diff options
| -rw-r--r-- | 04b/in03 | 552 | ||||
| -rw-r--r-- | 04b/in04b | 29 | ||||
| -rw-r--r-- | instructions.txt | 4 |
3 files changed, 504 insertions, 81 deletions
@@ -4,7 +4,8 @@ D=:global_variables 8C=D ; initialize static_memory_end C=:static_memory_end -D=x500000 +; 0x40000 = 256KB for code +D=x440000 8C=D ; initialize labels_end C=:labels_end @@ -150,6 +151,12 @@ D=A ?D!0:exit_success ; set 2nd pass to 1 1C=d1 + ; make sure output file is large enough for static memory + ; we'll use the ftruncate syscall to set the size of the file + J=d4 + I=:static_memory_end + I=8I + syscall x4d ; seek both files back to start J=d3 I=d0 @@ -192,12 +199,13 @@ align call :ident_lookup C=A ?C!0:local_redeclaration + C=:local_variable_name I=8C - J=:local_variables_end J=8J call :ident_copy + ; increase stack_end, store it in J C=:stack_end D=4C @@ -207,6 +215,7 @@ align J+=d4 ; store null terminator 1J=0 + ; update :local_variables_end I=:local_variables_end 8I=J @@ -349,7 +358,7 @@ align I=:line I+=d1 - J=:global_variables + J=:labels call :ident_lookup C=A ?C!0:label_redefinition @@ -386,7 +395,7 @@ align ; "return " is 7 chars long I+=d7 - call :set_rax_to_term + call :set_rax_to_rvalue J=d4 I=:function_epilogue @@ -477,73 +486,342 @@ align ?B=A:return_1 !:return_0 -; set rax to the term in rsi +; set <rax> to the term in rsi :set_rax_to_term R=I C=1I D='' ?C=D:term_char - - C=1I + D='. + ?C=D:term_label D=d58 ?C<D:term_number - + ; (fallthrough) +; set <rax> to the variable in rsi +:set_rax_to_variable ; variable + call :set_rax_to_address_of_variable + call :set_rbx_to_rax + call :set_rax_to_[rbx] + return + +:term_label + C=:second_pass + C=1C + ; skip looking up label on first pass; just use whatever's in rsi + ?C=0:set_rax_to_immediate + ; move past . + I+=d1 + J=:labels + call :ident_lookup + C=A + ?C=0:bad_label + ; set rax to label value + I=4C + !:set_rax_to_immediate + +align +:rvalue + reserve d8 + +; set <rax> to the rvalue in rsi +:set_rax_to_rvalue + ; store pointer to rvalue + C=:rvalue + 8C=I + + C=1I + D='& + ?C=D:rvalue_addressof + + D='~ + ?C=D:rvalue_bitwise_not + + D='* + ?C=D:rvalue_dereference + + J=I + :rvalue_loop + C=1J + D='( + ?C=D:rvalue_function + D=x20 + ?C=D:rvalue_binary_op + D=xa + ; no space or opening bracket; this must be a term + ?C=D:set_rax_to_term + J+=d1 + !:rvalue_loop + +:rvalue_function + xcc + +:binary_op + reserve d1 +:rvalue_binary_op + ; move past ' ' + J+=d1 + ; store binary op + D=1J + C=:binary_op + 1C=D + + ; make sure space follows operator + J+=d1 + C=1J + D=x20 + ?C!D:bad_term + ; set rsi to second operand + J+=d1 + I=J + call :set_rax_to_term + call :set_rsi_to_rax + + ; now set rax to first operand + I=:rvalue + I=8I + call :set_rax_to_term + + ; and combine + C=:binary_op + C=1C + + D='+ + ?C=D:rvalue_add + + D='- + ?C=D:rvalue_sub + + D='* + ?C=D:rvalue_mul + + D='/ + ?C=D:rvalue_div + + D='% + ?C=D:rvalue_rem + + D='& + ?C=D:rvalue_and + + D='| + ?C=D:rvalue_or + + D='^ + ?C=D:rvalue_xor + + D='< + ?C=D:rvalue_shl + + D='> + ?C=D:rvalue_shr + + !:bad_term + +:rvalue_add + call :set_rbx_to_rsi + J=d4 + I=:add_rax_rbx + D=d3 + syscall x1 + return +:add_rax_rbx + x48 + x01 + xd8 + +:rvalue_sub + call :set_rbx_to_rsi + J=d4 + I=:sub_rax_rbx + D=d3 + syscall x1 + return +:sub_rax_rbx + x48 + x29 + xd8 + +:rvalue_mul + call :set_rbx_to_rsi + J=d4 + I=:imul_rbx + D=d3 + syscall x1 + return +:imul_rbx + x48 + xf7 + xeb + +:rvalue_div + call :set_rbx_to_rsi + call :zero_rdx + J=d4 + I=:idiv_rbx + D=d3 + syscall x1 + return +:idiv_rbx + x48 + xf7 + xfb + +:rvalue_rem + call :set_rbx_to_rsi + call :zero_rdx + J=d4 + I=:idiv_rbx + D=d3 + syscall x1 + call :set_rax_to_rdx + return + +:rvalue_and + call :set_rbx_to_rsi + J=d4 + I=:and_rax_rbx + D=d3 + syscall x1 + return +:and_rax_rbx + x48 + x21 + xd8 + +:rvalue_or + call :set_rbx_to_rsi + J=d4 + I=:or_rax_rbx + D=d3 + syscall x1 + return +:or_rax_rbx + x48 + x09 + xd8 + +:rvalue_xor + call :set_rbx_to_rsi + J=d4 + I=:xor_rax_rbx + D=d3 + syscall x1 + return +:xor_rax_rbx + x48 + x31 + xd8 + +:rvalue_shl + call :set_rcx_to_rsi + J=d4 + I=:shl_rax_cl + D=d3 + syscall x1 + return +:shl_rax_cl + x48 + xd3 + xe0 + +:rvalue_shr + call :set_rcx_to_rsi + J=d4 + I=:shr_rax_cl + D=d3 + syscall x1 + return +:shr_rax_cl + x48 + xd3 + xe8 + +:rvalue_addressof + I+=d1 + !:set_rax_to_address_of_variable + +:rvalue_bitwise_not + I+=d1 + call :set_rax_to_term + J=d4 + I=:not_rax + D=d3 + syscall x1 + return +:not_rax + x48 + xf7 + xd0 + +:rvalue_dereference_size + reserve d1 + +:rvalue_dereference + I+=d1 + D=1I + C=:rvalue_dereference_size + 1C=D + I+=d1 + call :set_rax_to_variable + call :set_rbx_to_rax + call :zero_rax + C=:rvalue_dereference_size + C=1C + + D='1 + ?C=D:set_al_to_[rbx] + D='2 + ?C=D:set_ax_to_[rbx] + D='4 + ?C=D:set_eax_to_[rbx] + D='8 + ?C=D:set_rax_to_[rbx] + + !:bad_term + + +; set <rax> to address of variable in rsi +:set_rax_to_address_of_variable J=:local_variables call :ident_lookup C=A - ?C=0:rax2term_try_global + ?C=0:try_global ; it's a local variable - ; read the offset from rbp + ; read the offset from <rbp> D=4C - ; put negated offset in rcx - C=d0 - C-=D - ; store negated offset in :rax2term_addr - D=:rax2term_addr - 4D=C + ; put negated offset in rbp + R=d0 + R-=D + ; lea rax, [rbp+ J=d4 - I=:load_rbp_offset_prefix + I=:lea_rax_rbp_offset_prefix D=d3 syscall x1 + + ; offset] J=d4 - I=:rax2term_addr + I=:imm64 + 4I=R D=d4 syscall x1 return + :try_global + J=:global_variables + call :ident_lookup + C=A + ?C=0:bad_variable + ; it's a global variable + ; get its address + C=4C - :rax2term_try_global - J=:global_variables - call :ident_lookup - C=A - ?C=0:bad_term - ; it's a global variable - ; get its address - C=4C - D=:rax2term_addr - 4D=C - - ; put address in rbx - J=d4 - I=:mov_ebx_imm32_prefix - D=d1 - syscall x1 - J=d4 - I=:rax2term_addr - D=d4 - syscall x1 - - ; now load [rbx] into rax - J=d4 - I=:mov_rax_[rbx] - D=d3 - syscall x1 + ; put address in rax + I=C + !:set_rax_to_immediate - return - :term_char I+=d1 I=1I @@ -553,23 +831,29 @@ align reserve d1 :term_number + call :read_number + I=A + !:set_rax_to_immediate + +; set rax to the number in the string at rsi +:read_number C=1I D='- ; set rdx to 0 if number is positive, 1 if negative - ?C=D:term_number_negative + ?C=D:read_number_negative D=d0 - !:term_number_cont - :term_number_negative + !:read_number_cont + :read_number_negative D=d1 I+=d1 - :term_number_cont + :read_number_cont ; store away negativity C=:number_is_negative 1C=D C=1I D='0 - ?C=D:term_hex_number + ?C=D:read_hex_number ; it's a decimal number ; rbp will store the number R=d0 @@ -591,14 +875,14 @@ align I+=d1 !:decimal_number_loop :decimal_number_loop_end - !:term_number_output + !:read_number_output -:term_hex_number +:read_hex_number I+=d1 C=1I D='x ; 0 followed by something other than x - ?C!D:bad_term + ?C!D:bad_number I+=d1 ; rbp will store the number R=d0 @@ -626,10 +910,18 @@ align I+=d1 !:hex_number_loop :hex_number_loop_end - !:term_number_output + !:read_number_output -:term_number_output - ; we now have the *unsigned* number in rbp. first, take the sign into consideration +:read_number_output + ; first, make sure number is followed by space or newline + C=1I + D=x20 + ?C=D:read_number_valid + D=xa + ?C=D:read_number_valid + !:bad_number +:read_number_valid + ; we now have the *unsigned* number in rbp. take the sign into consideration C=:number_is_negative D=1C ?D=0:number_not_negative @@ -638,8 +930,9 @@ align R=d0 R-=C :number_not_negative - I=R - !:set_rax_to_immediate + ; finally, return + A=R + return @@ -661,13 +954,114 @@ align syscall x1 return -align -:rax2term_addr - reserve d4 +:zero_rax + J=d4 + I=:xor_eax_eax + D=d2 + syscall x1 + return +:xor_eax_eax + x31 + xc0 + +:zero_rdx + J=d4 + I=:xor_edx_edx + D=d2 + syscall x1 + return +:xor_edx_edx + x31 + xd2 + +:set_rbx_to_rax + J=d4 + I=:mov_rbx_rax + D=d3 + syscall x1 + return +:mov_rbx_rax + B=A + +:set_rbx_to_rsi + J=d4 + I=:mov_rbx_rsi + D=d3 + syscall x1 + return +:mov_rbx_rsi + B=I + +:set_rcx_to_rsi + J=d4 + I=:mov_rcx_rsi + D=d3 + syscall x1 + return +:mov_rcx_rsi + C=I + +:set_rax_to_rdx + J=d4 + I=:mov_rax_rdx + D=d3 + syscall x1 + return +:mov_rax_rdx + A=D -:mov_ebx_imm32_prefix - xbb +:set_rsi_to_rax + J=d4 + I=:mov_rsi_rax + D=d3 + syscall x1 + return +:mov_rsi_rax + I=A +:set_rax_to_[rbx] + J=d4 + I=:mov_rax_[rbx] + D=d3 + syscall x1 + return +:mov_rax_[rbx] + x48 + x8b + x03 + +:set_eax_to_[rbx] + J=d4 + I=:mov_eax_[rbx] + D=d2 + syscall x1 + return +:mov_eax_[rbx] + x8b + x03 + +:set_ax_to_[rbx] + J=d4 + I=:mov_ax_[rbx] + D=d3 + syscall x1 + return +:mov_ax_[rbx] + x66 + x8b + x03 + +:set_al_to_[rbx] + J=d4 + I=:mov_al_[rbx] + D=d2 + syscall x1 + return +:mov_al_[rbx] + x8a + x03 + + :mov_rax_imm64_prefix x48 xb8 @@ -675,15 +1069,11 @@ align align :imm64 reserve d8 -:mov_rax_[rbx] - x48 - x8b - x03 -; prefix for mov rax, [rbp+IMM32] -:load_rbp_offset_prefix +; prefix for lea rax, [rbp+IMM32] +:lea_rax_rbp_offset_prefix x48 - x8b + x8d x85 :input_filename @@ -730,6 +1120,24 @@ align xa x0 +:bad_variable + B=:bad_variable_error_message + !:program_error + +:bad_variable_error_message + str No such variable. + xa + x0 + +:bad_number + B=:bad_number_error_message + !:program_error + +:bad_number_error_message + str Bad number. + xa + x0 + :bad_term B=:bad_term_error_message !:program_error @@ -964,6 +1372,8 @@ align :"function" str function xa +:zero + x0 ; put a 0 byte before the line (this is important for removing whitespace at the end of the line, ; specifically, we don't want this to be a space character) @@ -1,9 +1,7 @@ -:test - return -0x3874f - ; declaration: -; global <type> <name> -; local <type> <name> +; global <name> +; local <name> +; argument <name> ; :<label> ; statement: ; <declaration> @@ -16,8 +14,10 @@ ; return <rvalue> ; string <str> ; byte <number> +; reserve <number> ; term: ; <var> +; .<label> ; <number> ; number: ; 'c @@ -25,12 +25,12 @@ ; 0xabc ; lvalue: ; <var> -; *1 <var> / *2 <var> / *4 <var> / *8 <var> +; *1<var> / *2<var> / *4<var> / *8<var> ; rvalue: -; <var> +; <term> ; &<var> -; *1 <var> / *2 <var> / *4 <var> / *8 <var> -; ~<var> +; *1<var> / *2<var> / *4<var> / *8<var> +; ~<term> ; <function>(<term>, <term>, ...) ; <term> + <term> ; <term> - <term> @@ -49,7 +49,16 @@ main() ; hello global x global y ;123 global z - +:test +function + local eee + local fff + local ggg + return *2fff +:test2 +function + return -123 + :syscall function ; ... diff --git a/instructions.txt b/instructions.txt index 52dcea5..13020ca 100644 --- a/instructions.txt +++ b/instructions.txt @@ -9,6 +9,8 @@ mov rax, imm64 >48 b8 IMM64 xor eax, eax (sets rax to 0, much shorter than mov rax, 0) >31 c0 +xor edx, edx +>31 d2 mov rdest, rsrc ax bx cx dx sp bp si di 0 3 1 2 4 5 6 7 @@ -51,6 +53,8 @@ neg rax >48 f7 d8 add rax, rbx >48 01 d8 +sub rax, rbx +>48 29 d8 imul rbx >48 f7 eb idiv rbx |