AuroraMiddleware/flac
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

check in Miroslav's PIC patch

Browse Source
This commit is contained in:
Josh Coalson 2001-12-04 05:36:09 +00:00
parent 457f467959
commit 651d6de93a
1 changed files with 33 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
src/libFLAC/ia32/lpc_asm.nasm
View File

@ -59,10 +59,10 @@ cglobal FLAC__lpc_restore_signal_asm_ia32_mmx
; ;
ALIGN 16 ALIGN 16
cident FLAC__lpc_compute_autocorrelation_asm_ia32 cident FLAC__lpc_compute_autocorrelation_asm_ia32
;[esp + 24] == autoc[] ;[esp + 28] == autoc[]
;[esp + 20] == lag ;[esp + 24] == lag
;[esp + 16] == data_len ;[esp + 20] == data_len
;[esp + 12] == data[] ;[esp + 16] == data[]
;ASSERT(lag > 0) ;ASSERT(lag > 0)
;ASSERT(lag <= 33) ;ASSERT(lag <= 33)
@ -71,21 +71,22 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
.begin: .begin:
push esi push esi
push edi push edi
push ebx
; for(coeff = 0; coeff < lag; coeff++) ; for(coeff = 0; coeff < lag; coeff++)
; autoc[coeff] = 0.0; ; autoc[coeff] = 0.0;
mov edi, [esp + 24] ; edi == autoc mov edi, [esp + 28] ; edi == autoc
mov ecx, [esp + 20] ; ecx = # of dwords (=lag) of 0 to write mov ecx, [esp + 24] ; ecx = # of dwords (=lag) of 0 to write
xor eax, eax xor eax, eax
rep stosd rep stosd
; const unsigned limit = data_len - lag; ; const unsigned limit = data_len - lag;
mov eax, [esp + 20] ; eax == lag mov eax, [esp + 24] ; eax == lag
mov ecx, [esp + 16] mov ecx, [esp + 20]
sub ecx, eax ; ecx == limit sub ecx, eax ; ecx == limit
mov edi, [esp + 24] ; edi == autoc mov edi, [esp + 28] ; edi == autoc
mov esi, [esp + 12] ; esi == data mov esi, [esp + 16] ; esi == data
inc ecx ; we are looping <= limit so we add one to the counter inc ecx ; we are looping <= limit so we add one to the counter
; for(sample = 0; sample <= limit; sample++) { ; for(sample = 0; sample <= limit; sample++) {
@ -97,7 +98,11 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
; each iteration is 11 bytes so we need (-eax)*11, so we do (-12*eax + eax) ; each iteration is 11 bytes so we need (-eax)*11, so we do (-12*eax + eax)
lea edx, [eax + eax*2] lea edx, [eax + eax*2]
neg edx neg edx
lea edx, [eax + edx*4 + .jumper1_0] lea edx, [eax + edx*4 + .jumper1_0 - .get_eip1]
call .get_eip1
.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
inc edx ; compensate for the shorter opcode on the last iteration inc edx ; compensate for the shorter opcode on the last iteration
inc edx ; compensate for the shorter opcode on the last iteration inc edx ; compensate for the shorter opcode on the last iteration
@ -254,7 +259,7 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
; for(coeff = 0; coeff < data_len - sample; coeff++) ; for(coeff = 0; coeff < data_len - sample; coeff++)
; autoc[coeff] += d * data[sample+coeff]; ; autoc[coeff] += d * data[sample+coeff];
; } ; }
mov ecx, [esp + 20] ; ecx <- lag mov ecx, [esp + 24] ; ecx <- lag
dec ecx ; ecx <- lag - 1 dec ecx ; ecx <- lag - 1
jz near .end ; skip loop if 0 (i.e. lag == 1) jz near .end ; skip loop if 0 (i.e. lag == 1)
@ -263,7 +268,11 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
; each iteration is 11 bytes so we need (-eax)*11, so we do (-12*eax + eax) ; each iteration is 11 bytes so we need (-eax)*11, so we do (-12*eax + eax)
lea edx, [eax + eax*2] lea edx, [eax + eax*2]
neg edx neg edx
lea edx, [eax + edx*4 + .jumper2_0] lea edx, [eax + edx*4 + .jumper2_0 - .get_eip2]
call .get_eip2
.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
inc edx ; compensate for the shorter opcode on the last iteration inc edx ; compensate for the shorter opcode on the last iteration
inc edx ; compensate for the shorter opcode on the last iteration inc edx ; compensate for the shorter opcode on the last iteration
@ -409,6 +418,7 @@ cident FLAC__lpc_compute_autocorrelation_asm_ia32
.loop2_end: .loop2_end:
.end: .end:
pop ebx
pop edi pop edi
pop esi pop esi
ret ret
@ -804,7 +814,11 @@ cident FLAC__lpc_compute_residual_from_qlp_coefficients_asm_ia32
.i_32: .i_32:
sub edi, esi sub edi, esi
neg eax neg eax
lea edx, [eax + eax * 8 + .jumper_0] lea edx, [eax + eax * 8 + .jumper_0 - .get_eip0]
call .get_eip0
.get_eip0:
pop eax
add edx, eax
inc edx inc edx
mov eax, [esp + 28] ; eax = qlp_coeff[] mov eax, [esp + 28] ; eax = qlp_coeff[]
xor ebp, ebp xor ebp, ebp
@ -1203,7 +1217,11 @@ cident FLAC__lpc_restore_signal_asm_ia32
.x87_32: .x87_32:
sub esi, edi sub esi, edi
neg eax neg eax
lea edx, [eax + eax * 8 + .jumper_0] lea edx, [eax + eax * 8 + .jumper_0 - .get_eip0]
call .get_eip0
.get_eip0:
pop eax
add edx, eax
inc edx ; compensate for the shorter opcode on the last iteration inc edx ; compensate for the shorter opcode on the last iteration
mov eax, [esp + 28] ; eax = qlp_coeff[] mov eax, [esp + 28] ; eax = qlp_coeff[]
xor ebp, ebp xor ebp, ebp