- Tricky ... - 7 Updates
- How to get mantissa of long double? - 7 Updates
- Most efficient prefetching distance - 2 Updates
| RadicalRabbit@theburrow.co.uk: Oct 03 08:25AM On Fri, 1 Oct 2021 13:11:21 -0700 >Yeah, they could. Humm... I am working on another animation using a more >robust coloring algorithm for the field lines. Here is an example: >https://fractalforums.org/gallery/1612-300921002353.png That looks much more sophisticated. |
| "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com>: Oct 03 01:21PM -0700 >> robust coloring algorithm for the field lines. Here is an example: >> https://fractalforums.org/gallery/1612-300921002353.png > That looks much more sophisticated. It does! Thanks. Fwiw, here is another interesting zoom on a spiral formation using the experimental coloring algorihtm: https://fractalforums.org/gallery/1612-031021065422.png Now, when I am finished with my new animation, I am going to cycle the colors using an interpolation across the frames. It should look really strange, and mesmerizing. That's the goal. ;^) |
| "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com>: Oct 03 01:33PM -0700 On 10/1/2021 1:54 PM, Branimir Maksimovic wrote: >>> Learn More >> That's odd. The links I posted work for me. Just checked them. Humm... > Safari, iCloud private relay.... ipv6 Humm... Can you see any of my work on YouTube? Here is my channel: https://www.youtube.com/channel/UC_DhsJu-AbQ6Msnxdf8z6Kg Does that link work for you? |
| Branimir Maksimovic <branimir.maksimovic@icloud.com>: Oct 03 09:06PM > Now, when I am finished with my new animation, I am going to cycle the > colors using an interpolation across the frames. It should look really > strange, and mesmerizing. That's the goal. ;^) What about this (not mine work): https://www.icloud.com/iclouddrive/0sLxM6sxtszTkGEX_3YwH57bA#mandelbrot proggy: format ELF64 executable 3 entry start segment readable executable ;============================================================================== macro IACA_START { ; mov ebx,111 ; db 0x64,0x67,0x90 } macro IACA_END { ; mov ebx,222 ; db 0x64,0x67,0x90 } ;============================================================================== align 16 compute_color: ; in: <ymm0>, <ymm1> normalized x, y coordinates ; out: <ymm0>, <ymm1>, <ymm2> r, g, b color components ;------------------------------------------------------------------------------ vaddps ymm0,ymm0,[.c_xoffset] vxorps ymm2,ymm2,ymm2 ; ymm2 = x vmovaps ymm3,ymm2 ; ymm3 = y vmovaps ymm4,ymm2 ; ymm4 = x^2 vmovaps ymm5,ymm2 ; ymm5 = y^2 vxorps ymm8,ymm8,ymm8 mov eax,256 align 32 .loop: IACA_START ; 12.00 cycles on HSW vmulps ymm3,ymm2,ymm3 ; ymm3 = x*y vsubps ymm2,ymm4,ymm5 ; ymm2 = x^2 - y^2 vaddps ymm3,ymm3,ymm3 ; ymm3 = 2*x*y vaddps ymm2,ymm2,ymm0 ; ymm2 = xn = x^2 - y^2 + a vaddps ymm3,ymm3,ymm1 ; ymm3 = yn = 2*x*y + b vmulps ymm4,ymm2,ymm2 ; ymm4 = xn^2 vmulps ymm5,ymm3,ymm3 ; ymm5 = yn^2 vaddps ymm6,ymm2,ymm3 ; ymm6 = xn^2 + yn^2 = m2 vcmpltps ymm7,ymm6,[.c_4_0] vandnps ymm7,ymm7,[.c_1_0] vaddps ymm8,ymm8,ymm7 sub eax,1 jnz .loop IACA_END vmovaps ymm0,ymm8 vdivps ymm0,ymm0,[.c_255_0] vmulps ymm0,ymm0,ymm0 vmulps ymm0,ymm0,ymm0 vmulps ymm0,ymm0,ymm0 vmovaps ymm1,ymm0 vmovaps ymm2,ymm0 ret align 32 .c_4_0: dd 8 dup 4.0 .c_1_0: dd 8 dup 1.0 .c_255_0: dd 8 dup 255.0 .c_xoffset: dd 8 dup -0.5 ;============================================================================== align 16 thread: ;------------------------------------------------------------------------------ virtual at rsp .startx dd ? .starty dd ? end virtual push rbp rbx mov rbp,rsp sub rsp,32 and rsp,-32 .tile: mov r15d,1 lock xadd [image_tile],r15d cmp r15d,TILE_COUNT jge .finish xor edx,edx mov eax,r15d mov edi,TILE_X_COUNT div edi imul eax,TILE_SIZE imul edx,TILE_SIZE mov [.startx],edx mov [.starty],eax imul eax,IMAGE_SIZE add eax,edx shl eax,2 mov rbx,[image_ptr] add rbx,rax xor r14d,r14d .row: xor r13d,r13d align 16 .pixel: mov edx,[.startx] mov eax,[.starty] add edx,r13d add eax,r14d ;------------------------------------ compute color vmovaps ymm2,[image_size] vmovaps ymm3,ymm2 vrcpps ymm3,ymm3 vcvtsi2ss xmm0,xmm0,edx vcvtsi2ss xmm1,xmm1,eax vbroadcastss ymm0,xmm0 vbroadcastss ymm1,xmm1 vaddps ymm0,ymm0,[.c_01234567f] vaddps ymm1,ymm1,ymm1 vaddps ymm0,ymm0,ymm0 vsubps ymm0,ymm0,ymm2 vsubps ymm1,ymm1,ymm2 vmulps ymm0,ymm0,ymm3 vmulps ymm1,ymm1,ymm3 call compute_color ;------------------------------------ convert color from RGB32F to BGRA8 vxorps ymm3,ymm3,ymm3 vmovaps ymm4,[.c_1_0] vminps ymm0,ymm0,ymm4 vminps ymm1,ymm1,ymm4 vminps ymm2,ymm2,ymm4 vmaxps ymm0,ymm0,ymm3 vmaxps ymm1,ymm1,ymm3 vmaxps ymm2,ymm2,ymm3 vmovaps ymm3,[.c_255_0] vmulps ymm0,ymm0,ymm3 vmulps ymm1,ymm1,ymm3 vmulps ymm2,ymm2,ymm3 vcvttps2dq ymm0,ymm0 vcvttps2dq ymm1,ymm1 vcvttps2dq ymm2,ymm2 vpslld ymm1,ymm1,8 vpslld ymm0,ymm0,16 vpor ymm0,ymm0,[.c_ff000000] vpor ymm1,ymm1,ymm2 vpor ymm0,ymm0,ymm1 vmovdqa [rbx+r13*4],ymm0 ;------------------------------------ add r13d,8 cmp r13d,TILE_SIZE jne .pixel add rbx,IMAGE_SIZE*4 add r14d,1 cmp r14d,TILE_SIZE jne .row jmp .tile .finish: mov rsp,rbp pop rbx rbp ret align 32 .c_01234567f: dd 0.0,1.0,2.0,3.0,4.0,5.0,6.0,7.0 .c_1_0: dd 8 dup 1.0 .c_255_0: dd 8 dup 255.0 .c_ff000000: dd 8 dup 0xff000000 ;============================================================================== align 16 mem_alloc: ; in: <rdi> size in bytes ; out: <rax> pointer to the allocated memory ;------------------------------------------------------------------------------ mov eax,9 ; sys_mmap mov rsi,rdi ; length xor edi,edi ; addr mov edx,0x1+0x2 ; PROT_READ | PROT_WRITE mov r10d,0x02+0x20 ; MAP_PRIVATE | MAP_ANONYMOUS mov r8,-1 ; fd xor r9d,r9d ; offset syscall ret ;============================================================================== align 16 thread_create: ; in: <rbx> mutex address ;------------------------------------------------------------------------------ mov edi,4096 call mem_alloc mov rsi,rax add rsi,4096 mov eax,56 ; sys_clone mov edi,0x100+0x200+0x400+0x800+0x10000 xor edx,edx syscall test eax,eax jnz .ret call thread mov dword [rbx],1 mov eax,202 ; sys_futex mov rdi,rbx ; mutex address mov esi,1 ; FUTEX_WAKE mov edx,1 ; wake 1 thread syscall mov eax,60 ; sys_exit xor edi,edi ; exit code syscall .ret: ret ;============================================================================== align 16 thread_wait: ; in: <rbx> mutex address ;------------------------------------------------------------------------------ mov eax,202 ; sys_futex mov rdi,rbx ; mutex address mov esi,0 ; FUTEX_WAIT mov edx,0 ; mutex 'running' value xor r10d,r10d ; unused but must be zero syscall ret ;============================================================================== align 16 image_save: ;------------------------------------------------------------------------------ push rbx mov eax,85 mov rdi,.tga_name mov esi,110000000b syscall mov rbx,rax mov eax,1 mov rdi,rbx mov rsi,.tga_head mov edx,18 syscall mov eax,1 mov rdi,rbx mov rsi,[image_ptr] mov edx,IMAGE_SIZE*IMAGE_SIZE*4 syscall pop rbx ret .tga_name db 'mandelbrot.tga',0 .tga_head db 0,0,2,9 dup 0 db (IMAGE_SIZE and 0x00ff),(IMAGE_SIZE and 0xff00) shr 8 db (IMAGE_SIZE and 0x00ff),(IMAGE_SIZE and 0xff00) shr 8,32,0 ;============================================================================== align 16 main: ;------------------------------------------------------------------------------ mov rdi,IMAGE_SIZE*IMAGE_SIZE*4 call mem_alloc mov [image_ptr],rax mov rbx,thread0_mutex call thread_create mov rbx,thread1_mutex call thread_create mov rbx,thread2_mutex call thread_create mov rbx,thread3_mutex call thread_create mov rbx,thread0_mutex call thread_wait mov rbx,thread1_mutex call thread_wait mov rbx,thread2_mutex call thread_wait mov rbx,thread3_mutex call thread_wait call image_save ret ;============================================================================== align 16 start: ;------------------------------------------------------------------------------ call main mov eax,60 ; sys_exit xor edi,edi ; exit code syscall ;============================================================================== segment readable writeable align 4 thread0_mutex dd 0 thread1_mutex dd 0 thread2_mutex dd 0 thread3_mutex dd 0 align 8 image_ptr dq 0 align 4 image_tile dd 0 TILE_SIZE = 64 TILE_X_COUNT = IMAGE_SIZE / TILE_SIZE TILE_Y_COUNT = IMAGE_SIZE / TILE_SIZE TILE_COUNT = TILE_X_COUNT * TILE_Y_COUNT IMAGE_SIZE = 1024 align 32 image_size: dd 8 dup 1024.0 ;============================================================================== -- 7-77-777 Evil Sinner! to weak you should be meek, and you should brainfuck stronger https://github.com/rofl0r/chaos-pp |
| Branimir Maksimovic <branimir.maksimovic@icloud.com>: Oct 03 09:07PM > Humm... Can you see any of my work on YouTube? Here is my channel: > https://www.youtube.com/channel/UC_DhsJu-AbQ6Msnxdf8z6Kg > Does that link work for you? Bookmarked, will enjoy, THANKS! -- 7-77-777 Evil Sinner! to weak you should be meek, and you should brainfuck stronger https://github.com/rofl0r/chaos-pp |
| "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com>: Oct 03 02:33PM -0700 On 10/3/2021 2:06 PM, Branimir Maksimovic wrote: > https://www.icloud.com/iclouddrive/0sLxM6sxtszTkGEX_3YwH57bA#mandelbrot > proggy: > format ELF64 executable 3 [...] Definite field lines. Not sure if its using binary decomposition. Actually, check these out. Its from a field line algorithm I created for escape time fractals: https://fractalforums.org/fractal-mathematics-and-new-theories/28/plotting-field-lines-during-iteration/4233 It was mentioned here: https://en.wikibooks.org/wiki/Fractals/Iterations_in_the_complex_plane/MandelbrotSetExteriorComplex_potential Search for my last name in the page: http://www.fractalforums.com/new-theories-and-research/plotting-field-lines-during-iteration/ |
| "Chris M. Thomasson" <chris.m.thomasson.1@gmail.com>: Oct 03 02:51PM -0700 On 10/3/2021 2:07 PM, Branimir Maksimovic wrote: >> https://www.youtube.com/channel/UC_DhsJu-AbQ6Msnxdf8z6Kg >> Does that link work for you? > Bookmarked, will enjoy, THANKS! No problem. Glad you can see them. Also, fwiw, here is my vector field rendered in real time using a GLSL shader: https://www.shadertoy.com/view/MdcyRs You can press and drag a point around in the animation to create an attractor in the field. Also, he is my field using WebGL: http://fractallife247.com/test/webgl/ Does it work for you? Thanks. |
| Branimir Maksimovic <branimir.maksimovic@icloud.com>: Oct 03 12:45AM > It would be safer and more portable to use FType; there's no portable > guarantee that any integer type is large enough to hold the mantissa, > but FType is. How so if FType is just typedef? -- 7-77-777 Evil Sinner! to weak you should be meek, and you should brainfuck stronger https://github.com/rofl0r/chaos-pp |
| Branimir Maksimovic <branimir.maksimovic@icloud.com>: Oct 03 12:47AM > that definition might result in the mantissa of "large" having fewer > significant digits than it has on mine, but that's not particularly > important. Now outputs: bmaxa@Branimirs-Air projects % ./a.out max: 179769313486231570814527423731704356798070567525844996598917476803157260780028538760589558632766878171540458953514382464234321326889464182768467546703537516986049910576551282076245490090389328944075868508455133942304583236903222948165808559332123348274797826204144723168738177180919299881250404026184124858368.000000 large: 120645172288001372126619919515947355653853135095820093742269387851763173210613194516902557021349374744036403756647462602101944733127725809392434319981526284828181273773403605513307431121904981243948320057805774787281290926848565000291282225047507294705767371139696722108291516984908752371556782562287095382016.000000 middling: 2882400001.137778 maxll: 9223372036854775807 largell: 9223372036854775807 middlingll: 2882400001 max: 0x1.fffffffffffffp+1023 large: 0x1.579bde02468acp+1023 middling: 0x1.579bde02468adp+31 maxll: 0x7fffffffffffffff largell: 0x7fffffffffffffff middlingll: 0xabcdef01 -- 7-77-777 Evil Sinner! to weak you should be meek, and you should brainfuck stronger https://github.com/rofl0r/chaos-pp |
| Bonita Montero <Bonita.Montero@gmail.com>: Oct 03 08:09AM +0200 So, this should be the most elegant code: #pragma once #include <limits> #include <cstdint> #include <cassert> struct dbl_parts { static_assert(std::numeric_limits<double>::is_iec559, "must be standard fp"); dbl_parts( double d ); dbl_parts &operator =( double d ); dbl_parts() = default; operator double(); bool getSign(); std::uint16_t getBiasedExponent(); std::int16_t getExponent(); std::uint64_t getMantissa(); void setSign( bool sign ); void setBiasedExponent( uint16_t exp ); void setExponent( int16_t exp ); void setMantissa( uint64_t mantissa ); private: static unsigned const MANTISSA_BITS = 52; using i64 = std::int64_t; using ui64 = std::uint64_t; static ui64 const SIGN_MASK = (ui64)1 << 63, EXP_MASK = (ui64)0x7FF << MANTISSA_BITS, MANTISSA_MASK = ~-((i64)1 << MANTISSA_BITS), MANTISSA_MAX = ((ui64)1 << MANTISSA_BITS) | MANTISSA_MASK; using ui16 = std::uint16_t; using i16 = std::int16_t; static ui16 const BEXP_DENORMAL = 0, BEXP_BASE = 0x3FF, BEXP_MAX = 0x7FF; static i16 const EXP_MIN = 0 - BEXP_BASE, EXP_MAX = BEXP_MAX - BEXP_BASE; union { double value; ui64 binary; }; }; inline dbl_parts::dbl_parts( double d ) : value( d ) { } inline dbl_parts &dbl_parts::operator =( double d ) { value = d; return *this; } inline dbl_parts::operator double() { return value; } inline bool dbl_parts::getSign() { return (i64)binary < 0; } inline std::uint16_t dbl_parts::getBiasedExponent() { return (ui16)(binary >> MANTISSA_BITS) & BEXP_MAX; } inline int16_t dbl_parts::getExponent() { return (i16)(getBiasedExponent() - BEXP_BASE); } inline std::uint64_t dbl_parts::getMantissa() { ui16 bExp = getBiasedExponent(); ui64 hiBit = (ui64)(bExp && bExp != BEXP_MAX) << MANTISSA_BITS; return binary & MANTISSA_MASK | hiBit; } inline void dbl_parts::setSign( bool sign ) { binary = binary & ~SIGN_MASK | (ui64)sign << 63; } inline void dbl_parts::setBiasedExponent( std::uint16_t exp ) { assert(exp <= BEXP_MAX); binary = binary & (SIGN_MASK | MANTISSA_MASK) | (ui64)exp << MANTISSA_BITS; } inline void dbl_parts::setExponent( std::int16_t exp ) { exp += BEXP_BASE; setBiasedExponent( exp ); } inline void dbl_parts::setMantissa( std::uint64_t mantissa ) { #if !defined(NDEBUG) ui64 mantissaMax = MANTISSA_MASK | (ui64)(getBiasedExponent() != BEXP_DENORMAL && getBiasedExponent() != BEXP_MAX) << MANTISSA_BITS; assert(mantissa <= mantissaMax); 
Subscribe to:
Post Comments (Atom)
|
No comments:
Post a Comment