claunia/flac
1
0
Fork 0
mirror of https://github.com/claunia/flac.git synced 2025-12-16 18:54:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

libFLAC/ia32/lpc_asm.nasm : Match calls and returns.

Browse Source 
According to Agner Fog, "...you must make sure that all calls
are matched with returns. Never jump out of a subroutine without
a return and never use a return as an indirect jump."

(see paragraph 3.15 in microarchitecture.pdf and
examples 3.5a and 3.5b in optimizing_assembly.pdf)

Patch-from: lvqcl <lvqcl.mail@gmail.com>
This commit is contained in:
Erik de Castro Lopo
2014-01-07 21:25:03 +11:00
parent 6cd8b42438
commit 8e4a45ac86
1 changed files with 16 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/libFLAC/ia32/lpc_asm.nasm
View File

@@ -115,9 +115,8 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
lea edx, [eax + eax*2]
neg edx
lea edx, [eax + edx*4 + .jumper1_0 - .get_eip1]
call .get_eip1
call .mov_eip_to_ebx
.get_eip1:
pop ebx
add edx, ebx
inc edx ; compensate for the shorter opcode on the last iteration
inc edx ; compensate for the shorter opcode on the last iteration
@@ -128,6 +127,10 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
.loop1_start:
jmp edx
.mov_eip_to_ebx:
mov ebx, [esp]
ret
fld st0 ; ST = d d
fmul dword [esi + (32*4)] ; ST = d*data[sample+32] d WATCHOUT: not a byte displacement here!
fadd dword [edi + (32*4)] ; ST = autoc[32]+d*data[sample+32] d WATCHOUT: not a byte displacement here!
@@ -285,9 +288,8 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
lea edx, [eax + eax*2]
neg edx
lea edx, [eax + edx*4 + .jumper2_0 - .get_eip2]
call .get_eip2
call .mov_eip_to_ebx
.get_eip2:
pop ebx
add edx, ebx
inc edx ; compensate for the shorter opcode on the last iteration
inc edx ; compensate for the shorter opcode on the last iteration
@@ -919,13 +921,16 @@ cident FLAC__lpc_compute_residual_from_qlp_coefficients_asm_ia32
jmp .end
.mov_eip_to_eax:
mov eax, [esp]
ret
.i_32:
sub edi, esi
neg eax
lea edx, [eax + eax * 8 + .jumper_0 - .get_eip0]
call .get_eip0
call .mov_eip_to_eax
.get_eip0:
pop eax
add edx, eax
inc edx
mov eax, [esp + 28] ; eax = qlp_coeff[]
@@ -1323,13 +1328,16 @@ cident FLAC__lpc_restore_signal_asm_ia32
jmp .end
.mov_eip_to_eax:
mov eax, [esp]
ret
.x87_32:
sub esi, edi
neg eax
lea edx, [eax + eax * 8 + .jumper_0 - .get_eip0]
call .get_eip0
call .mov_eip_to_eax
.get_eip0:
pop eax
add edx, eax
inc edx ; compensate for the shorter opcode on the last iteration
mov eax, [esp + 28] ; eax = qlp_coeff[]