gcc plugin to collect cross-references, part 9
Lets extract some useful results from my gcc plugin for collecting cross-references: 1, 2, 3, 4, 5, 6, 7& 8. I've noticed that plugin worked unbearably slowly on big source files (like compiling...
View ArticleTLS in gcc RTL
Lets check how TLS looks like in RTL. I wrote simple test:(insn 29 8 10 3 (set (reg:SI 0 ax [orig:82 _1 ] [82]) (mem/c:SI (const:DI (unspec:DI [ (symbol_ref:DI...
View Articlebinding c++ objects to perl
Sure there are lots of ways to do this (as usually in Perl: "there's more than one way to do it"), just to name few:swig - result looks not native and clumsy, also you need to make facade-like...
View Articleperl module for DWARF debug info parsing
I've made perl binding of my c++ dwarf dumper. Supports 64/32 bit, no DWO, don't sure if it can load arbitrary object files but at least can parse LKM - I even added relocations processingMaybe one day...
View Articleperl module for powerpc disasm
It seems that there are no good open-source disasm for PPC except Capstone. And it even has perl binding - unfortunately it can extract only basic fields like opcode and text but no operands for...
View Articleptx internals
It seems that syntax of PTX is undocumented - at least I was unable to find actual BNF grammar or reference implementation. Grammar from antlr project is greatly out-dated and don't contain...
View Articlenvidia sass disassembler
Couple weeks ago I made decryptor to extract from nvdisasm so called "machine descriptions" (MD) (btw nvdisasm v12 uses lz4 compression library, so I made yet another decryptor + results). And after...
View Articlenvidia sass disassembler, part 2
Lets continue explore "machine descriptions" - in this time try to understand how to make format output more similar to genuine nvdisasmFor example format for one of variant I2F looks like: FORMAT...
View Articlenvidia sass disassembler, part 3
It looks like this rabbit hole goes much deeperSome const banks does not have ConstBankAddressX:CX:Sb[UniformRegister:URb][UImm(16)*:Sb_offset]BITS_6_37_32_Ra_URb=URbBITS_14_53_40_Sb_offset=Sb_offset...
View ArticleClik here to view.
nvidia sass disassembler, part 4
I've made native sass disasm - just adding c++ codegen (can be produced by ead.pl with -C option). It works via dynamic loading of right disasm module - see list of supported architectures in map...
View Articlenvidia sass disassembler, part 5
Previous parts: 1, 2, 3& 4I've finally add native rendering for instructions - actually just rewrite from perl terrible function make_inst. Because in output typically rendering only small fraction...
View Articleptx instructions emitting by nvidia compiler
I recently became curious what exactly ptx instructions can produce nvidia compiler - like if it uses something totally undocumented or vice versa - some official ptx instructions are never generated...
View Articleptx instructions emitting by nvidia compiler. part 2
Part 1 described v10And today let's check cicc v12. The first thing that catches your eye is its size - almost 76Mb! And it also contains at least 5 different decryptors - Nvidia really wants to hide...
View Articlenvidia sass disassembler, part 6: predicates
Previous parts: 1, 2, 3, 4& 5Lets check how pairs of instructions are chained together - this information stored in MD files with prefix _2.txt - for example from sm90_2.txt: CONNECTOR CONDITIONS...
View Article