--- libavcodec/ffv1enc_vulkan.c | 1 + libavcodec/vulkan/ffv1_enc.comp | 7 ------- libavcodec/vulkan/ffv1_enc_setup.comp | 10 +++++----- libavcodec/vulkan/rangecoder.comp | 23 +++++++++++------------ 4 files changed, 17 insertions(+), 24 deletions(-)
diff --git a/libavcodec/ffv1enc_vulkan.c b/libavcodec/ffv1enc_vulkan.c index d78ba3aca8..956463e932 100644 --- a/libavcodec/ffv1enc_vulkan.c +++ b/libavcodec/ffv1enc_vulkan.c @@ -976,6 +976,7 @@ static int init_setup_shader(AVCodecContext *avctx, FFVkSPIRVCompiler *spv) av_bprintf(&shd->src, "#define MAX_QUANT_TABLES %i\n", MAX_QUANT_TABLES); av_bprintf(&shd->src, "#define MAX_CONTEXT_INPUTS %i\n", MAX_CONTEXT_INPUTS); av_bprintf(&shd->src, "#define MAX_QUANT_TABLE_SIZE %i\n", MAX_QUANT_TABLE_SIZE); + av_bprintf(&shd->src, "#define FULL_RENORM\n"); desc_set = (FFVulkanDescriptorSetBinding []) { { diff --git a/libavcodec/vulkan/ffv1_enc.comp b/libavcodec/vulkan/ffv1_enc.comp index 7f8c831efa..a3c22f7459 100644 --- a/libavcodec/vulkan/ffv1_enc.comp +++ b/libavcodec/vulkan/ffv1_enc.comp @@ -63,13 +63,6 @@ ivec2 get_pred(readonly uimage2D pred, ivec2 sp, ivec2 off, int comp, int sw, ui } #ifndef GOLOMB -void put_rac(inout RangeCoder c, uint64_t state, bool bit) -{ - put_rac_norenorm(c, state, bit); - if (c.range < 0x100) - renorm_encoder(c); -} - /* Note - only handles signed values */ void put_symbol(inout RangeCoder c, uint64_t state, int v) { diff --git a/libavcodec/vulkan/ffv1_enc_setup.comp b/libavcodec/vulkan/ffv1_enc_setup.comp index d395770ba8..6f21e47523 100644 --- a/libavcodec/vulkan/ffv1_enc_setup.comp +++ b/libavcodec/vulkan/ffv1_enc_setup.comp @@ -50,18 +50,18 @@ void init_slice(out SliceContext sc, const uint slice_idx) void put_usymbol(inout RangeCoder c, uint v) { bool is_nil = (v == 0); - put_rac(c, state[0], is_nil); + put_rac_direct(c, state[0], is_nil); if (is_nil) return; const int e = findMSB(v); for (int i = 0; i < e; i++) - put_rac(c, state[1 + min(i, 9)], true); - put_rac(c, state[1 + min(e, 9)], false); + put_rac_direct(c, state[1 + min(i, 9)], true); + put_rac_direct(c, state[1 + min(e, 9)], false); for (int i = e - 1; i >= 0; i--) - put_rac(c, state[22 + min(i, 9)], bool(bitfieldExtract(v, i, 1))); + put_rac_direct(c, state[22 + min(i, 9)], bool(bitfieldExtract(v, i, 1))); } void write_slice_header(inout SliceContext sc) @@ -83,7 +83,7 @@ void write_slice_header(inout SliceContext sc) put_usymbol(sc.c, sar.y); if (version >= 4) { - put_rac(sc.c, state[0], sc.slice_reset_contexts); + put_rac_direct(sc.c, state[0], sc.slice_reset_contexts); put_usymbol(sc.c, sc.slice_coding_mode); if (sc.slice_coding_mode != 1 && colorspace == 1) { put_usymbol(sc.c, sc.slice_rct_coef.y); diff --git a/libavcodec/vulkan/rangecoder.comp b/libavcodec/vulkan/rangecoder.comp index 1db42e1dc9..badc65293f 100644 --- a/libavcodec/vulkan/rangecoder.comp +++ b/libavcodec/vulkan/rangecoder.comp @@ -31,8 +31,9 @@ struct RangeCoder { uint8_t outstanding_byte; }; +#ifdef FULL_RENORM /* Full renorm version that can handle outstanding_byte == 0xFF */ -void renorm_encoder_full(inout RangeCoder c) +void renorm_encoder(inout RangeCoder c) { int bs_cnt = 0; u8buf bytestream = u8buf(c.bytestream); @@ -62,6 +63,8 @@ void renorm_encoder_full(inout RangeCoder c) c.low = bitfieldInsert(0, c.low, 8, 8); } +#else + /* Cannot deal with outstanding_byte == -1 in the name of speed */ void renorm_encoder(inout RangeCoder c) { @@ -90,8 +93,9 @@ void renorm_encoder(inout RangeCoder c) for (int i = 1; i < oc; i++) bs[i].v = fill; } +#endif -void put_rac_direct(inout RangeCoder c, uint8_t state, bool bit) +void put_rac_direct(inout RangeCoder c, inout uint8_t state, bool bit) { int range1 = uint16_t((c.range * state) >> 8); @@ -111,21 +115,16 @@ void put_rac_direct(inout RangeCoder c, uint8_t state, bool bit) } else { c.range = diff; } -} -void put_rac_norenorm(inout RangeCoder c, uint64_t state, bool bit) -{ - put_rac_direct(c, u8buf(state).v, bit); + if (c.range < 0x100) + renorm_encoder(c); - u8buf(state).v = zero_one_state[(uint(bit) << 8) + u8buf(state).v]; + state = zero_one_state[(uint(bit) << 8) + state]; } -void put_rac(inout RangeCoder c, inout uint8_t state, bool bit) +void put_rac(inout RangeCoder c, uint64_t state, bool bit) { - put_rac_direct(c, state, bit); - if (c.range < 0x100) - renorm_encoder_full(c); - state = zero_one_state[(uint(bit) << 8) + state]; + put_rac_direct(c, u8buf(state).v, bit); } /* Equiprobable bit */ -- 2.49.0.395.g12beb8f557c _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".