From 1a51f2915121275038677317c8bf61f1a78b590c Mon Sep 17 00:00:00 2001 From: Peter Harris Date: Thu, 11 Jan 2024 20:22:13 +0000 Subject: [PATCH] Update code for 4.7.0 release --- CMakeLists.txt | 4 ++-- Docs/ChangeLog-4x.md | 32 ++++++++++++++++++---------- Source/astcenc_compress_symbolic.cpp | 2 -- 3 files changed, 23 insertions(+), 15 deletions(-) diff --git a/CMakeLists.txt b/CMakeLists.txt index fb8958545..304471530 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -1,6 +1,6 @@ # SPDX-License-Identifier: Apache-2.0 # ---------------------------------------------------------------------------- -# Copyright 2020-2023 Arm Limited +# Copyright 2020-2024 Arm Limited # # Licensed under the Apache License, Version 2.0 (the "License"); you may not # use this file except in compliance with the License. You may obtain a copy @@ -24,7 +24,7 @@ if(MSVC) add_compile_options("/wd4324") # Disable structure was padded due to alignment specifier endif() -project(astcencoder VERSION 4.6.1) +project(astcencoder VERSION 4.7.0) set(CMAKE_CXX_STANDARD 14) set(CMAKE_CXX_STANDARD_REQUIRED ON) diff --git a/Docs/ChangeLog-4x.md b/Docs/ChangeLog-4x.md index 887f9c08b..4450a490b 100644 --- a/Docs/ChangeLog-4x.md +++ b/Docs/ChangeLog-4x.md @@ -9,17 +9,27 @@ clocked at 4.2 GHz, running `astcenc` using AVX2 and 6 threads. ## 4.7.0 -**Status:** TBD +**Status:** January 2024 -The 4.7.0 release is a maintenance release. +The 4.7.0 release is a major maintenance release, fixing rounding behavior in +the decompressor to match the Khronos specification. This fix includes the +addition of explicit support for optimizing for `decode_unorm8` rounding. + +Reminder - the codec library API is not designed to be binary compatible across +versions. We always recommend rebuilding your client-side code using the updated +`astcenc.h` header. * **General:** - * **Bug fix:** sRGB LDR decompression now uses correct `decode_fp16` decode - mode rounding rules for the alpha channel. - * **Bug fix:** Linear LDR decompression now uses correct `decode_unorm8` - decode mode rounding rules when writing to an 8-bit output image. - * **Bug fix:** Avoid using `alignas()` the reference C implementation, as the - default `alignas(16)` is narrower than the native alignment on some CPUs. + * **Bug fix:** sRGB LDR decompression now uses the correct endpoint expansion + method to create the 16-bit RGB endpoint colors, and removes the previous + correction code from the interpolation function. This bug could result in + LSB bit flips relative to the standard specification. + * **Bug fix:** Decompressing to an 8-bit per component output image now matches + the `decode_unorm8` extension rounding rules. This bug could result in + LSB bit flips relative to the standard specification. + * **Bug fix:** Code now avoids using `alignas()` in the reference C + implementation, as the default `alignas(16)` is narrower than the + native minimum alignment requirement on some CPUs. * **Feature:** Library configuration supports a new flag, `ASTCENC_FLG_USE_DECODE_UNORM8`. This flag indicates that the image will be used with the `decode_unorm8` decode mode. When set during compression @@ -30,7 +40,7 @@ The 4.7.0 release is a maintenance release. decode mode. This option will automatically be set for decompression (`-d*`) and trial (`-t*`) tool operation if the decompressed output image is stored to an 8-bit per component file format. This option must be set - maually for compression (`-c*`) tool operation, as the desired decode mode + manually for compression (`-c*`) tool operation, as the desired decode mode cannot be reliably determined. * **Feature:** Library configuration supports a new optional progress reporting callback to be specified. This is called during compression to @@ -49,7 +59,7 @@ large core count Windows systems. * **General:** * **Optimization:** Windows builds of the `astcenc` command line tool can now use more than 64 cores on large core count systems. This change doubled - command line performance for `-exhastive` compression when testing on an + command line performance for `-exhaustive` compression when testing on an 96 core/192 thread system. * **Feature:** Windows Arm64 native builds of the `astcenc` command line tool are now included in the prebuilt release binaries. @@ -385,4 +395,4 @@ Key for charts: - - - -_Copyright © 2022-2023, Arm Limited and contributors. All rights reserved._ +_Copyright © 2022-2024, Arm Limited and contributors. All rights reserved._ diff --git a/Source/astcenc_compress_symbolic.cpp b/Source/astcenc_compress_symbolic.cpp index b0890e1b0..98d249512 100644 --- a/Source/astcenc_compress_symbolic.cpp +++ b/Source/astcenc_compress_symbolic.cpp @@ -1237,8 +1237,6 @@ void compress_block( vfloat4 color_f32 = clamp(0.0f, 1.0f, blk.origin_texel) * 65535.0f; vint4 color_u16 = float_to_int_rtn(color_f32); store(color_u16, scb.constant_color); - - // TODO: Check this encodes correctly for decode_unorm8 } trace_add_data("exit", "quality hit");