breeze/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2026-01-12 00:06:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Revert "avutil/tx_template: extend to 2M"

Browse Source 
This reverts commit 8f48a62, 9af8782, and bd3e71b.

Commit 8f48a62 extends tx to 2M, resulting in the tx_float bss
section reaching a size of 4M.

This isn't a issue on devices with normal memory sizes and OS
supporting virtual memory. But it's a real issue for embedded devices
with realtime OS, which may not support virtual memory, e.g., Nuttx.
This 4M of bss section map to physical memory directly, which is a
scarce resource on embedded devices.
This commit is contained in:
Zhao Zhili
2025-12-13 12:53:58 +08:00
committed by James Almer
parent 3da2a21710
commit 1e2d86201f
3 changed files with 11 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
libavutil/tx_template.c
View File

@@ -45,10 +45,6 @@
SR_TABLE(32768) \
SR_TABLE(65536) \
SR_TABLE(131072) \
SR_TABLE(262144) \
SR_TABLE(524288) \
SR_TABLE(1048576) \
SR_TABLE(2097152) \
#define SR_TABLE(len) \
TABLE_DEF(len, len/4 + 1);
@@ -724,10 +720,6 @@ DECL_SR_CODELET(16384,8192,4096)
DECL_SR_CODELET(32768,16384,8192)
DECL_SR_CODELET(65536,32768,16384)
DECL_SR_CODELET(131072,65536,32768)
DECL_SR_CODELET(262144,131072,65536)
DECL_SR_CODELET(524288,262144,131072)
DECL_SR_CODELET(1048576,524288,262144)
DECL_SR_CODELET(2097152,1048576,524288)
static av_cold int TX_NAME(ff_tx_fft_init)(AVTXContext *s,
const FFTXCodelet *cd,
@@ -2160,10 +2152,6 @@ const FFTXCodelet * const TX_NAME(ff_tx_codelet_list)[] = {
&TX_NAME(ff_tx_fft32768_ns_def),
&TX_NAME(ff_tx_fft65536_ns_def),
&TX_NAME(ff_tx_fft131072_ns_def),
&TX_NAME(ff_tx_fft262144_ns_def),
&TX_NAME(ff_tx_fft524288_ns_def),
&TX_NAME(ff_tx_fft1048576_ns_def),
&TX_NAME(ff_tx_fft2097152_ns_def),
/* Prime factor codelets */
&TX_NAME(ff_tx_fft3_ns_def),

8
libavutil/x86/tx_float.asm
View File

@@ -46,7 +46,7 @@
%endif
%assign i 16
%rep 18
%rep 14
cextern tab_ %+ i %+ _float ; ff_tab_i_float...
%assign i (i << 1)
%endrep
@@ -1385,11 +1385,7 @@ FFT_SPLIT_RADIX_DEF 8192, .16384pt
FFT_SPLIT_RADIX_DEF 16384, .32768pt
FFT_SPLIT_RADIX_DEF 32768, .65536pt
FFT_SPLIT_RADIX_DEF 65536, .131072pt
FFT_SPLIT_RADIX_DEF 131072, .262144pt
FFT_SPLIT_RADIX_DEF 262144, .524288pt
FFT_SPLIT_RADIX_DEF 524288, .1048576pt
FFT_SPLIT_RADIX_DEF 1048576, .2097152pt
FFT_SPLIT_RADIX_DEF 2097152
FFT_SPLIT_RADIX_DEF 131072
;===============================================================================
; Final synthesis + deinterleaving code

18
libavutil/x86/tx_float_init.c
View File

@@ -271,15 +271,15 @@ const FFTXCodelet * const ff_tx_codelet_list_float_x86[] = {
AV_TX_INPLACE | FF_TX_PRESHUFFLE | FF_TX_ASM_CALL, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft32_ns, FFT, 32, 32, 2, 0, 352, b8_i2, fma3, FMA3, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr, FFT, 64, 2097152, 2, 0, 256, b8_i2, avx, AVX, 0, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_asm, FFT, 64, 2097152, 2, 0, 320, b8_i2, avx, AVX,
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 256, b8_i2, avx, AVX, 0, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_asm, FFT, 64, 131072, 2, 0, 320, b8_i2, avx, AVX,
AV_TX_INPLACE | FF_TX_PRESHUFFLE | FF_TX_ASM_CALL, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_ns, FFT, 64, 2097152, 2, 0, 320, b8_i2, avx, AVX, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 320, b8_i2, avx, AVX, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr, FFT, 64, 2097152, 2, 0, 288, b8_i2, fma3, FMA3, 0, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_asm, FFT, 64, 2097152, 2, 0, 352, b8_i2, fma3, FMA3,
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 288, b8_i2, fma3, FMA3, 0, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_asm, FFT, 64, 131072, 2, 0, 352, b8_i2, fma3, FMA3,
AV_TX_INPLACE | FF_TX_PRESHUFFLE | FF_TX_ASM_CALL, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr_ns, FFT, 64, 2097152, 2, 0, 352, b8_i2, fma3, FMA3, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 352, b8_i2, fma3, FMA3, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft15, FFT, 15, 15, 15, 0, 320, factor_init, avx2, AVX2,
@@ -287,11 +287,11 @@ const FFTXCodelet * const ff_tx_codelet_list_float_x86[] = {
TX_DEF(fft15_ns, FFT, 15, 15, 15, 0, 384, factor_init, avx2, AVX2,
AV_TX_INPLACE | FF_TX_PRESHUFFLE, AV_CPU_FLAG_AVXSLOW),
TX_DEF(fft_sr, FFT, 64, 2097152, 2, 0, 320, b8_i2, avx2, AVX2, 0,
TX_DEF(fft_sr, FFT, 64, 131072, 2, 0, 320, b8_i2, avx2, AVX2, 0,
AV_CPU_FLAG_AVXSLOW | AV_CPU_FLAG_SLOW_GATHER),
TX_DEF(fft_sr_asm, FFT, 64, 2097152, 2, 0, 384, b8_i2, avx2, AVX2,
TX_DEF(fft_sr_asm, FFT, 64, 131072, 2, 0, 384, b8_i2, avx2, AVX2,
AV_TX_INPLACE | FF_TX_PRESHUFFLE | FF_TX_ASM_CALL, AV_CPU_FLAG_AVXSLOW | AV_CPU_FLAG_SLOW_GATHER),
TX_DEF(fft_sr_ns, FFT, 64, 2097152, 2, 0, 384, b8_i2, avx2, AVX2, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
TX_DEF(fft_sr_ns, FFT, 64, 131072, 2, 0, 384, b8_i2, avx2, AVX2, AV_TX_INPLACE | FF_TX_PRESHUFFLE,
AV_CPU_FLAG_AVXSLOW | AV_CPU_FLAG_SLOW_GATHER),
TX_DEF(fft_pfa_15xM, FFT, 60, TX_LEN_UNLIMITED, 15, 2, 320, fft_pfa_init, avx2, AVX2,