의 음모/motion simulator2021. 6. 29. 19:02
USB 조이스틱 중 포스피드백 되는 장치를 만들어주는 코드
[링크 : https://github.com/tloimu/adapt-ffb-joy/wiki]
+
2024.10.07
[링크 : https://github.com/YukMingLaw/ArduinoJoystickWithFFBLibrary]
'모종의 음모 > motion simulator' 카테고리의 다른 글
| new-lg4ff 와 oversteer 설치 시도 (0) | 2024.10.12 |
|---|---|
| 플심용 자작 시뮬레이터 (2) | 2024.10.11 |
| ffb (force feedback) linux driver (0) | 2024.10.07 |
| ffb - force feedback (0) | 2023.08.25 |
| usb joystick DIY / Force Feedback (2) | 2018.03.04 |
