Go Native : Squeeze the juice out of your 64-bit processor using C++
Download as PPTX, PDF0 likes674 views
The document discusses native 64-bit development using C/C++. It begins with introductions from the presenter and asks attendees about their experiences. The talk's schedule is then outlined, covering introducing 64-bit processors, advantages over 32-bit, how native 64-bit development looks, data models, common pitfalls, optimization tips, real-world tips, code analysis and debugging tools, and prospecting the costs of 64-bit development. The presentation aims to help developers optimize their code and leverage 64-bit capabilities.
Go Native : Squeeze the juice out of your 64-bit processor using C++
- 1. Go Native Squeeze the juice out of your 64-bit processor using…
- 2. Go Native C/C++ Squeeze the juice out of your 64-bit processor using…
- 3. Who am I
- 4. Who am I -> Fernando Moreira ( @fpmore )
- 5. Who am I -> Fernando Moreira ( @fpmore ) -> MSc student @ FEUP
- 6. Who am I -> Fernando Moreira ( @fpmore ) -> MSc student @ FEUP -> Undergraduate Researcher @ Porto Interactive Center
- 7. Who am I -> Fernando Moreira ( @fpmore ) -> MSc student @ FEUP -> Undergraduate Researcher @ Porto Interactive Center -> Microsoft Student Partner Lead @ M$ PT
- 8. Who am I -> Fernando Moreira ( @fpmore ) -> MSc student @ FEUP -> Undergraduate Researcher @ Porto Interactive Center -> Microsoft Student Partner Lead @ M$ PT -> I’ve doing C++ for over… 5y
- 9. Who are you ?
- 10. Who are you ? -> Norte
- 11. Who are you ? -> Norte . Centro
- 12. Who are you ? -> Norte . Centro . Sul
- 13. Who are you ? -> Norte . Centro . Sul . Açores
- 14. Who are you ? -> Norte . Centro . Sul . Açores . Madeira
- 15. Who are you ? -> Norte . Centro . Sul . Açores . Madeira . FMI
- 16. Who are you ? -> Norte . Centro . Sul . Açores . Madeira . FMI -> Who has experience with C?
- 17. Who are you ? -> Norte . Centro . Sul . Açores . Madeira . FMI -> Who has experience with C? And with C++?
- 18. Who are you ? -> Norte . Centro . Sul . Açores . Madeira . FMI -> Who has experience with C? And with C++? -> Who has experience with 64bit native dev?
- 19. Talk’s Schedule int main( int argc, char **argv ) { try { } catch( Timeout &e ) { return -1; } return 0; }
- 20. Talk’s Schedule int main( int argc, char **argv ) { try { introducing_x64(); } catch( Timeout &e ) { return -1; } return 0; }
- 21. Talk’s Schedule int main( int argc, char **argv ) { try { introducing_x64(); advantagesOver_x86(); } catch( Timeout &e ) { return -1; } return 0; }
- 22. Talk’s Schedule int main( int argc, char **argv ) { try { introducing_x64(); advantagesOver_x86(); nativeDev_x64( const Topic &t ); } catch( Timeout &e ) { return -1; } Promising not to change the topic. return 0; }
- 23. Talk’s Schedule int main( int argc, char **argv ) { try { introducing_x64(); advantagesOver_x86(); nativeDev_x64( const Topic &t ); codeAnalysis_and_DebugTools(); } catch( Timeout &e ) { return -1; } return 0; }
- 24. Talk’s Schedule int main( int argc, char **argv ) { try { introducing_x64(); advantagesOver_x86(); nativeDev_x64( const Topic &t ); codeAnalysis_and_DebugTools(); costProspectionOn_x64Dev(); } catch( Timeout &e ) { return -1; } return 0; }
- 26. introducing_x64() -> The names : x64, x86-64, AMD64, Intel 64, IA-64, etc…
- 27. introducing_x64() -> The names : x64, x86-64, AMD64, Intel 64, IA-64, etc… -> Notice : IA-64 ≠ AMD64
- 28. introducing_x64() -> The names : x64, x86-64, AMD64, Intel 64, IA-64, etc… -> Notice : IA-64 ≠ AMD64 -> AMD64 is backwards compatible with x86 (IA-64 isn’t)
- 29. introducing_x64() -> The names : x64, x86-64, AMD64, Intel 64, IA-64, etc… -> Notice : IA-64 ≠ AMD64 -> AMD64 is backwards compatible with x86 (IA-64 isn’t) -> Some Hardware: Phenom, Athlon 64, Core-iX, Core 2, …
- 30. introducing_x64() -> The names : x64, x86-64, AMD64, Intel 64, IA-64, etc… -> Notice : IA-64 ≠ AMD64 -> AMD64 is backwards compatible with x86 (IA-64 isn’t) -> Some Hardware: Phenom, Athlon 64, Core-iX, Core 2, … -> Some OS’s : Win(XP.Vista.7), OSX, Several Linux distros.
- 31. introducing_x64() This talk will be focused on the AMD64 architecture.
- 33. advantagesOver_x86() -> Address space : Theoretical limit of 16 ExaBytes (2^64)
- 34. advantagesOver_x86() -> Address space : Theoretical limit of 16 ExaBytes (2^64) -> More available registers. (there’s one called RIP)
- 35. advantagesOver_x86() -> Address space : Theoretical limit of 16 ExaBytes (2^64) -> More available registers. (there’s one called RIP) -> Larger instruction set with emphasis on SIMD
- 36. advantagesOver_x86() -> Address space : Theoretical limit of 16 ExaBytes (2^64) -> More available registers. (there’s one called RIP) -> Larger instruction set with emphasis on SIMD -> SSE1, SSE2, and SSE3 are always there
- 37. advantagesOver_x86() -> Address space : Theoretical limit of 16 ExaBytes (2^64) -> More available registers. (there’s one called RIP) -> Larger instruction set with emphasis on SIMD -> SSE1, SSE2, and SSE3 are always there -> Unified function calling convention
- 38. advantagesOver_x86() Can run x86 environments Can run x86 binaries under x64 environments On Windows: . 32bit processes can’t load 64bit DLLs for execution . 64bit processes can’t load 32bit DLLs for execution
- 40. nativeDev_x64( how_it_looks_like ) -> A valid, yet useless, 64bit application. int main( int argc, char **argv } { return 0; }
- 41. nativeDev_x64( how_it_looks_like ) -> A valid, yet useless and dangerous, 64bit application. int main( int argc, char **argv } { size_t external_debt = SIZE_MAX; int *ptr = &external_debt; *ptr = 0; return 0; }
- 42. nativeDev_x64( how_it_looks_like ) -> A valid, yet useless and dangerous, 64bit application. int main( int argc, char **argv } { size_t external_debt = SIZE_MAX; int *ptr = &external_debt; *ptr = 0; return 0; }
- 44. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model
- 45. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model -> On Linux : LP64 model
- 46. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model -> On Linux : LP64 model -> LLP64: short( 2 ), int( 4 ), long( 4 ), ptr( 8 ), long long(8)
- 47. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model -> On Linux : LP64 model -> LLP64: short( 2 ), int( 4 ), long( 4 ), ptr( 8 ), long long(8) -> LP64: short( 2 ), int( 4 ), long( 8 ), ptr( 8 ), long long( 8 )
- 48. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model -> On Linux : LP64 model -> LLP64: short( 2 ), int( 4 ), long( 4 ), ptr( 8 ), long long(8) -> LP64: short( 2 ), int( 4 ), long( 8 ), ptr( 8 ), long long( 8 ) Can you see the data portability problem?
- 49. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model -> On Linux : LP64 model -> LLP64: short( 2 ), int( 4 ), long( 4 ), ptr( 8 ), long long(8) -> LP64: short( 2 ), int( 4 ), long( 8 ), ptr( 8 ), long long( 8 ) Suggestions: Use conditional compilation and type aliasing.
- 50. nativeDev_x64( data_model ) -> On Microsoft Win64 : LLP64 model -> On Linux : LP64 model -> LLP64: short( 2 ), int( 4 ), long( 4 ), ptr( 8 ), long long(8) -> LP64: short( 2 ), int( 4 ), long( 8 ), ptr( 8 ), long long( 8 ) Suggestions: Use conditional compilation and type aliasing. Make conscious usage of the sizeof operator.
- 51. nativeDev_x64( data_model ) -> On x86 : ptr( 4 ), size_t( 4 ), ptrdiff_t( 4 )
- 52. nativeDev_x64( data_model ) -> On x86 : ptr( 4 ), size_t( 4 ), ptrdiff_t( 4 ) -> On x64 : ptr( 8 ), size_t( 8 ), ptrdiff_t( 8 )
- 53. nativeDev_x64( data_model ) -> On x86 : ptr( 4 ), size_t( 4 ), ptrdiff_t( 4 ) -> On x64 : ptr( 8 ), size_t( 8 ), ptrdiff_t( 8 ) These ones will increase memory usage… But will be performance-wise.
- 55. nativeDev_x64( common_pitfalls ) -> Usage of magic numbers & bit-wise ops: 0x7fffffff
- 56. nativeDev_x64( common_pitfalls ) -> Usage of magic numbers & bit-wise ops: 0x7fffffff -> Functions with variable number of arguments : printf
- 57. nativeDev_x64( common_pitfalls ) -> Usage of magic numbers & bit-wise ops: 0x7fffffff -> Functions with variable number of arguments : printf -> Virtual functions
- 58. nativeDev_x64( common_pitfalls ) -> Usage of magic numbers & bit-wise ops: 0x7fffffff -> Functions with variable number of arguments : printf -> Virtual functions -> Data exchange between x86 and x64 apps
- 59. nativeDev_x64( common_pitfalls ) -> Usage of magic numbers & bit-wise ops: 0x7fffffff -> Functions with variable number of arguments : printf -> Virtual functions -> Data exchange between x86 and x64 apps -> Data misalignment : SSE requires 16-byte alignment
- 61. nativeDev_x64( optimization_tips ) -> Use native types for loops or tight data usage
- 62. nativeDev_x64( optimization_tips ) -> Use native types for loops or tight data usage -> Use 16-byte alignment for SSE loads and stores
- 63. nativeDev_x64( optimization_tips ) -> Use native types for loops or tight data usage -> Use 16-byte alignment for SSE loads and stores -> Heap-allocs in Win64 and XBOX360 are 16-byte aligned
- 64. nativeDev_x64( optimization_tips ) -> Use native types for loops or tight data usage -> Use 16-byte alignment for SSE loads and stores -> Heap-allocs in Win64 and XBOX360 are 16-byte aligned -> *Use* intrinsics : #include <immintrin.h>
- 65. nativeDev_x64( optimization_tips ) -> Use native types for loops or tight data usage -> Use 16-byte alignment for SSE loads and stores -> Heap-allocs in Win64 and XBOX360 are 16-byte aligned -> *Use* intrinsics : #include <immintrin.h> -> Unroll loops and sort object’s member data by their size
- 67. nativeDev_x64( real-world_tips ) -> Don’t sacrifice your software architecture.
- 68. nativeDev_x64( real-world_tips ) -> Don’t sacrifice your software architecture. -> Don’t use it if you don’t know how to.
- 69. nativeDev_x64( real-world_tips ) -> Don’t sacrifice your software architecture. -> Don’t use it if you don’t know how to. -> Don’t go into premature optimization.
- 70. nativeDev_x64( real-world_tips ) -> Don’t sacrifice your software architecture. -> Don’t use it if you don’t know how to. -> Don’t go into premature optimization. -> Do it at lower levels and then hide it.
- 71. nativeDev_x64( real-world_tips ) -> Don’t sacrifice your software architecture. -> Don’t use it if you don’t know how to. -> Don’t go into premature optimization. -> Do it at lower levels and then hide it. -> Trust your compiler to help you do the job.
- 73. codeAnalysis_and_DebugTools() -> Your IDE : LEARN to fu**** use it!
- 74. codeAnalysis_and_DebugTools() -> Your IDE : LEARN to fu**** use it! -> Conditional break points, call-stack
- 75. codeAnalysis_and_DebugTools() -> Your IDE : LEARN to fu**** use it! -> Conditional break points, call-stack -> Free tool : CppCheck (CmdLine, Eclipse, CodeBlocks, …)
- 76. codeAnalysis_and_DebugTools() -> Your IDE : LEARN to fu**** use it! -> Conditional break points, call-stack -> Free tool : CppCheck (CmdLine, Eclipse, CodeBlocks, …) -> State-of-the-art tool: PVS-Studio (VS 05,08,10)
- 77. codeAnalysis_and_DebugTools() -> Your IDE : LEARN to fu**** use it! -> Conditional break points, call-stack -> Free tool : CppCheck (CmdLine, Eclipse, CodeBlocks, …) -> State-of-the-art tool: PVS-Studio (VS 05,08,10) -> Do pair programming and peer-review if possible
- 79. costProspectionOn_x64Dev() -> Hardware & Software (IDE + Plugins + Tools + Libs)
- 80. costProspectionOn_x64Dev() -> Hardware & Software (IDE + Plugins + Tools + Libs) -> You’ll need to teach the developers (theory & practice)
- 81. costProspectionOn_x64Dev() -> Hardware & Software (IDE + Plugins + Tools + Libs) -> You’ll need to teach the developers (theory & practice) -> A port takes time, adds bugs, and it’s not creative
- 82. costProspectionOn_x64Dev() -> Hardware & Software (IDE + Plugins + Tools + Libs) -> You’ll need to teach the developers (theory & practice) -> A port takes time, adds bugs, and it’s not creative -> … plus you’ll probably have to maintain two code paths
- 83. costProspectionOn_x64Dev() -> Hardware & Software (IDE + Plugins + Tools + Libs) -> You’ll need to teach the developers (theory & practice) -> A port takes time, adds bugs, and it’s not creative -> … plus you’ll probably have to maintain two code paths -> Full implementation adds creativity, but takes much more time and will add many more bugs.
- 85. Questions?