Merge claude/project-thread-0izcgq (large window at qualities 3 to 9)

Put the q10/q11 variable region before the ring buffer (now the last
region), growing it (and moving the ring buffer) at the first
transform_io call to use a workbuf longer than workbuf_len's minimum.
Large window now also works at qualities 10 and 11.
This commit is contained in:
Claude committed 2026-10-27 04:46:52 +00:00
commit 7d58caf91c
11 files changed
+1664 -216

No files matched your search

+40 -18
View File
@@ -17,30 +17,37 @@
// The workbuf holds, in this order (see README.md's "Encoder Workbuf Layout"
// section, which compute_layout_offset mirrors):
// - the storage (the C code's GetBrotliStorage) for one metablock,
// - the ring buffer (the C code's RingBuffer.data_),
// - the hasher's memory (the C code's common->extra),
// - the commands (16 bytes each), and
// - the commands (16 bytes each),
// - at qualities 4 and above, the metablock split (see
// encode_metablock_greedy.wuffs), the literal context map, the
// EncodeContextMap symbols and the block encoders' depths and bits.
// EncodeContextMap symbols and the block encoders' depths and bits, and
// - the ring buffer (the C code's RingBuffer.data_).
// The workbuf layout's region indexes. LAYOUT_END's offset is the total
// length.
// The ring buffer is last, so that a workbuf shorter than workbuf_len works
// for short inputs (see transform_io's rb_short_workbuf check).
pri const LAYOUT_STORAGE : base.u32 = 0
pri const LAYOUT_RB : base.u32 = 1
pri const LAYOUT_HASH : base.u32 = 2
pri const LAYOUT_CMDS : base.u32 = 3
pri const LAYOUT_TYPES_0 : base.u32 = 4
pri const LAYOUT_LENGTHS_0 : base.u32 = 7
pri const LAYOUT_HISTO_0 : base.u32 = 10
pri const LAYOUT_COMB : base.u32 = 13
pri const LAYOUT_CMAP : base.u32 = 14
pri const LAYOUT_RLE : base.u32 = 15
pri const LAYOUT_BE_DEPTH_0 : base.u32 = 16
pri const LAYOUT_BE_BITS_0 : base.u32 = 19
pri const LAYOUT_VAR : base.u32 = 22
pri const LAYOUT_HASH : base.u32 = 1
pri const LAYOUT_CMDS : base.u32 = 2
pri const LAYOUT_TYPES_0 : base.u32 = 3
pri const LAYOUT_LENGTHS_0 : base.u32 = 6
pri const LAYOUT_HISTO_0 : base.u32 = 9
pri const LAYOUT_COMB : base.u32 = 12
pri const LAYOUT_CMAP : base.u32 = 13
pri const LAYOUT_RLE : base.u32 = 14
pri const LAYOUT_BE_DEPTH_0 : base.u32 = 15
pri const LAYOUT_BE_BITS_0 : base.u32 = 18
pri const LAYOUT_VAR : base.u32 = 21
pri const LAYOUT_RB : base.u32 = 22
pri const LAYOUT_END : base.u32 = 23
// RB_SHORT_SLACK is how many bytes past the input's end (in the ring buffer)
// a short workbuf must have: the C code reads at most 7 bytes past the
// input's end (its kSlackForEightByteHashingEverywhere), rounded up.
pri const RB_SHORT_SLACK : base.u64 = 16
// The C code's MAX_NUM_DELAYED_SYMBOLS (in quality.h).
pri const MAX_NUM_DELAYED_SYMBOLS : base.u64 = 0x2FFF
@@ -91,11 +98,13 @@ pri func encoder.max_metablock_size(lgwin: base.u32[..= 30], lgblock: base.u32[.
// hasher_total_size returns the sum of FN(HashMemAllocInBytes)'s
// alloc_size[i] for the hasher that ChooseHasher picks for the given
// quality, lgwin and size_hint.
// quality, lgwin and size_hint (including, for lgwin above 24, the
// large-window composite hashers' rolling hasher table).
pri func encoder.hasher_total_size(quality: base.u32[..= 11], lgwin: base.u32[..= 30], size_hint: base.u32) base.u64 {
var htype : base.u32
var bucket_bits : base.u32[..= 24]
var block_bits : base.u32[..= 16]
var rolling : base.u64
if args.quality >= 10 {
return (4 * H10_BUCKET_SIZE) + this.h10_alloc_size_1(lgwin: args.lgwin)
@@ -126,9 +135,21 @@ pri func encoder.hasher_total_size(quality: base.u32[..= 11], lgwin: base.u32[..
}
block_bits = args.quality - 1
}
return (this.hasher_alloc_size(htype: htype, bucket_bits: bucket_bits, block_bits: block_bits, i: 0) ~mod+
rolling = 0
if args.lgwin > 24 {
// The large-window composite hashers H35, H55 and H65 (see
// choose_hasher): HASHER_A plus the rolling hasher's table.
if (htype == 3) or (htype == 54) {
rolling = this.hasher_rolling_alloc_size()
} else if (htype == 6) or (htype == 68) {
htype = 6
rolling = this.hasher_rolling_alloc_size()
}
}
return ((this.hasher_alloc_size(htype: htype, bucket_bits: bucket_bits, block_bits: block_bits, i: 0) ~mod+
this.hasher_alloc_size(htype: htype, bucket_bits: bucket_bits, block_bits: block_bits, i: 1)) ~mod+
this.hasher_alloc_size(htype: htype, bucket_bits: bucket_bits, block_bits: block_bits, i: 2)
this.hasher_alloc_size(htype: htype, bucket_bits: bucket_bits, block_bits: block_bits, i: 2)) ~mod+
rolling
}
// hash_region_size returns the workbuf length reserved for the hasher's
@@ -279,6 +300,7 @@ pri func encoder.compute_layout!() {
this.mb_cmap_off = this.compute_layout_offset(quality: q, lgwin: lw, lgblock: lb, idx: LAYOUT_CMAP)
this.mb_rle_off = this.compute_layout_offset(quality: q, lgwin: lw, lgblock: lb, idx: LAYOUT_RLE)
this.var_off = this.compute_layout_offset(quality: q, lgwin: lw, lgblock: lb, idx: LAYOUT_VAR)
this.var_end = this.rb_off
this.workbuf_end = this.compute_layout_offset(quality: q, lgwin: lw, lgblock: lb, idx: LAYOUT_END)
// RingBufferSetup.