cosmopolitan build

build-cosmo.sh

@@ -1,5 +1,5 @@
 #!/bin/sh
 
-zig build-obj ./src/platform/cosmopolitan/main.zig -fno-PIE -fno-PIC -fno-stack-check --mod nmvm::src/nmvm.zig --deps nmvm
+zig build-obj ./src/main.zig -fno-PIE -fno-PIC -fno-stack-check
 ld.bfd main.o -o zig-out/bin/nmvm.com.dbg -T extern/cosmopolitan/ape.lds extern/cosmopolitan/crt.o extern/cosmopolitan/ape-copy-self.o \
     extern/cosmopolitan/cosmopolitan.a -z common-page-size=0x1000 -z max-page-size=0x1000 --gc-sections

prepare.sh

@@ -4,4 +4,4 @@ cd ./extern
 ./get.sh
 
 cd ../
-zig translate-c ./extern/cosmopolitan/cosmopolitan.h > ./src/platform/cosmopolitan/cosmopolitan.zig
+zig translate-c ./extern/cosmopolitan/cosmopolitan.h > ./src/cosmopolitan/cosmopolitan.zig

src/arch/x86-64.zig

@@ -1,2 +1,2 @@
 pub usingnamespace @import("x86-64/jedino-jedro.zig");
-pub usingnamespace @import("x86-64/zov/ve-sistema.zig");
+pub usingnamespace @import("x86-64/ve-sistema.zig");

src/arch/x86-64/jedino-jedro.zig

@@ -14,9 +14,6 @@
 
 // todo: Use ZF flag as conditional register so to not involve stack?
 //       Alternatively we could keep boolean word, but implement it in vector semantics.
-//
-//       ZF flag route can be achieved with using LEA instead of ADD as it doesn't touch flags,
-//       but we would need to store the flag when doing other calling convention calls.
 
 // Resources:
 // https://mort.coffee/home/fast-interpreters/
@@ -26,25 +23,10 @@
 // https://ziglang.org/documentation/master/#toc-Assembly
 // https://csiflabs.cs.ucdavis.edu/~ssdavis/50/att-syntax.htm
 // https://stackoverflow.com/questions/37639993/is-this-assembly-function-call-safe-complete
-// https://groups.csail.mit.edu/pag/OLD/parg/piumarta98optimizing.pdf
-// https://dl.acm.org/doi/pdf/10.1145/1328195.1328197
-// https://www.agner.org/optimize/instruction_tables.pdf
-// https://stackoverflow.com/questions/6323027/lea-or-add-instruction
 
 // Neat things:
 // https://joryanick.com/retro-fast-x86-memcpy.php
 // https://www.codeproject.com/Articles/1110153/Apex-memmove-the-fastest-memcpy-memmove-on-x-x-EVE
-// https://www.usenix.org/legacy/publications/library/proceedings/jvm01/gagnon/gagnon_html/node19.html#piumarta
-// https://www.agner.org/optimize/optimizing_assembly.pdf
-// http://sebastianmihai.com/x86-assembly-optimization.html
-
-// todo: Opcode for fast integer divisions with statically known divider.
-// todo: Opcodes taking operands based on offset from top of stack, without consuming.
-// todo: Certain constant multiplication optimization by LEA:
-//   LEA EAX, [EAX * 2 + EAX]   ;EAX = EAX * 3
-//   LEA EAX, [EAX * 4 + EAX]   ;EAX = EAX * 5
-//   LEA EAX, [EAX * 8 + EAX]   ;EAX = EAX * 9
-//
 
 const tolmac = @import("../../tolmac.zig");
 const Word = tolmac.Word;
@@ -53,7 +35,7 @@ const Word = tolmac.Word;
 /// (iw | -- iw)
 pub fn opPushWord() callconv(.Naked) noreturn {
     asm volatile (
-        \\ addq $0x10, %%r12
+        \\ add $0x10, %%r12
         \\ pushq -8(%%r12)
         \\ jmpq *(%%r12)
     );
@@ -63,7 +45,7 @@ pub fn opPushWord() callconv(.Naked) noreturn {
 /// (w)
 pub fn opSinkWord() callconv(.Naked) noreturn {
     asm volatile (
-        \\ addq $0x08, %%r12
+        \\ add $0x08, %%r12
         \\ addq $0x08, %%rsp
         \\ jmpq *(%%r12)
     );
@@ -83,29 +65,20 @@ pub fn opSinkWord() callconv(.Naked) noreturn {
 //     @call(.always_tail, binary[2].function, .{ &binary[2], cond });
 // }
 
+// todo: Generate operation permutations procedurally.
+// todo: Jump on overflow instead of cond setting?
 /// (w1 w2 -- sum overflow)
 pub fn opSumWordsWithOverflow() callconv(.Naked) noreturn {
-    // https://www.felixcloutier.com/x86/add
+    // https://www.felixcloutier.com/x86/adc
     // https://www.felixcloutier.com/x86/setcc
+    // idea: Could https://www.felixcloutier.com/x86/cmovcc be better for overflow push?
     asm volatile (
         \\ addq $0x08, %%r12
-        \\ movq (%%rsp), %%rbx
-        \\ movq %%rbx, %%rax
-        \\ addq 8(%%rsp), %%rax
+        \\ movq (%%rsp), %%rax
+        \\ adcq 8(%%rsp), %%rax
         \\ movq %%rax, 8(%%rsp)
-        \\ xorq %%rbx, (%%rsp)
-        \\ setc (%%rsp)
-        \\ jmpq *(%%r12)
-    );
-}
-
-/// (w1 w2 -- sum)
-pub fn opSumWords() callconv(.Naked) noreturn {
-    asm volatile (
-        \\ addq $0x08, %%r12
-        \\ popq %%rax
-        \\ addq (%%rsp), %%rax
-        \\ movq %%rax, (%%rsp)
+        \\ setc %%al
+        \\ movb %%al, (%%rsp)
         \\ jmpq *(%%r12)
     );
 }
@@ -119,6 +92,9 @@ pub fn opSumWords() callconv(.Naked) noreturn {
 //     @call(.always_tail, binary[offset].function, .{ &binary[offset], cond });
 // }
 
+// todo: Complex call op that would receive immediate mask that would tell
+//       which positions of stack to duplicate, as well as mixing of plain immediate operands.
+//       Or we could decouple it from call, it might be useful at other places.
 /// (iw |)
 pub fn opCall() callconv(.Naked) noreturn {
     asm volatile (

src/arch/x86-64/ve-sistema.zig

@@ -1,16 +1,12 @@
-//! .zov.ve-sistema:x86-64
+//! ve sistema (.ve-sistema:x86-64)
 //!
 //! Provides entry opcodes for System V calling convention, optimized for specific prototypes.
 //!
 
 // https://refspecs.linuxbase.org/elf/x86_64-abi-0.99.pdf
 
-// todo: Provide opcode that would dynamically dispatch based on marshaled C prototypes,
-//       which will be sufficient for rare prototypes sporadically used, so to not bloat
-//       the binary with all possible permutations or ask for them on comptime, which is unreasonable.
-
 const std = @import("std");
-const tolmac = @import("../../../tolmac.zig");
+const tolmac = @import("../../tolmac.zig");
 
 /// Used for stack parameter passing.
 pub const WordLimit = 128;
@@ -115,8 +111,8 @@ pub fn generateOpZovSysvFromPrototype(prototype: anytype) !*const fn () callconv
         ;
 
         var integer_allocation: usize = 0;
-        const IntegerAllocations = [_][]const u8{ "rdi", "rsi", "rdx", "rcx", "r8", "r9" };
-        //  var sse_allocation: enum { xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7 } = .xmm0;
+        const IntegerAllocations = [_][]const u8{ "rdi", "rsi", "rdx", "rcx", "r8", "r9", "stack" };
+        //  var sse_allocation: enum { xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, stack } = .xmm0;
 
         var class_buffer = [_]Class{.void} ** ClassBufferLimit;
 

src/main.zig

@@ -1,5 +1,5 @@
-const tolmac = @import("nmvm").tolmac;
-const cosmo = @import("cosmopolitan.zig");
+const tolmac = @import("tolmac.zig");
+const cosmo = @import("cosmopolitan/cosmopolitan.zig");
 
 fn printInt3(int: u64, other: u32, another: u16) callconv(.SysV) void {
     @setAlignStack(16);
@@ -20,7 +20,7 @@ comptime {
 
 // todo: No cosmopolitan main.
 
-fn cosmopolitanMain(argc: c_int, argv: [*][*:0]u8) callconv(.SysV) c_int {
+export fn cosmopolitanMain(argc: c_int, argv: [*][*:0]u8) c_int {
     _ = argc;
     _ = argv;
 
@@ -57,5 +57,5 @@ fn cosmopolitanMain(argc: c_int, argv: [*][*:0]u8) callconv(.SysV) c_int {
 }
 
 test {
-    _ = @import("nmvm").tolmac;
+    _ = @import("tolmac.zig");
 }

src/nmvm.zig

@@ -1 +0,0 @@
-pub const tolmac = @import("tolmac.zig");