mirror of
https://gitlab.freedesktop.org/mesa/mesa.git
synced 2026-05-07 11:28:05 +02:00
Merge remote-tracking branch 'mesa-public/master' into vulkan
This commit is contained in:
Jason Ekstrand
commit
ff8895ba56
60 changed files with 975 additions and 1635 deletions
|
|
@ -51,7 +51,6 @@ noinst_HEADERS = \
|
|||
include/c99_alloca.h \
|
||||
include/c99_compat.h \
|
||||
include/c99_math.h \
|
||||
include/c99 \
|
||||
include/c11 \
|
||||
include/D3D9 \
|
||||
include/HaikuGL \
|
||||
|
|
|
|||
10
configure.ac
10
configure.ac
|
|
@ -305,8 +305,7 @@ if test "x$GCC" = xyes; then
|
|||
|
||||
# Flags to help ensure that certain portions of the code -- and only those
|
||||
# portions -- can be built with MSVC:
|
||||
# - src/util, src/gallium/auxiliary, and src/gallium/drivers/llvmpipe needs
|
||||
# to build with Windows SDK 7.0.7600, which bundles MSVC 2008
|
||||
# - src/util, src/gallium/auxiliary, rc/gallium/drivers/llvmpipe, and
|
||||
# - non-Linux/Posix OpenGL portions needs to build on MSVC 2013 (which
|
||||
# supports most of C99)
|
||||
# - the rest has no compiler compiler restrictions
|
||||
|
|
@ -323,9 +322,6 @@ if test "x$GCC" = xyes; then
|
|||
AC_MSG_RESULT([yes])],
|
||||
AC_MSG_RESULT([no]));
|
||||
CFLAGS="$save_CFLAGS"
|
||||
|
||||
MSVC2008_COMPAT_CFLAGS="$MSVC2013_COMPAT_CFLAGS -Werror=declaration-after-statement"
|
||||
MSVC2008_COMPAT_CXXFLAGS="$MSVC2013_COMPAT_CXXFLAGS"
|
||||
fi
|
||||
if test "x$GXX" = xyes; then
|
||||
CXXFLAGS="$CXXFLAGS -Wall"
|
||||
|
|
@ -353,8 +349,6 @@ fi
|
|||
|
||||
AC_SUBST([MSVC2013_COMPAT_CFLAGS])
|
||||
AC_SUBST([MSVC2013_COMPAT_CXXFLAGS])
|
||||
AC_SUBST([MSVC2008_COMPAT_CFLAGS])
|
||||
AC_SUBST([MSVC2008_COMPAT_CXXFLAGS])
|
||||
|
||||
dnl even if the compiler appears to support it, using visibility attributes isn't
|
||||
dnl going to do anything useful currently on cygwin apart from emit lots of warnings
|
||||
|
|
@ -2188,7 +2182,7 @@ radeon_llvm_check() {
|
|||
if test "x$enable_gallium_llvm" != "xyes"; then
|
||||
AC_MSG_ERROR([--enable-gallium-llvm is required when building $1])
|
||||
fi
|
||||
llvm_check_version_for "3" "5" "0" $1
|
||||
llvm_check_version_for "3" "6" "0" $1
|
||||
if test true && $LLVM_CONFIG --targets-built | grep -iqvw $amdgpu_llvm_target_name ; then
|
||||
AC_MSG_ERROR([LLVM $amdgpu_llvm_target_name not enabled in your LLVM build.])
|
||||
fi
|
||||
|
|
|
|||
|
|
@ -16,6 +16,12 @@
|
|||
|
||||
<h1>News</h1>
|
||||
|
||||
<h2>February 10, 2016</h2>
|
||||
<p>
|
||||
<a href="relnotes/11.1.2.html">Mesa 11.1.2</a> is released.
|
||||
This is a bug-fix release.
|
||||
</p>
|
||||
|
||||
<h2>January 22, 2016</h2>
|
||||
<p>
|
||||
<a href="relnotes/11.0.9.html">Mesa 11.0.9</a> is released.
|
||||
|
|
|
|||
|
|
@ -21,6 +21,7 @@ The release notes summarize what's new or changed in each Mesa release.
|
|||
</p>
|
||||
|
||||
<ul>
|
||||
<li><a href="relnotes/11.1.2.html">11.1.2 release notes</a>
|
||||
<li><a href="relnotes/11.0.9.html">11.0.9 release notes</a>
|
||||
<li><a href="relnotes/11.1.1.html">11.1.1 release notes</a>
|
||||
<li><a href="relnotes/11.0.8.html">11.0.8 release notes</a>
|
||||
|
|
|
|||
182
docs/relnotes/11.1.2.html
Normal file
182
docs/relnotes/11.1.2.html
Normal file
|
|
@ -0,0 +1,182 @@
|
|||
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta http-equiv="content-type" content="text/html; charset=utf-8">
|
||||
<title>Mesa Release Notes</title>
|
||||
<link rel="stylesheet" type="text/css" href="../mesa.css">
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<div class="header">
|
||||
<h1>The Mesa 3D Graphics Library</h1>
|
||||
</div>
|
||||
|
||||
<iframe src="../contents.html"></iframe>
|
||||
<div class="content">
|
||||
|
||||
<h1>Mesa 11.1.2 Release Notes / February 10, 2016</h1>
|
||||
|
||||
<p>
|
||||
Mesa 11.1.2 is a bug fix release which fixes bugs found since the 11.1.1 release.
|
||||
</p>
|
||||
<p>
|
||||
Mesa 11.1.2 implements the OpenGL 4.1 API, but the version reported by
|
||||
glGetString(GL_VERSION) or glGetIntegerv(GL_MAJOR_VERSION) /
|
||||
glGetIntegerv(GL_MINOR_VERSION) depends on the particular driver being used.
|
||||
Some drivers don't support all the features required in OpenGL 4.1. OpenGL
|
||||
4.1 is <strong>only</strong> available if requested at context creation
|
||||
because compatibility contexts are not supported.
|
||||
</p>
|
||||
|
||||
|
||||
<h2>SHA256 checksums</h2>
|
||||
<pre>
|
||||
ba0e7462b2936b86e6684c26fbb55519f8d9ad31d13a1c1e1afbe41e73466eea mesa-11.1.2.tar.gz
|
||||
8f72aead896b340ba0f7a4a474bfaf71681f5d675592aec1cb7ba698e319148b mesa-11.1.2.tar.xz
|
||||
</pre>
|
||||
|
||||
|
||||
<h2>New features</h2>
|
||||
<p>None</p>
|
||||
|
||||
<h2>Bug fixes</h2>
|
||||
|
||||
<p>This list is likely incomplete.</p>
|
||||
|
||||
<ul>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=91596">Bug 91596</a> - EGL_KHR_gl_colorspace (v2) causes problem with Android-x86 GUI</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93628">Bug 93628</a> - Exception: attempt to use unavailable module DRM when building MesaGL 11.1.0 on windows</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93648">Bug 93648</a> - Random lines being rendered when playing Dolphin (geometry shaders related, w/ apitrace)</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93650">Bug 93650</a> - GL_ARB_separate_shader_objects is buggy (PCSX2)</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93717">Bug 93717</a> - Meta mipmap generation can corrupt texture state</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93722">Bug 93722</a> - Segfault when compiling shader with a subroutine that takes a parameter</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93731">Bug 93731</a> - glUniformSubroutinesuiv segfaults when subroutine uniform is bound to a specific location</li>
|
||||
|
||||
<li><a href="https://bugs.freedesktop.org/show_bug.cgi?id=93761">Bug 93761</a> - A conditional discard in a fragment shader causes no depth writing at all</li>
|
||||
|
||||
</ul>
|
||||
|
||||
|
||||
<h2>Changes</h2>
|
||||
|
||||
<p>Ben Widawsky (1):</p>
|
||||
<ul>
|
||||
<li>i965/bxt: Fix conservative wm thread counts.</li>
|
||||
</ul>
|
||||
|
||||
<p>Dave Airlie (1):</p>
|
||||
<ul>
|
||||
<li>glsl: fix subroutine lowering reusing actual parmaters</li>
|
||||
</ul>
|
||||
|
||||
<p>Emil Velikov (6):</p>
|
||||
<ul>
|
||||
<li>docs: add sha256 checksums for 11.1.1</li>
|
||||
<li>cherry-ignore: drop the i965/kbl .num_slices patch</li>
|
||||
<li>i915: correctly parse/set the context flags</li>
|
||||
<li>targets/dri: android: use WHOLE static libraries</li>
|
||||
<li>egl/dri2: expose srgb configs when KHR_gl_colorspace is available</li>
|
||||
<li>Update version to 11.1.2</li>
|
||||
</ul>
|
||||
|
||||
<p>Eric Anholt (2):</p>
|
||||
<ul>
|
||||
<li>vc4: Don't record the seqno of a failed job submit.</li>
|
||||
<li>vc4: Throttle outstanding rendering after submission.</li>
|
||||
</ul>
|
||||
|
||||
<p>François Tigeot (1):</p>
|
||||
<ul>
|
||||
<li>gallium: Add DragonFly support</li>
|
||||
</ul>
|
||||
|
||||
<p>Grazvydas Ignotas (1):</p>
|
||||
<ul>
|
||||
<li>r600g: don't leak driver const buffers</li>
|
||||
</ul>
|
||||
|
||||
<p>Ian Romanick (2):</p>
|
||||
<ul>
|
||||
<li>meta/blit: Restore GL_DEPTH_STENCIL_TEXTURE_MODE state for GL_TEXTURE_RECTANGLE</li>
|
||||
<li>meta: Use internal functions to set texture parameters</li>
|
||||
</ul>
|
||||
|
||||
<p>Ilia Mirkin (6):</p>
|
||||
<ul>
|
||||
<li>st/mesa: use surface format to generate mipmaps when available</li>
|
||||
<li>glsl: always compute proper varying type, irrespective of varying packing</li>
|
||||
<li>nvc0: avoid crashing when there are holes in vertex array bindings</li>
|
||||
<li>nv50,nvc0: fix buffer clearing to respect engine alignment requirements</li>
|
||||
<li>nv50/ir: fix false global CSE on instructions with multiple defs</li>
|
||||
<li>st/mesa: treat a write as a read for range purposes</li>
|
||||
</ul>
|
||||
|
||||
<p>Jason Ekstrand (3):</p>
|
||||
<ul>
|
||||
<li>i965/vec4: Use UW type for multiply into accumulator on GEN8+</li>
|
||||
<li>i965/fs/generator: Take an actual shader stage rather than a string</li>
|
||||
<li>i965/fs: Always set channel 2 of texture headers in some stages</li>
|
||||
</ul>
|
||||
|
||||
<p>Jose Fonseca (2):</p>
|
||||
<ul>
|
||||
<li>scons: Conditionally use DRM module on pipe-loader.</li>
|
||||
<li>pipe-loader: Fix PATH_MAX define on MSVC.</li>
|
||||
</ul>
|
||||
|
||||
<p>Karol Herbst (1):</p>
|
||||
<ul>
|
||||
<li>nv50/ir: fix memory corruption when spilling and redoing RA</li>
|
||||
</ul>
|
||||
|
||||
<p>Kenneth Graunke (2):</p>
|
||||
<ul>
|
||||
<li>glsl: Make bitfield_insert/extract and bfi/bfm non-vectorizable.</li>
|
||||
<li>glsl: Allow implicit int -> uint conversions for bitwise operators (&, ^, |).</li>
|
||||
</ul>
|
||||
|
||||
<p>Leo Liu (2):</p>
|
||||
<ul>
|
||||
<li>vl: add zig zag scan for list 4x4</li>
|
||||
<li>st/omx/dec/h264: fix corruption when scaling matrix present flag set</li>
|
||||
</ul>
|
||||
|
||||
<p>Marek Olšák (1):</p>
|
||||
<ul>
|
||||
<li>radeonsi: don't miss changes to SPI_TMPRING_SIZE</li>
|
||||
</ul>
|
||||
|
||||
<p>Nicolai Hähnle (11):</p>
|
||||
<ul>
|
||||
<li>mesa/bufferobj: make _mesa_delete_buffer_object externally accessible</li>
|
||||
<li>st/mesa: use _mesa_delete_buffer_object</li>
|
||||
<li>radeon: use _mesa_delete_buffer_object</li>
|
||||
<li>i915: use _mesa_delete_buffer_object</li>
|
||||
<li>i965: use _mesa_delete_buffer_object</li>
|
||||
<li>util/u_pstipple.c: copy immediates during transformation</li>
|
||||
<li>radeonsi: extract the VGT_GS_MODE calculation into its own function</li>
|
||||
<li>radeonsi: ensure that VGT_GS_MODE is sent when necessary</li>
|
||||
<li>radeonsi: add DCC buffer for sampler views on new CS</li>
|
||||
<li>st/mesa: use the correct address generation functions in st_TexSubImage blit</li>
|
||||
<li>radeonsi: fix discard-only fragment shaders (11.1 version)</li>
|
||||
</ul>
|
||||
|
||||
<p>Timothy Arceri (4):</p>
|
||||
<ul>
|
||||
<li>glsl: fix segfault linking subroutine uniform with explicit location</li>
|
||||
<li>mesa: fix segfault in glUniformSubroutinesuiv()</li>
|
||||
<li>glsl: fix interface block error message</li>
|
||||
<li>glsl: create helper to remove outer vertex index array used by some stages</li>
|
||||
</ul>
|
||||
|
||||
|
||||
</div>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,305 +0,0 @@
|
|||
// ISO C9x compliant inttypes.h for Microsoft Visual Studio
|
||||
// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124
|
||||
//
|
||||
// Copyright (c) 2006 Alexander Chemeris
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without
|
||||
// modification, are permitted provided that the following conditions are met:
|
||||
//
|
||||
// 1. Redistributions of source code must retain the above copyright notice,
|
||||
// this list of conditions and the following disclaimer.
|
||||
//
|
||||
// 2. Redistributions in binary form must reproduce the above copyright
|
||||
// notice, this list of conditions and the following disclaimer in the
|
||||
// documentation and/or other materials provided with the distribution.
|
||||
//
|
||||
// 3. The name of the author may be used to endorse or promote products
|
||||
// derived from this software without specific prior written permission.
|
||||
//
|
||||
// THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
||||
// WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
||||
// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
||||
// EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
|
||||
// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
|
||||
// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
|
||||
// OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
|
||||
// ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
//
|
||||
///////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
#ifndef _MSC_VER // [
|
||||
#error "Use this header only with Microsoft Visual C++ compilers!"
|
||||
#endif // _MSC_VER ]
|
||||
|
||||
#ifndef _MSC_INTTYPES_H_ // [
|
||||
#define _MSC_INTTYPES_H_
|
||||
|
||||
#if _MSC_VER > 1000
|
||||
#pragma once
|
||||
#endif
|
||||
|
||||
#include "stdint.h"
|
||||
|
||||
// 7.8 Format conversion of integer types
|
||||
|
||||
typedef struct {
|
||||
intmax_t quot;
|
||||
intmax_t rem;
|
||||
} imaxdiv_t;
|
||||
|
||||
// 7.8.1 Macros for format specifiers
|
||||
|
||||
#if !defined(__cplusplus) || defined(__STDC_FORMAT_MACROS) // [ See footnote 185 at page 198
|
||||
|
||||
// The fprintf macros for signed integers are:
|
||||
#define PRId8 "d"
|
||||
#define PRIi8 "i"
|
||||
#define PRIdLEAST8 "d"
|
||||
#define PRIiLEAST8 "i"
|
||||
#define PRIdFAST8 "d"
|
||||
#define PRIiFAST8 "i"
|
||||
|
||||
#define PRId16 "hd"
|
||||
#define PRIi16 "hi"
|
||||
#define PRIdLEAST16 "hd"
|
||||
#define PRIiLEAST16 "hi"
|
||||
#define PRIdFAST16 "hd"
|
||||
#define PRIiFAST16 "hi"
|
||||
|
||||
#define PRId32 "I32d"
|
||||
#define PRIi32 "I32i"
|
||||
#define PRIdLEAST32 "I32d"
|
||||
#define PRIiLEAST32 "I32i"
|
||||
#define PRIdFAST32 "I32d"
|
||||
#define PRIiFAST32 "I32i"
|
||||
|
||||
#define PRId64 "I64d"
|
||||
#define PRIi64 "I64i"
|
||||
#define PRIdLEAST64 "I64d"
|
||||
#define PRIiLEAST64 "I64i"
|
||||
#define PRIdFAST64 "I64d"
|
||||
#define PRIiFAST64 "I64i"
|
||||
|
||||
#define PRIdMAX "I64d"
|
||||
#define PRIiMAX "I64i"
|
||||
|
||||
#define PRIdPTR "Id"
|
||||
#define PRIiPTR "Ii"
|
||||
|
||||
// The fprintf macros for unsigned integers are:
|
||||
#define PRIo8 "o"
|
||||
#define PRIu8 "u"
|
||||
#define PRIx8 "x"
|
||||
#define PRIX8 "X"
|
||||
#define PRIoLEAST8 "o"
|
||||
#define PRIuLEAST8 "u"
|
||||
#define PRIxLEAST8 "x"
|
||||
#define PRIXLEAST8 "X"
|
||||
#define PRIoFAST8 "o"
|
||||
#define PRIuFAST8 "u"
|
||||
#define PRIxFAST8 "x"
|
||||
#define PRIXFAST8 "X"
|
||||
|
||||
#define PRIo16 "ho"
|
||||
#define PRIu16 "hu"
|
||||
#define PRIx16 "hx"
|
||||
#define PRIX16 "hX"
|
||||
#define PRIoLEAST16 "ho"
|
||||
#define PRIuLEAST16 "hu"
|
||||
#define PRIxLEAST16 "hx"
|
||||
#define PRIXLEAST16 "hX"
|
||||
#define PRIoFAST16 "ho"
|
||||
#define PRIuFAST16 "hu"
|
||||
#define PRIxFAST16 "hx"
|
||||
#define PRIXFAST16 "hX"
|
||||
|
||||
#define PRIo32 "I32o"
|
||||
#define PRIu32 "I32u"
|
||||
#define PRIx32 "I32x"
|
||||
#define PRIX32 "I32X"
|
||||
#define PRIoLEAST32 "I32o"
|
||||
#define PRIuLEAST32 "I32u"
|
||||
#define PRIxLEAST32 "I32x"
|
||||
#define PRIXLEAST32 "I32X"
|
||||
#define PRIoFAST32 "I32o"
|
||||
#define PRIuFAST32 "I32u"
|
||||
#define PRIxFAST32 "I32x"
|
||||
#define PRIXFAST32 "I32X"
|
||||
|
||||
#define PRIo64 "I64o"
|
||||
#define PRIu64 "I64u"
|
||||
#define PRIx64 "I64x"
|
||||
#define PRIX64 "I64X"
|
||||
#define PRIoLEAST64 "I64o"
|
||||
#define PRIuLEAST64 "I64u"
|
||||
#define PRIxLEAST64 "I64x"
|
||||
#define PRIXLEAST64 "I64X"
|
||||
#define PRIoFAST64 "I64o"
|
||||
#define PRIuFAST64 "I64u"
|
||||
#define PRIxFAST64 "I64x"
|
||||
#define PRIXFAST64 "I64X"
|
||||
|
||||
#define PRIoMAX "I64o"
|
||||
#define PRIuMAX "I64u"
|
||||
#define PRIxMAX "I64x"
|
||||
#define PRIXMAX "I64X"
|
||||
|
||||
#define PRIoPTR "Io"
|
||||
#define PRIuPTR "Iu"
|
||||
#define PRIxPTR "Ix"
|
||||
#define PRIXPTR "IX"
|
||||
|
||||
// The fscanf macros for signed integers are:
|
||||
#define SCNd8 "d"
|
||||
#define SCNi8 "i"
|
||||
#define SCNdLEAST8 "d"
|
||||
#define SCNiLEAST8 "i"
|
||||
#define SCNdFAST8 "d"
|
||||
#define SCNiFAST8 "i"
|
||||
|
||||
#define SCNd16 "hd"
|
||||
#define SCNi16 "hi"
|
||||
#define SCNdLEAST16 "hd"
|
||||
#define SCNiLEAST16 "hi"
|
||||
#define SCNdFAST16 "hd"
|
||||
#define SCNiFAST16 "hi"
|
||||
|
||||
#define SCNd32 "ld"
|
||||
#define SCNi32 "li"
|
||||
#define SCNdLEAST32 "ld"
|
||||
#define SCNiLEAST32 "li"
|
||||
#define SCNdFAST32 "ld"
|
||||
#define SCNiFAST32 "li"
|
||||
|
||||
#define SCNd64 "I64d"
|
||||
#define SCNi64 "I64i"
|
||||
#define SCNdLEAST64 "I64d"
|
||||
#define SCNiLEAST64 "I64i"
|
||||
#define SCNdFAST64 "I64d"
|
||||
#define SCNiFAST64 "I64i"
|
||||
|
||||
#define SCNdMAX "I64d"
|
||||
#define SCNiMAX "I64i"
|
||||
|
||||
#ifdef _WIN64 // [
|
||||
# define SCNdPTR "I64d"
|
||||
# define SCNiPTR "I64i"
|
||||
#else // _WIN64 ][
|
||||
# define SCNdPTR "ld"
|
||||
# define SCNiPTR "li"
|
||||
#endif // _WIN64 ]
|
||||
|
||||
// The fscanf macros for unsigned integers are:
|
||||
#define SCNo8 "o"
|
||||
#define SCNu8 "u"
|
||||
#define SCNx8 "x"
|
||||
#define SCNX8 "X"
|
||||
#define SCNoLEAST8 "o"
|
||||
#define SCNuLEAST8 "u"
|
||||
#define SCNxLEAST8 "x"
|
||||
#define SCNXLEAST8 "X"
|
||||
#define SCNoFAST8 "o"
|
||||
#define SCNuFAST8 "u"
|
||||
#define SCNxFAST8 "x"
|
||||
#define SCNXFAST8 "X"
|
||||
|
||||
#define SCNo16 "ho"
|
||||
#define SCNu16 "hu"
|
||||
#define SCNx16 "hx"
|
||||
#define SCNX16 "hX"
|
||||
#define SCNoLEAST16 "ho"
|
||||
#define SCNuLEAST16 "hu"
|
||||
#define SCNxLEAST16 "hx"
|
||||
#define SCNXLEAST16 "hX"
|
||||
#define SCNoFAST16 "ho"
|
||||
#define SCNuFAST16 "hu"
|
||||
#define SCNxFAST16 "hx"
|
||||
#define SCNXFAST16 "hX"
|
||||
|
||||
#define SCNo32 "lo"
|
||||
#define SCNu32 "lu"
|
||||
#define SCNx32 "lx"
|
||||
#define SCNX32 "lX"
|
||||
#define SCNoLEAST32 "lo"
|
||||
#define SCNuLEAST32 "lu"
|
||||
#define SCNxLEAST32 "lx"
|
||||
#define SCNXLEAST32 "lX"
|
||||
#define SCNoFAST32 "lo"
|
||||
#define SCNuFAST32 "lu"
|
||||
#define SCNxFAST32 "lx"
|
||||
#define SCNXFAST32 "lX"
|
||||
|
||||
#define SCNo64 "I64o"
|
||||
#define SCNu64 "I64u"
|
||||
#define SCNx64 "I64x"
|
||||
#define SCNX64 "I64X"
|
||||
#define SCNoLEAST64 "I64o"
|
||||
#define SCNuLEAST64 "I64u"
|
||||
#define SCNxLEAST64 "I64x"
|
||||
#define SCNXLEAST64 "I64X"
|
||||
#define SCNoFAST64 "I64o"
|
||||
#define SCNuFAST64 "I64u"
|
||||
#define SCNxFAST64 "I64x"
|
||||
#define SCNXFAST64 "I64X"
|
||||
|
||||
#define SCNoMAX "I64o"
|
||||
#define SCNuMAX "I64u"
|
||||
#define SCNxMAX "I64x"
|
||||
#define SCNXMAX "I64X"
|
||||
|
||||
#ifdef _WIN64 // [
|
||||
# define SCNoPTR "I64o"
|
||||
# define SCNuPTR "I64u"
|
||||
# define SCNxPTR "I64x"
|
||||
# define SCNXPTR "I64X"
|
||||
#else // _WIN64 ][
|
||||
# define SCNoPTR "lo"
|
||||
# define SCNuPTR "lu"
|
||||
# define SCNxPTR "lx"
|
||||
# define SCNXPTR "lX"
|
||||
#endif // _WIN64 ]
|
||||
|
||||
#endif // __STDC_FORMAT_MACROS ]
|
||||
|
||||
// 7.8.2 Functions for greatest-width integer types
|
||||
|
||||
// 7.8.2.1 The imaxabs function
|
||||
#define imaxabs _abs64
|
||||
|
||||
// 7.8.2.2 The imaxdiv function
|
||||
|
||||
// This is modified version of div() function from Microsoft's div.c found
|
||||
// in %MSVC.NET%\crt\src\div.c
|
||||
#ifdef STATIC_IMAXDIV // [
|
||||
static
|
||||
#else // STATIC_IMAXDIV ][
|
||||
_inline
|
||||
#endif // STATIC_IMAXDIV ]
|
||||
imaxdiv_t __cdecl imaxdiv(intmax_t numer, intmax_t denom)
|
||||
{
|
||||
imaxdiv_t result;
|
||||
|
||||
result.quot = numer / denom;
|
||||
result.rem = numer % denom;
|
||||
|
||||
if (numer < 0 && result.rem > 0) {
|
||||
// did division wrong; must fix up
|
||||
++result.quot;
|
||||
result.rem -= denom;
|
||||
}
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
// 7.8.2.3 The strtoimax and strtoumax functions
|
||||
#define strtoimax _strtoi64
|
||||
#define strtoumax _strtoui64
|
||||
|
||||
// 7.8.2.4 The wcstoimax and wcstoumax functions
|
||||
#define wcstoimax _wcstoi64
|
||||
#define wcstoumax _wcstoui64
|
||||
|
||||
|
||||
#endif // _MSC_INTTYPES_H_ ]
|
||||
|
|
@ -1,46 +0,0 @@
|
|||
/**************************************************************************
|
||||
*
|
||||
* Copyright 2007-2010 VMware, Inc.
|
||||
* All Rights Reserved.
|
||||
*
|
||||
* Permission is hereby granted, free of charge, to any person obtaining a
|
||||
* copy of this software and associated documentation files (the
|
||||
* "Software"), to deal in the Software without restriction, including
|
||||
* without limitation the rights to use, copy, modify, merge, publish,
|
||||
* distribute, sub license, and/or sell copies of the Software, and to
|
||||
* permit persons to whom the Software is furnished to do so, subject to
|
||||
* the following conditions:
|
||||
*
|
||||
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
|
||||
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
|
||||
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
|
||||
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
|
||||
* USE OR OTHER DEALINGS IN THE SOFTWARE.
|
||||
*
|
||||
* The above copyright notice and this permission notice (including the
|
||||
* next paragraph) shall be included in all copies or substantial portions
|
||||
* of the Software.
|
||||
*
|
||||
**************************************************************************/
|
||||
|
||||
#ifndef _STDBOOL_H_
|
||||
#define _STDBOOL_H_
|
||||
|
||||
#ifndef __cplusplus
|
||||
|
||||
#define false 0
|
||||
#define true 1
|
||||
#define bool _Bool
|
||||
|
||||
/* For compilers that don't have the builtin _Bool type. */
|
||||
#if (defined(_MSC_VER) && _MSC_VER < 1800)
|
||||
typedef unsigned char _Bool;
|
||||
#endif
|
||||
|
||||
#endif /* !__cplusplus */
|
||||
|
||||
#define __bool_true_false_are_defined 1
|
||||
|
||||
#endif /* !_STDBOOL_H_ */
|
||||
|
|
@ -1,247 +0,0 @@
|
|||
// ISO C9x compliant stdint.h for Microsoft Visual Studio
|
||||
// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124
|
||||
//
|
||||
// Copyright (c) 2006-2008 Alexander Chemeris
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without
|
||||
// modification, are permitted provided that the following conditions are met:
|
||||
//
|
||||
// 1. Redistributions of source code must retain the above copyright notice,
|
||||
// this list of conditions and the following disclaimer.
|
||||
//
|
||||
// 2. Redistributions in binary form must reproduce the above copyright
|
||||
// notice, this list of conditions and the following disclaimer in the
|
||||
// documentation and/or other materials provided with the distribution.
|
||||
//
|
||||
// 3. The name of the author may be used to endorse or promote products
|
||||
// derived from this software without specific prior written permission.
|
||||
//
|
||||
// THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
|
||||
// WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
|
||||
// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
|
||||
// EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
|
||||
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
|
||||
// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
|
||||
// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
|
||||
// OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
|
||||
// ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
//
|
||||
///////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
#ifndef _MSC_VER // [
|
||||
#error "Use this header only with Microsoft Visual C++ compilers!"
|
||||
#endif // _MSC_VER ]
|
||||
|
||||
#ifndef _MSC_STDINT_H_ // [
|
||||
#define _MSC_STDINT_H_
|
||||
|
||||
#if _MSC_VER > 1000
|
||||
#pragma once
|
||||
#endif
|
||||
|
||||
#include <limits.h>
|
||||
|
||||
// For Visual Studio 6 in C++ mode and for many Visual Studio versions when
|
||||
// compiling for ARM we should wrap <wchar.h> include with 'extern "C++" {}'
|
||||
// or compiler give many errors like this:
|
||||
// error C2733: second C linkage of overloaded function 'wmemchr' not allowed
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
# include <wchar.h>
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
// Define _W64 macros to mark types changing their size, like intptr_t.
|
||||
#ifndef _W64
|
||||
# if !defined(__midl) && (defined(_X86_) || defined(_M_IX86)) && _MSC_VER >= 1300
|
||||
# define _W64 __w64
|
||||
# else
|
||||
# define _W64
|
||||
# endif
|
||||
#endif
|
||||
|
||||
|
||||
// 7.18.1 Integer types
|
||||
|
||||
// 7.18.1.1 Exact-width integer types
|
||||
|
||||
// Visual Studio 6 and Embedded Visual C++ 4 doesn't
|
||||
// realize that, e.g. char has the same size as __int8
|
||||
// so we give up on __intX for them.
|
||||
#if (_MSC_VER < 1300)
|
||||
typedef signed char int8_t;
|
||||
typedef signed short int16_t;
|
||||
typedef signed int int32_t;
|
||||
typedef unsigned char uint8_t;
|
||||
typedef unsigned short uint16_t;
|
||||
typedef unsigned int uint32_t;
|
||||
#else
|
||||
typedef signed __int8 int8_t;
|
||||
typedef signed __int16 int16_t;
|
||||
typedef signed __int32 int32_t;
|
||||
typedef unsigned __int8 uint8_t;
|
||||
typedef unsigned __int16 uint16_t;
|
||||
typedef unsigned __int32 uint32_t;
|
||||
#endif
|
||||
typedef signed __int64 int64_t;
|
||||
typedef unsigned __int64 uint64_t;
|
||||
|
||||
|
||||
// 7.18.1.2 Minimum-width integer types
|
||||
typedef int8_t int_least8_t;
|
||||
typedef int16_t int_least16_t;
|
||||
typedef int32_t int_least32_t;
|
||||
typedef int64_t int_least64_t;
|
||||
typedef uint8_t uint_least8_t;
|
||||
typedef uint16_t uint_least16_t;
|
||||
typedef uint32_t uint_least32_t;
|
||||
typedef uint64_t uint_least64_t;
|
||||
|
||||
// 7.18.1.3 Fastest minimum-width integer types
|
||||
typedef int8_t int_fast8_t;
|
||||
typedef int16_t int_fast16_t;
|
||||
typedef int32_t int_fast32_t;
|
||||
typedef int64_t int_fast64_t;
|
||||
typedef uint8_t uint_fast8_t;
|
||||
typedef uint16_t uint_fast16_t;
|
||||
typedef uint32_t uint_fast32_t;
|
||||
typedef uint64_t uint_fast64_t;
|
||||
|
||||
// 7.18.1.4 Integer types capable of holding object pointers
|
||||
#ifdef _WIN64 // [
|
||||
typedef signed __int64 intptr_t;
|
||||
typedef unsigned __int64 uintptr_t;
|
||||
#else // _WIN64 ][
|
||||
typedef _W64 signed int intptr_t;
|
||||
typedef _W64 unsigned int uintptr_t;
|
||||
#endif // _WIN64 ]
|
||||
|
||||
// 7.18.1.5 Greatest-width integer types
|
||||
typedef int64_t intmax_t;
|
||||
typedef uint64_t uintmax_t;
|
||||
|
||||
|
||||
// 7.18.2 Limits of specified-width integer types
|
||||
|
||||
#if !defined(__cplusplus) || defined(__STDC_LIMIT_MACROS) // [ See footnote 220 at page 257 and footnote 221 at page 259
|
||||
|
||||
// 7.18.2.1 Limits of exact-width integer types
|
||||
#define INT8_MIN ((int8_t)_I8_MIN)
|
||||
#define INT8_MAX _I8_MAX
|
||||
#define INT16_MIN ((int16_t)_I16_MIN)
|
||||
#define INT16_MAX _I16_MAX
|
||||
#define INT32_MIN ((int32_t)_I32_MIN)
|
||||
#define INT32_MAX _I32_MAX
|
||||
#define INT64_MIN ((int64_t)_I64_MIN)
|
||||
#define INT64_MAX _I64_MAX
|
||||
#define UINT8_MAX _UI8_MAX
|
||||
#define UINT16_MAX _UI16_MAX
|
||||
#define UINT32_MAX _UI32_MAX
|
||||
#define UINT64_MAX _UI64_MAX
|
||||
|
||||
// 7.18.2.2 Limits of minimum-width integer types
|
||||
#define INT_LEAST8_MIN INT8_MIN
|
||||
#define INT_LEAST8_MAX INT8_MAX
|
||||
#define INT_LEAST16_MIN INT16_MIN
|
||||
#define INT_LEAST16_MAX INT16_MAX
|
||||
#define INT_LEAST32_MIN INT32_MIN
|
||||
#define INT_LEAST32_MAX INT32_MAX
|
||||
#define INT_LEAST64_MIN INT64_MIN
|
||||
#define INT_LEAST64_MAX INT64_MAX
|
||||
#define UINT_LEAST8_MAX UINT8_MAX
|
||||
#define UINT_LEAST16_MAX UINT16_MAX
|
||||
#define UINT_LEAST32_MAX UINT32_MAX
|
||||
#define UINT_LEAST64_MAX UINT64_MAX
|
||||
|
||||
// 7.18.2.3 Limits of fastest minimum-width integer types
|
||||
#define INT_FAST8_MIN INT8_MIN
|
||||
#define INT_FAST8_MAX INT8_MAX
|
||||
#define INT_FAST16_MIN INT16_MIN
|
||||
#define INT_FAST16_MAX INT16_MAX
|
||||
#define INT_FAST32_MIN INT32_MIN
|
||||
#define INT_FAST32_MAX INT32_MAX
|
||||
#define INT_FAST64_MIN INT64_MIN
|
||||
#define INT_FAST64_MAX INT64_MAX
|
||||
#define UINT_FAST8_MAX UINT8_MAX
|
||||
#define UINT_FAST16_MAX UINT16_MAX
|
||||
#define UINT_FAST32_MAX UINT32_MAX
|
||||
#define UINT_FAST64_MAX UINT64_MAX
|
||||
|
||||
// 7.18.2.4 Limits of integer types capable of holding object pointers
|
||||
#ifdef _WIN64 // [
|
||||
# define INTPTR_MIN INT64_MIN
|
||||
# define INTPTR_MAX INT64_MAX
|
||||
# define UINTPTR_MAX UINT64_MAX
|
||||
#else // _WIN64 ][
|
||||
# define INTPTR_MIN INT32_MIN
|
||||
# define INTPTR_MAX INT32_MAX
|
||||
# define UINTPTR_MAX UINT32_MAX
|
||||
#endif // _WIN64 ]
|
||||
|
||||
// 7.18.2.5 Limits of greatest-width integer types
|
||||
#define INTMAX_MIN INT64_MIN
|
||||
#define INTMAX_MAX INT64_MAX
|
||||
#define UINTMAX_MAX UINT64_MAX
|
||||
|
||||
// 7.18.3 Limits of other integer types
|
||||
|
||||
#ifdef _WIN64 // [
|
||||
# define PTRDIFF_MIN _I64_MIN
|
||||
# define PTRDIFF_MAX _I64_MAX
|
||||
#else // _WIN64 ][
|
||||
# define PTRDIFF_MIN _I32_MIN
|
||||
# define PTRDIFF_MAX _I32_MAX
|
||||
#endif // _WIN64 ]
|
||||
|
||||
#define SIG_ATOMIC_MIN INT_MIN
|
||||
#define SIG_ATOMIC_MAX INT_MAX
|
||||
|
||||
#ifndef SIZE_MAX // [
|
||||
# ifdef _WIN64 // [
|
||||
# define SIZE_MAX _UI64_MAX
|
||||
# else // _WIN64 ][
|
||||
# define SIZE_MAX _UI32_MAX
|
||||
# endif // _WIN64 ]
|
||||
#endif // SIZE_MAX ]
|
||||
|
||||
// WCHAR_MIN and WCHAR_MAX are also defined in <wchar.h>
|
||||
#ifndef WCHAR_MIN // [
|
||||
# define WCHAR_MIN 0
|
||||
#endif // WCHAR_MIN ]
|
||||
#ifndef WCHAR_MAX // [
|
||||
# define WCHAR_MAX _UI16_MAX
|
||||
#endif // WCHAR_MAX ]
|
||||
|
||||
#define WINT_MIN 0
|
||||
#define WINT_MAX _UI16_MAX
|
||||
|
||||
#endif // __STDC_LIMIT_MACROS ]
|
||||
|
||||
|
||||
// 7.18.4 Limits of other integer types
|
||||
|
||||
#if !defined(__cplusplus) || defined(__STDC_CONSTANT_MACROS) // [ See footnote 224 at page 260
|
||||
|
||||
// 7.18.4.1 Macros for minimum-width integer constants
|
||||
|
||||
#define INT8_C(val) val##i8
|
||||
#define INT16_C(val) val##i16
|
||||
#define INT32_C(val) val##i32
|
||||
#define INT64_C(val) val##i64
|
||||
|
||||
#define UINT8_C(val) val##ui8
|
||||
#define UINT16_C(val) val##ui16
|
||||
#define UINT32_C(val) val##ui32
|
||||
#define UINT64_C(val) val##ui64
|
||||
|
||||
// 7.18.4.2 Macros for greatest-width integer constants
|
||||
#define INTMAX_C INT64_C
|
||||
#define UINTMAX_C UINT64_C
|
||||
|
||||
#endif // __STDC_CONSTANT_MACROS ]
|
||||
|
||||
|
||||
#endif // _MSC_STDINT_H_ ]
|
||||
|
|
@ -36,17 +36,17 @@
|
|||
*/
|
||||
#if defined(_MSC_VER)
|
||||
|
||||
# if _MSC_VER < 1500
|
||||
# error "Microsoft Visual Studio 2008 or higher required"
|
||||
# if _MSC_VER < 1800
|
||||
# error "Microsoft Visual Studio 2013 or higher required"
|
||||
# endif
|
||||
|
||||
/*
|
||||
* Visual Studio 2012 will complain if we define the `inline` keyword, but
|
||||
* Visual Studio will complain if we define the `inline` keyword, but
|
||||
* actually it only supports the keyword on C++.
|
||||
*
|
||||
* To avoid this the _ALLOW_KEYWORD_MACROS must be set.
|
||||
*/
|
||||
# if (_MSC_VER >= 1700) && !defined(_ALLOW_KEYWORD_MACROS)
|
||||
# if !defined(_ALLOW_KEYWORD_MACROS)
|
||||
# define _ALLOW_KEYWORD_MACROS
|
||||
# endif
|
||||
|
||||
|
|
|
|||
|
|
@ -38,55 +38,16 @@
|
|||
#include "c99_compat.h"
|
||||
|
||||
|
||||
#if defined(_MSC_VER)
|
||||
|
||||
/* This is to ensure that we get M_PI, etc. definitions */
|
||||
#if !defined(_USE_MATH_DEFINES)
|
||||
#if defined(_MSC_VER) && !defined(_USE_MATH_DEFINES)
|
||||
#error _USE_MATH_DEFINES define required when building with MSVC
|
||||
#endif
|
||||
|
||||
#if _MSC_VER < 1800
|
||||
#define isfinite(x) _finite((double)(x))
|
||||
#define isnan(x) _isnan((double)(x))
|
||||
#endif /* _MSC_VER < 1800 */
|
||||
|
||||
#if _MSC_VER < 1800
|
||||
static inline double log2( double x )
|
||||
{
|
||||
const double invln2 = 1.442695041;
|
||||
return log( x ) * invln2;
|
||||
}
|
||||
|
||||
static inline double
|
||||
round(double x)
|
||||
{
|
||||
return x >= 0.0 ? floor(x + 0.5) : ceil(x - 0.5);
|
||||
}
|
||||
|
||||
static inline float
|
||||
roundf(float x)
|
||||
{
|
||||
return x >= 0.0f ? floorf(x + 0.5f) : ceilf(x - 0.5f);
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifndef INFINITY
|
||||
#include <float.h> // DBL_MAX
|
||||
#define INFINITY (DBL_MAX + DBL_MAX)
|
||||
#endif
|
||||
|
||||
#ifndef NAN
|
||||
#define NAN (INFINITY - INFINITY)
|
||||
#endif
|
||||
|
||||
#endif /* _MSC_VER */
|
||||
|
||||
|
||||
#if (defined(_MSC_VER) && _MSC_VER < 1800) || \
|
||||
(!defined(_MSC_VER) && \
|
||||
__STDC_VERSION__ < 199901L && \
|
||||
(!defined(_XOPEN_SOURCE) || _XOPEN_SOURCE < 600) && \
|
||||
!defined(__cplusplus))
|
||||
#if !defined(_MSC_VER) && \
|
||||
__STDC_VERSION__ < 199901L && \
|
||||
(!defined(_XOPEN_SOURCE) || _XOPEN_SOURCE < 600) && \
|
||||
!defined(__cplusplus)
|
||||
|
||||
static inline long int
|
||||
lrint(double d)
|
||||
|
|
|
|||
|
|
@ -94,16 +94,8 @@ def msvc2013_compat(env):
|
|||
'-Werror=pointer-arith',
|
||||
])
|
||||
|
||||
def msvc2008_compat(env):
|
||||
msvc2013_compat(env)
|
||||
if env['gcc']:
|
||||
env.Append(CFLAGS = [
|
||||
'-Werror=declaration-after-statement',
|
||||
])
|
||||
|
||||
def createMSVCCompatMethods(env):
|
||||
env.AddMethod(msvc2013_compat, 'MSVC2013Compat')
|
||||
env.AddMethod(msvc2008_compat, 'MSVC2008Compat')
|
||||
|
||||
|
||||
def num_jobs():
|
||||
|
|
@ -479,20 +471,12 @@ def generate(env):
|
|||
# See also:
|
||||
# - http://msdn.microsoft.com/en-us/library/19z1t1wy.aspx
|
||||
# - cl /?
|
||||
if 'MSVC_VERSION' not in env or distutils.version.LooseVersion(env['MSVC_VERSION']) < distutils.version.LooseVersion('12.0'):
|
||||
# Use bundled stdbool.h and stdint.h headers for older MSVC
|
||||
# versions. stdint.h was introduced in MSVC 2010, but stdbool.h
|
||||
# was only introduced in MSVC 2013.
|
||||
top_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
|
||||
env.Append(CPPPATH = [os.path.join(top_dir, 'include/c99')])
|
||||
if env['build'] == 'debug':
|
||||
ccflags += [
|
||||
'/Od', # disable optimizations
|
||||
'/Oi', # enable intrinsic functions
|
||||
]
|
||||
else:
|
||||
if 'MSVC_VERSION' in env and distutils.version.LooseVersion(env['MSVC_VERSION']) < distutils.version.LooseVersion('11.0'):
|
||||
print 'scons: warning: Visual Studio versions prior to 2012 are known to produce incorrect code when optimizations are enabled ( https://bugs.freedesktop.org/show_bug.cgi?id=58718 )'
|
||||
ccflags += [
|
||||
'/O2', # optimize for speed
|
||||
]
|
||||
|
|
|
|||
|
|
@ -6268,13 +6268,24 @@ ast_process_struct_or_iface_block_members(exec_list *instructions,
|
|||
|
||||
decl_list->type->specifier->hir(instructions, state);
|
||||
|
||||
/* Section 10.9 of the GLSL ES 1.00 specification states that
|
||||
* embedded structure definitions have been removed from the language.
|
||||
/* Section 4.1.8 (Structures) of the GLSL 1.10 spec says:
|
||||
*
|
||||
* "Anonymous structures are not supported; so embedded structures
|
||||
* must have a declarator. A name given to an embedded struct is
|
||||
* scoped at the same level as the struct it is embedded in."
|
||||
*
|
||||
* The same section of the GLSL 1.20 spec says:
|
||||
*
|
||||
* "Anonymous structures are not supported. Embedded structures are
|
||||
* not supported."
|
||||
*
|
||||
* The GLSL ES 1.00 and 3.00 specs have similar langauge. So, we allow
|
||||
* embedded structures in 1.10 only.
|
||||
*/
|
||||
if (state->es_shader && decl_list->type->specifier->structure != NULL) {
|
||||
_mesa_glsl_error(&loc, state, "embedded structure definitions are "
|
||||
"not allowed in GLSL ES 1.00");
|
||||
}
|
||||
if (state->language_version != 110 &&
|
||||
decl_list->type->specifier->structure != NULL)
|
||||
_mesa_glsl_error(&loc, state,
|
||||
"embedded structure declarations are not allowed");
|
||||
|
||||
const glsl_type *decl_type =
|
||||
decl_list->type->glsl_type(& type_name, state);
|
||||
|
|
@ -6293,30 +6304,28 @@ ast_process_struct_or_iface_block_members(exec_list *instructions,
|
|||
*/
|
||||
assert(decl_type);
|
||||
|
||||
if (is_interface && decl_type->contains_opaque()) {
|
||||
_mesa_glsl_error(&loc, state,
|
||||
"uniform/buffer in non-default interface block contains "
|
||||
"opaque variable");
|
||||
}
|
||||
if (is_interface) {
|
||||
if (decl_type->contains_opaque()) {
|
||||
_mesa_glsl_error(&loc, state, "uniform/buffer in non-default "
|
||||
"interface block contains opaque variable");
|
||||
}
|
||||
} else {
|
||||
if (decl_type->contains_atomic()) {
|
||||
/* From section 4.1.7.3 of the GLSL 4.40 spec:
|
||||
*
|
||||
* "Members of structures cannot be declared as atomic counter
|
||||
* types."
|
||||
*/
|
||||
_mesa_glsl_error(&loc, state, "atomic counter in structure");
|
||||
}
|
||||
|
||||
if (decl_type->contains_atomic()) {
|
||||
/* From section 4.1.7.3 of the GLSL 4.40 spec:
|
||||
*
|
||||
* "Members of structures cannot be declared as atomic counter
|
||||
* types."
|
||||
*/
|
||||
_mesa_glsl_error(&loc, state, "atomic counter in structure, "
|
||||
"shader storage block or uniform block");
|
||||
}
|
||||
|
||||
if (decl_type->contains_image()) {
|
||||
/* FINISHME: Same problem as with atomic counters.
|
||||
* FINISHME: Request clarification from Khronos and add
|
||||
* FINISHME: spec quotation here.
|
||||
*/
|
||||
_mesa_glsl_error(&loc, state,
|
||||
"image in structure, shader storage block or "
|
||||
"uniform block");
|
||||
if (decl_type->contains_image()) {
|
||||
/* FINISHME: Same problem as with atomic counters.
|
||||
* FINISHME: Request clarification from Khronos and add
|
||||
* FINISHME: spec quotation here.
|
||||
*/
|
||||
_mesa_glsl_error(&loc, state, "image in structure");
|
||||
}
|
||||
}
|
||||
|
||||
if (qual->flags.q.explicit_binding) {
|
||||
|
|
@ -6515,33 +6524,6 @@ ast_struct_specifier::hir(exec_list *instructions,
|
|||
{
|
||||
YYLTYPE loc = this->get_location();
|
||||
|
||||
/* Section 4.1.8 (Structures) of the GLSL 1.10 spec says:
|
||||
*
|
||||
* "Anonymous structures are not supported; so embedded structures must
|
||||
* have a declarator. A name given to an embedded struct is scoped at
|
||||
* the same level as the struct it is embedded in."
|
||||
*
|
||||
* The same section of the GLSL 1.20 spec says:
|
||||
*
|
||||
* "Anonymous structures are not supported. Embedded structures are not
|
||||
* supported.
|
||||
*
|
||||
* struct S { float f; };
|
||||
* struct T {
|
||||
* S; // Error: anonymous structures disallowed
|
||||
* struct { ... }; // Error: embedded structures disallowed
|
||||
* S s; // Okay: nested structures with name are allowed
|
||||
* };"
|
||||
*
|
||||
* The GLSL ES 1.00 and 3.00 specs have similar langauge and examples. So,
|
||||
* we allow embedded structures in 1.10 only.
|
||||
*/
|
||||
if (state->language_version != 110 && state->struct_specifier_depth != 0)
|
||||
_mesa_glsl_error(&loc, state,
|
||||
"embedded structure declarations are not allowed");
|
||||
|
||||
state->struct_specifier_depth++;
|
||||
|
||||
unsigned expl_location = 0;
|
||||
if (layout && layout->flags.q.explicit_location) {
|
||||
if (!process_qualifier_constant(state, &loc, "location",
|
||||
|
|
@ -6584,8 +6566,6 @@ ast_struct_specifier::hir(exec_list *instructions,
|
|||
}
|
||||
}
|
||||
|
||||
state->struct_specifier_depth--;
|
||||
|
||||
/* Structure type definitions do not have r-values.
|
||||
*/
|
||||
return NULL;
|
||||
|
|
@ -6705,11 +6685,6 @@ ast_interface_block::hir(exec_list *instructions,
|
|||
exec_list declared_variables;
|
||||
glsl_struct_field *fields;
|
||||
|
||||
/* Treat an interface block as one level of nesting, so that embedded struct
|
||||
* specifiers will be disallowed.
|
||||
*/
|
||||
state->struct_specifier_depth++;
|
||||
|
||||
/* For blocks that accept memory qualifiers (i.e. shader storage), verify
|
||||
* that we don't have incompatible qualifiers
|
||||
*/
|
||||
|
|
@ -6752,8 +6727,6 @@ ast_interface_block::hir(exec_list *instructions,
|
|||
qual_stream,
|
||||
expl_location);
|
||||
|
||||
state->struct_specifier_depth--;
|
||||
|
||||
if (!redeclaring_per_vertex) {
|
||||
validate_identifier(this->block_name, loc, state);
|
||||
|
||||
|
|
|
|||
|
|
@ -69,8 +69,6 @@ _mesa_glsl_parse_state::_mesa_glsl_parse_state(struct gl_context *_ctx,
|
|||
this->error = false;
|
||||
this->loop_nesting_ast = NULL;
|
||||
|
||||
this->struct_specifier_depth = 0;
|
||||
|
||||
this->uses_builtin_functions = false;
|
||||
|
||||
/* Set default language version and extensions */
|
||||
|
|
|
|||
|
|
@ -289,13 +289,6 @@ struct _mesa_glsl_parse_state {
|
|||
unsigned forced_language_version;
|
||||
gl_shader_stage stage;
|
||||
|
||||
/**
|
||||
* Number of nested struct_specifier levels
|
||||
*
|
||||
* Outside a struct_specifier, this is zero.
|
||||
*/
|
||||
unsigned struct_specifier_depth;
|
||||
|
||||
/**
|
||||
* Default uniform layout qualifiers tracked during parsing.
|
||||
* Currently affects uniform blocks and uniform buffer variables in
|
||||
|
|
|
|||
|
|
@ -22,12 +22,15 @@
|
|||
* OTHER DEALINGS IN THE SOFTWARE.
|
||||
*/
|
||||
|
||||
#include "main/core.h"
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
struct gl_context;
|
||||
struct gl_shader;
|
||||
struct gl_shader_program;
|
||||
|
||||
extern void
|
||||
_mesa_glsl_compile_shader(struct gl_context *ctx, struct gl_shader *shader,
|
||||
bool dump_ast, bool dump_hir);
|
||||
|
|
|
|||
|
|
@ -8,11 +8,11 @@ AM_CFLAGS = \
|
|||
-I$(top_srcdir)/src/gallium/auxiliary/util \
|
||||
$(GALLIUM_CFLAGS) \
|
||||
$(VISIBILITY_CFLAGS) \
|
||||
$(MSVC2008_COMPAT_CFLAGS)
|
||||
$(MSVC2013_COMPAT_CFLAGS)
|
||||
|
||||
AM_CXXFLAGS = \
|
||||
$(VISIBILITY_CXXFLAGS) \
|
||||
$(MSVC2008_COMPAT_CXXFLAGS)
|
||||
$(MSVC2013_COMPAT_CXXFLAGS)
|
||||
|
||||
libgallium_nir_la_SOURCES = \
|
||||
$(NIR_SOURCES)
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ env.Append(CPPPATH = [
|
|||
|
||||
env = env.Clone()
|
||||
|
||||
env.MSVC2008Compat()
|
||||
env.MSVC2013Compat()
|
||||
|
||||
env.CodeGenerate(
|
||||
target = 'indices/u_indices_gen.c',
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ Import('*')
|
|||
|
||||
env = env.Clone()
|
||||
|
||||
env.MSVC2008Compat()
|
||||
env.MSVC2013Compat()
|
||||
|
||||
env.Append(CPPPATH = [
|
||||
'#/src/loader',
|
||||
|
|
|
|||
|
|
@ -283,8 +283,7 @@ PIPE_ALIGN_STACK static inline boolean sse2_has_daz(void)
|
|||
fxarea.mxcsr_mask = 0;
|
||||
#if defined(PIPE_CC_GCC)
|
||||
__asm __volatile ("fxsave %0" : "+m" (fxarea));
|
||||
#elif (defined(PIPE_CC_MSVC) && _MSC_VER >= 1700) || defined(PIPE_CC_ICL)
|
||||
/* 1700 = Visual Studio 2012 */
|
||||
#elif defined(PIPE_CC_MSVC) || defined(PIPE_CC_ICL)
|
||||
_fxsave(&fxarea);
|
||||
#else
|
||||
fxarea.mxcsr_mask = 0;
|
||||
|
|
|
|||
|
|
@ -26,11 +26,11 @@ include $(top_srcdir)/src/gallium/Automake.inc
|
|||
AM_CFLAGS = \
|
||||
$(GALLIUM_DRIVER_CFLAGS) \
|
||||
$(LLVM_CFLAGS) \
|
||||
$(MSVC2008_COMPAT_CFLAGS)
|
||||
$(MSVC2013_COMPAT_CFLAGS)
|
||||
AM_CXXFLAGS= \
|
||||
$(GALLIUM_DRIVER_CXXFLAGS) \
|
||||
$(LLVM_CXXFLAGS) \
|
||||
$(MSVC2008_COMPAT_CXXFLAGS)
|
||||
$(MSVC2013_COMPAT_CXXFLAGS)
|
||||
|
||||
noinst_LTLIBRARIES = libllvmpipe.la
|
||||
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ if not env['llvm']:
|
|||
|
||||
env = env.Clone()
|
||||
|
||||
env.MSVC2008Compat()
|
||||
env.MSVC2013Compat()
|
||||
|
||||
llvmpipe = env.ConvenienceLibrary(
|
||||
target = 'llvmpipe',
|
||||
|
|
|
|||
|
|
@ -230,9 +230,7 @@ void nv50_stream_output_validate(struct nv50_context *);
|
|||
extern void nv50_init_state_functions(struct nv50_context *);
|
||||
|
||||
/* nv50_state_validate.c */
|
||||
/* @words: check for space before emitting relocs */
|
||||
extern bool nv50_state_validate(struct nv50_context *, uint32_t state_mask,
|
||||
unsigned space_words);
|
||||
bool nv50_state_validate(struct nv50_context *, uint32_t state_mask);
|
||||
|
||||
/* nv50_surface.c */
|
||||
extern void nv50_clear(struct pipe_context *, unsigned buffers,
|
||||
|
|
|
|||
|
|
@ -510,7 +510,7 @@ static struct state_validate {
|
|||
};
|
||||
|
||||
bool
|
||||
nv50_state_validate(struct nv50_context *nv50, uint32_t mask, unsigned words)
|
||||
nv50_state_validate(struct nv50_context *nv50, uint32_t mask)
|
||||
{
|
||||
uint32_t state_mask;
|
||||
int ret;
|
||||
|
|
|
|||
|
|
@ -525,7 +525,7 @@ nv50_clear(struct pipe_context *pipe, unsigned buffers,
|
|||
uint32_t mode = 0;
|
||||
|
||||
/* don't need NEW_BLEND, COLOR_MASK doesn't affect CLEAR_BUFFERS */
|
||||
if (!nv50_state_validate(nv50, NV50_NEW_FRAMEBUFFER, 9 + (fb->nr_cbufs * 2)))
|
||||
if (!nv50_state_validate(nv50, NV50_NEW_FRAMEBUFFER))
|
||||
return;
|
||||
|
||||
/* We have to clear ALL of the layers, not up to the min number of layers
|
||||
|
|
@ -1340,7 +1340,7 @@ nv50_blit_3d(struct nv50_context *nv50, const struct pipe_blit_info *info)
|
|||
|
||||
nv50_blitctx_prepare_state(blit);
|
||||
|
||||
nv50_state_validate(nv50, ~0, 36);
|
||||
nv50_state_validate(nv50, ~0);
|
||||
|
||||
x_range = (float)info->src.box.width / (float)info->dst.box.width;
|
||||
y_range = (float)info->src.box.height / (float)info->dst.box.height;
|
||||
|
|
|
|||
|
|
@ -790,7 +790,7 @@ nv50_draw_vbo(struct pipe_context *pipe, const struct pipe_draw_info *info)
|
|||
if (unlikely(nv50->num_so_targets && !nv50->gmtyprog))
|
||||
nv50->state.prim_size = nv50_pipe_prim_to_prim_size[info->mode];
|
||||
|
||||
nv50_state_validate(nv50, ~0, 8); /* 8 as minimum, we use flush_notify */
|
||||
nv50_state_validate(nv50, ~0);
|
||||
|
||||
push->kick_notify = nv50_draw_vbo_kick_notify;
|
||||
|
||||
|
|
|
|||
|
|
@ -258,8 +258,7 @@ extern void nvc0_init_state_functions(struct nvc0_context *);
|
|||
/* nvc0_state_validate.c */
|
||||
void nvc0_validate_global_residents(struct nvc0_context *,
|
||||
struct nouveau_bufctx *, int bin);
|
||||
extern bool nvc0_state_validate(struct nvc0_context *, uint32_t state_mask,
|
||||
unsigned space_words);
|
||||
bool nvc0_state_validate(struct nvc0_context *, uint32_t state_mask);
|
||||
|
||||
/* nvc0_surface.c */
|
||||
extern void nvc0_clear(struct pipe_context *, unsigned buffers,
|
||||
|
|
|
|||
|
|
@ -703,7 +703,7 @@ static struct state_validate {
|
|||
};
|
||||
|
||||
bool
|
||||
nvc0_state_validate(struct nvc0_context *nvc0, uint32_t mask, unsigned words)
|
||||
nvc0_state_validate(struct nvc0_context *nvc0, uint32_t mask)
|
||||
{
|
||||
uint32_t state_mask;
|
||||
int ret;
|
||||
|
|
|
|||
|
|
@ -693,7 +693,7 @@ nvc0_clear(struct pipe_context *pipe, unsigned buffers,
|
|||
uint32_t mode = 0;
|
||||
|
||||
/* don't need NEW_BLEND, COLOR_MASK doesn't affect CLEAR_BUFFERS */
|
||||
if (!nvc0_state_validate(nvc0, NVC0_NEW_FRAMEBUFFER, 9 + (fb->nr_cbufs * 2)))
|
||||
if (!nvc0_state_validate(nvc0, NVC0_NEW_FRAMEBUFFER))
|
||||
return;
|
||||
|
||||
if (buffers & PIPE_CLEAR_COLOR && fb->nr_cbufs) {
|
||||
|
|
@ -1191,7 +1191,7 @@ nvc0_blit_3d(struct nvc0_context *nvc0, const struct pipe_blit_info *info)
|
|||
|
||||
nvc0_blitctx_prepare_state(blit);
|
||||
|
||||
nvc0_state_validate(nvc0, ~0, 48);
|
||||
nvc0_state_validate(nvc0, ~0);
|
||||
|
||||
x_range = (float)info->src.box.width / (float)info->dst.box.width;
|
||||
y_range = (float)info->src.box.height / (float)info->dst.box.height;
|
||||
|
|
|
|||
|
|
@ -967,8 +967,7 @@ nvc0_draw_vbo(struct pipe_context *pipe, const struct pipe_draw_info *info)
|
|||
IMMED_NVC0(push, NVC0_3D(PATCH_VERTICES), nvc0->state.patch_vertices);
|
||||
}
|
||||
|
||||
/* 8 as minimum to avoid immediate double validation of new buffers */
|
||||
nvc0_state_validate(nvc0, ~0, 8);
|
||||
nvc0_state_validate(nvc0, ~0);
|
||||
|
||||
if (nvc0->vertprog->vp.need_draw_parameters) {
|
||||
PUSH_SPACE(push, 9);
|
||||
|
|
|
|||
|
|
@ -208,23 +208,6 @@ void *evergreen_create_compute_state(
|
|||
COMPUTE_DBG(ctx->screen, "*** evergreen_create_compute_state\n");
|
||||
header = cso->prog;
|
||||
code = cso->prog + sizeof(struct pipe_llvm_program_header);
|
||||
#if HAVE_LLVM < 0x0306
|
||||
(void)use_kill;
|
||||
(void)p;
|
||||
shader->llvm_ctx = LLVMContextCreate();
|
||||
shader->num_kernels = radeon_llvm_get_num_kernels(shader->llvm_ctx,
|
||||
code, header->num_bytes);
|
||||
shader->kernels = CALLOC(sizeof(struct r600_kernel),
|
||||
shader->num_kernels);
|
||||
{
|
||||
unsigned i;
|
||||
for (i = 0; i < shader->num_kernels; i++) {
|
||||
struct r600_kernel *kernel = &shader->kernels[i];
|
||||
kernel->llvm_module = radeon_llvm_get_kernel_module(
|
||||
shader->llvm_ctx, i, code, header->num_bytes);
|
||||
}
|
||||
}
|
||||
#else
|
||||
radeon_shader_binary_init(&shader->binary);
|
||||
radeon_elf_read(code, header->num_bytes, &shader->binary);
|
||||
r600_create_shader(&shader->bc, &shader->binary, &use_kill);
|
||||
|
|
@ -234,7 +217,6 @@ void *evergreen_create_compute_state(
|
|||
p = r600_buffer_map_sync_with_rings(&ctx->b, shader->code_bo, PIPE_TRANSFER_WRITE);
|
||||
memcpy(p, shader->bc.bytecode, shader->bc.ndw * 4);
|
||||
ctx->b.ws->buffer_unmap(shader->code_bo->buf);
|
||||
#endif
|
||||
#endif
|
||||
|
||||
shader->ctx = ctx;
|
||||
|
|
@ -255,20 +237,11 @@ void evergreen_delete_compute_state(struct pipe_context *ctx_, void* state)
|
|||
return;
|
||||
|
||||
#ifdef HAVE_OPENCL
|
||||
#if HAVE_LLVM < 0x0306
|
||||
for (unsigned i = 0; i < shader->num_kernels; i++) {
|
||||
struct r600_kernel *kernel = &shader->kernels[i];
|
||||
LLVMDisposeModule(module);
|
||||
}
|
||||
FREE(shader->kernels);
|
||||
LLVMContextDispose(shader->llvm_ctx);
|
||||
#else
|
||||
radeon_shader_binary_clean(&shader->binary);
|
||||
r600_destroy_shader(&shader->bc);
|
||||
|
||||
/* TODO destroy shader->code_bo, shader->const_bo
|
||||
* we'll need something like r600_buffer_free */
|
||||
#endif
|
||||
#endif
|
||||
FREE(shader);
|
||||
}
|
||||
|
|
@ -372,11 +345,7 @@ static void evergreen_emit_direct_dispatch(
|
|||
int group_size = 1;
|
||||
int grid_size = 1;
|
||||
unsigned lds_size = shader->local_size / 4 +
|
||||
#if HAVE_LLVM < 0x0306
|
||||
shader->active_kernel->bc.nlds_dw;
|
||||
#else
|
||||
shader->bc.nlds_dw;
|
||||
#endif
|
||||
|
||||
|
||||
/* Calculate group_size/grid_size */
|
||||
|
|
@ -565,18 +534,10 @@ void evergreen_emit_cs_shader(
|
|||
struct r600_resource *code_bo;
|
||||
unsigned ngpr, nstack;
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
struct r600_kernel *kernel = &shader->kernels[state->kernel_index];
|
||||
code_bo = kernel->code_bo;
|
||||
va = kernel->code_bo->gpu_address;
|
||||
ngpr = kernel->bc.ngpr;
|
||||
nstack = kernel->bc.nstack;
|
||||
#else
|
||||
code_bo = shader->code_bo;
|
||||
va = shader->code_bo->gpu_address + state->pc;
|
||||
ngpr = shader->bc.ngpr;
|
||||
nstack = shader->bc.nstack;
|
||||
#endif
|
||||
|
||||
radeon_compute_set_context_reg_seq(cs, R_0288D0_SQ_PGM_START_LS, 3);
|
||||
radeon_emit(cs, va >> 8); /* R_0288D0_SQ_PGM_START_LS */
|
||||
|
|
@ -601,45 +562,9 @@ static void evergreen_launch_grid(
|
|||
struct r600_pipe_compute *shader = ctx->cs_shader_state.shader;
|
||||
boolean use_kill;
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
struct r600_kernel *kernel = &shader->kernels[pc];
|
||||
(void)use_kill;
|
||||
if (!kernel->code_bo) {
|
||||
void *p;
|
||||
struct r600_bytecode *bc = &kernel->bc;
|
||||
LLVMModuleRef mod = kernel->llvm_module;
|
||||
boolean use_kill = false;
|
||||
bool dump = (ctx->screen->b.debug_flags & DBG_CS) != 0;
|
||||
unsigned use_sb = ctx->screen->b.debug_flags & DBG_SB_CS;
|
||||
unsigned sb_disasm = use_sb ||
|
||||
(ctx->screen->b.debug_flags & DBG_SB_DISASM);
|
||||
|
||||
r600_bytecode_init(bc, ctx->b.chip_class, ctx->b.family,
|
||||
ctx->screen->has_compressed_msaa_texturing);
|
||||
bc->type = TGSI_PROCESSOR_COMPUTE;
|
||||
bc->isa = ctx->isa;
|
||||
r600_llvm_compile(mod, ctx->b.family, bc, &use_kill, dump, &ctx->b.debug);
|
||||
|
||||
if (dump && !sb_disasm) {
|
||||
r600_bytecode_disasm(bc);
|
||||
} else if ((dump && sb_disasm) || use_sb) {
|
||||
if (r600_sb_bytecode_process(ctx, bc, NULL, dump, use_sb))
|
||||
R600_ERR("r600_sb_bytecode_process failed!\n");
|
||||
}
|
||||
|
||||
kernel->code_bo = r600_compute_buffer_alloc_vram(ctx->screen,
|
||||
kernel->bc.ndw * 4);
|
||||
p = r600_buffer_map_sync_with_rings(&ctx->b, kernel->code_bo, PIPE_TRANSFER_WRITE);
|
||||
memcpy(p, kernel->bc.bytecode, kernel->bc.ndw * 4);
|
||||
ctx->b.ws->buffer_unmap(kernel->code_bo->buf);
|
||||
}
|
||||
shader->active_kernel = kernel;
|
||||
ctx->cs_shader_state.kernel_index = pc;
|
||||
#else
|
||||
ctx->cs_shader_state.pc = pc;
|
||||
/* Get the config information for this kernel. */
|
||||
r600_shader_binary_read_config(&shader->binary, &shader->bc, pc, &use_kill);
|
||||
#endif
|
||||
#endif
|
||||
|
||||
COMPUTE_DBG(ctx->screen, "*** evergreen_launch_grid: pc = %u\n", pc);
|
||||
|
|
|
|||
|
|
@ -27,28 +27,9 @@
|
|||
|
||||
#include "r600_asm.h"
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
|
||||
struct r600_kernel {
|
||||
unsigned count;
|
||||
#ifdef HAVE_OPENCL
|
||||
LLVMModuleRef llvm_module;
|
||||
#endif
|
||||
struct r600_resource *code_bo;
|
||||
struct r600_bytecode bc;
|
||||
};
|
||||
|
||||
#endif
|
||||
|
||||
struct r600_pipe_compute {
|
||||
struct r600_context *ctx;
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
unsigned num_kernels;
|
||||
struct r600_kernel *kernels;
|
||||
struct r600_kernel *active_kernel;
|
||||
#endif
|
||||
|
||||
struct radeon_shader_binary binary;
|
||||
struct r600_resource *code_bo;
|
||||
struct r600_bytecode bc;
|
||||
|
|
|
|||
|
|
@ -528,11 +528,7 @@ static int r600_get_shader_param(struct pipe_screen* pscreen, unsigned shader, e
|
|||
return 16;
|
||||
case PIPE_SHADER_CAP_PREFERRED_IR:
|
||||
if (shader == PIPE_SHADER_COMPUTE) {
|
||||
#if HAVE_LLVM < 0x0306
|
||||
return PIPE_SHADER_IR_LLVM;
|
||||
#else
|
||||
return PIPE_SHADER_IR_NATIVE;
|
||||
#endif
|
||||
} else {
|
||||
return PIPE_SHADER_IR_TGSI;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -613,7 +613,7 @@ static int r600_get_compute_param(struct pipe_screen *screen,
|
|||
case PIPE_COMPUTE_CAP_IR_TARGET: {
|
||||
const char *gpu;
|
||||
const char *triple;
|
||||
if (rscreen->family <= CHIP_ARUBA || HAVE_LLVM < 0x0306) {
|
||||
if (rscreen->family <= CHIP_ARUBA) {
|
||||
triple = "r600--";
|
||||
} else {
|
||||
triple = "amdgcn--";
|
||||
|
|
@ -622,11 +622,6 @@ static int r600_get_compute_param(struct pipe_screen *screen,
|
|||
/* Clang < 3.6 is missing Hainan in its list of
|
||||
* GPUs, so we need to use the name of a similar GPU.
|
||||
*/
|
||||
#if HAVE_LLVM < 0x0306
|
||||
case CHIP_HAINAN:
|
||||
gpu = "oland";
|
||||
break;
|
||||
#endif
|
||||
default:
|
||||
gpu = r600_get_llvm_processor_name(rscreen->family);
|
||||
break;
|
||||
|
|
|
|||
|
|
@ -45,12 +45,6 @@ struct si_compute {
|
|||
|
||||
struct r600_resource *input_buffer;
|
||||
struct pipe_resource *global_buffers[MAX_GLOBAL_BUFFERS];
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
unsigned num_kernels;
|
||||
struct si_shader *kernels;
|
||||
LLVMContextRef llvm_ctx;
|
||||
#endif
|
||||
};
|
||||
|
||||
static void init_scratch_buffer(struct si_context *sctx, struct si_compute *program)
|
||||
|
|
@ -111,29 +105,6 @@ static void *si_create_compute_state(
|
|||
program->private_size = cso->req_private_mem;
|
||||
program->input_size = cso->req_input_mem;
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
{
|
||||
unsigned i;
|
||||
program->llvm_ctx = LLVMContextCreate();
|
||||
program->num_kernels = radeon_llvm_get_num_kernels(program->llvm_ctx,
|
||||
code, header->num_bytes);
|
||||
program->kernels = CALLOC(sizeof(struct si_shader),
|
||||
program->num_kernels);
|
||||
for (i = 0; i < program->num_kernels; i++) {
|
||||
LLVMModuleRef mod = radeon_llvm_get_kernel_module(program->llvm_ctx, i,
|
||||
code, header->num_bytes);
|
||||
si_compile_llvm(sctx->screen, &program->kernels[i].binary,
|
||||
&program->kernels[i].config, sctx->tm,
|
||||
mod, &sctx->b.debug, TGSI_PROCESSOR_COMPUTE,
|
||||
"Compute Shader");
|
||||
si_shader_dump(sctx->screen, &program->kernels[i],
|
||||
&sctx->b.debug, TGSI_PROCESSOR_COMPUTE);
|
||||
si_shader_binary_upload(sctx->screen, &program->kernels[i]);
|
||||
LLVMDisposeModule(mod);
|
||||
}
|
||||
}
|
||||
#else
|
||||
|
||||
radeon_elf_read(code, header->num_bytes, &program->shader.binary);
|
||||
|
||||
/* init_scratch_buffer patches the shader code with the scratch address,
|
||||
|
|
@ -147,7 +118,6 @@ static void *si_create_compute_state(
|
|||
TGSI_PROCESSOR_COMPUTE);
|
||||
si_shader_binary_upload(sctx->screen, &program->shader);
|
||||
|
||||
#endif
|
||||
program->input_buffer = si_resource_create_custom(sctx->b.b.screen,
|
||||
PIPE_USAGE_IMMUTABLE, program->input_size);
|
||||
|
||||
|
|
@ -247,11 +217,6 @@ static void si_launch_grid(
|
|||
unsigned lds_blocks;
|
||||
unsigned num_waves_for_scratch;
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
shader = &program->kernels[pc];
|
||||
#endif
|
||||
|
||||
|
||||
radeon_emit(cs, PKT3(PKT3_CONTEXT_CONTROL, 1, 0) | PKT3_SHADER_TYPE_S(1));
|
||||
radeon_emit(cs, 0x80000000);
|
||||
radeon_emit(cs, 0x80000000);
|
||||
|
|
@ -266,10 +231,8 @@ static void si_launch_grid(
|
|||
|
||||
pm4->compute_pkt = true;
|
||||
|
||||
#if HAVE_LLVM >= 0x0306
|
||||
/* Read the config information */
|
||||
si_shader_binary_read_config(&shader->binary, &shader->config, pc);
|
||||
#endif
|
||||
|
||||
/* Upload the kernel arguments */
|
||||
|
||||
|
|
@ -360,10 +323,8 @@ static void si_launch_grid(
|
|||
}
|
||||
|
||||
shader_va = shader->bo->gpu_address;
|
||||
|
||||
#if HAVE_LLVM >= 0x0306
|
||||
shader_va += pc;
|
||||
#endif
|
||||
|
||||
radeon_add_to_buffer_list(&sctx->b, &sctx->b.gfx, shader->bo,
|
||||
RADEON_USAGE_READ, RADEON_PRIO_USER_SHADER);
|
||||
si_pm4_set_reg(pm4, R_00B830_COMPUTE_PGM_LO, shader_va >> 8);
|
||||
|
|
@ -448,26 +409,9 @@ static void si_delete_compute_state(struct pipe_context *ctx, void* state){
|
|||
return;
|
||||
}
|
||||
|
||||
#if HAVE_LLVM < 0x0306
|
||||
if (program->kernels) {
|
||||
for (int i = 0; i < program->num_kernels; i++){
|
||||
if (program->kernels[i].bo){
|
||||
si_shader_destroy(&program->kernels[i]);
|
||||
}
|
||||
}
|
||||
FREE(program->kernels);
|
||||
}
|
||||
|
||||
if (program->llvm_ctx){
|
||||
LLVMContextDispose(program->llvm_ctx);
|
||||
}
|
||||
#else
|
||||
si_shader_destroy(&program->shader);
|
||||
#endif
|
||||
|
||||
pipe_resource_reference(
|
||||
(struct pipe_resource **)&program->input_buffer, NULL);
|
||||
|
||||
FREE(program);
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -203,7 +203,8 @@ static void si_set_sampler_view(struct si_context *sctx,
|
|||
pipe_sampler_view_reference(&views->views[slot], view);
|
||||
memcpy(views->desc.list + slot * 16, rview->state, 8*4);
|
||||
|
||||
if (rtex && rtex->fmask.size) {
|
||||
if (view->texture && view->texture->target != PIPE_BUFFER &&
|
||||
rtex->fmask.size) {
|
||||
memcpy(views->desc.list + slot*16 + 8,
|
||||
rview->fmask_state, 8*4);
|
||||
} else {
|
||||
|
|
|
|||
|
|
@ -74,9 +74,7 @@ static void si_destroy_context(struct pipe_context *context)
|
|||
|
||||
r600_common_context_cleanup(&sctx->b);
|
||||
|
||||
#if HAVE_LLVM >= 0x0306
|
||||
LLVMDisposeTargetMachine(sctx->tm);
|
||||
#endif
|
||||
|
||||
r600_resource_reference(&sctx->trace_buf, NULL);
|
||||
r600_resource_reference(&sctx->last_trace_buf, NULL);
|
||||
|
|
@ -104,9 +102,7 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
|
|||
struct si_screen* sscreen = (struct si_screen *)screen;
|
||||
struct radeon_winsys *ws = sscreen->b.ws;
|
||||
LLVMTargetRef r600_target;
|
||||
#if HAVE_LLVM >= 0x0306
|
||||
const char *triple = "amdgcn--";
|
||||
#endif
|
||||
int shader, i;
|
||||
|
||||
if (!sctx)
|
||||
|
|
@ -210,7 +206,6 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
|
|||
*/
|
||||
sctx->scratch_waves = 32 * sscreen->b.info.num_good_compute_units;
|
||||
|
||||
#if HAVE_LLVM >= 0x0306
|
||||
/* Initialize LLVM TargetMachine */
|
||||
r600_target = radeon_llvm_get_r600_target(triple);
|
||||
sctx->tm = LLVMCreateTargetMachine(r600_target, triple,
|
||||
|
|
@ -223,7 +218,6 @@ static struct pipe_context *si_create_context(struct pipe_screen *screen,
|
|||
LLVMCodeGenLevelDefault,
|
||||
LLVMRelocDefault,
|
||||
LLVMCodeModelDefault);
|
||||
#endif
|
||||
|
||||
return &sctx->b.b;
|
||||
fail:
|
||||
|
|
@ -310,6 +304,7 @@ static int si_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
|
|||
case PIPE_CAP_INVALIDATE_BUFFER:
|
||||
case PIPE_CAP_SURFACE_REINTERPRET_BLOCKS:
|
||||
case PIPE_CAP_QUERY_MEMORY_INFO:
|
||||
case PIPE_CAP_TGSI_PACK_HALF_FLOAT:
|
||||
return 1;
|
||||
|
||||
case PIPE_CAP_RESOURCE_FROM_USER_MEMORY:
|
||||
|
|
@ -335,9 +330,6 @@ static int si_get_param(struct pipe_screen* pscreen, enum pipe_cap param)
|
|||
case PIPE_CAP_MAX_TEXTURE_GATHER_COMPONENTS:
|
||||
return 4;
|
||||
|
||||
case PIPE_CAP_TGSI_PACK_HALF_FLOAT:
|
||||
return HAVE_LLVM >= 0x0306;
|
||||
|
||||
case PIPE_CAP_GLSL_FEATURE_LEVEL:
|
||||
return HAVE_LLVM >= 0x0307 ? 410 : 330;
|
||||
|
||||
|
|
@ -449,18 +441,13 @@ static int si_get_shader_param(struct pipe_screen* pscreen, unsigned shader, enu
|
|||
case PIPE_SHADER_TESS_CTRL:
|
||||
case PIPE_SHADER_TESS_EVAL:
|
||||
/* LLVM 3.6.2 is required for tessellation because of bug fixes there */
|
||||
if (HAVE_LLVM < 0x0306 ||
|
||||
(HAVE_LLVM == 0x0306 && MESA_LLVM_VERSION_PATCH < 2))
|
||||
if (HAVE_LLVM == 0x0306 && MESA_LLVM_VERSION_PATCH < 2)
|
||||
return 0;
|
||||
break;
|
||||
case PIPE_SHADER_COMPUTE:
|
||||
switch (param) {
|
||||
case PIPE_SHADER_CAP_PREFERRED_IR:
|
||||
#if HAVE_LLVM < 0x0306
|
||||
return PIPE_SHADER_IR_LLVM;
|
||||
#else
|
||||
return PIPE_SHADER_IR_NATIVE;
|
||||
#endif
|
||||
case PIPE_SHADER_CAP_DOUBLES:
|
||||
return HAVE_LLVM >= 0x0307;
|
||||
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -25,7 +25,7 @@ include $(top_srcdir)/src/gallium/Automake.inc
|
|||
|
||||
AM_CFLAGS = \
|
||||
$(GALLIUM_DRIVER_CFLAGS) \
|
||||
$(MSVC2008_COMPAT_CFLAGS)
|
||||
$(MSVC2013_COMPAT_CFLAGS)
|
||||
|
||||
noinst_LTLIBRARIES = libsoftpipe.la
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ Import('*')
|
|||
|
||||
env = env.Clone()
|
||||
|
||||
env.MSVC2008Compat()
|
||||
env.MSVC2013Compat()
|
||||
|
||||
softpipe = env.ConvenienceLibrary(
|
||||
target = 'softpipe',
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ include $(top_srcdir)/src/gallium/Automake.inc
|
|||
|
||||
AM_CFLAGS = \
|
||||
$(GALLIUM_DRIVER_CFLAGS) \
|
||||
$(MSVC2008_COMPAT_CFLAGS)
|
||||
$(MSVC2013_COMPAT_CFLAGS)
|
||||
|
||||
noinst_LTLIBRARIES = libtrace.la
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ Import('*')
|
|||
|
||||
env = env.Clone()
|
||||
|
||||
env.MSVC2008Compat()
|
||||
env.MSVC2013Compat()
|
||||
|
||||
trace = env.ConvenienceLibrary(
|
||||
target = 'trace',
|
||||
|
|
|
|||
|
|
@ -174,10 +174,9 @@ static boolean do_winsys_init(struct amdgpu_winsys *ws)
|
|||
goto fail;
|
||||
}
|
||||
|
||||
/* LLVM 3.6 is required for VI. */
|
||||
/* LLVM 3.6.1 is required for VI. */
|
||||
if (ws->info.chip_class >= VI &&
|
||||
(HAVE_LLVM < 0x0306 ||
|
||||
(HAVE_LLVM == 0x0306 && MESA_LLVM_VERSION_PATCH < 1))) {
|
||||
HAVE_LLVM == 0x0306 && MESA_LLVM_VERSION_PATCH < 1) {
|
||||
fprintf(stderr, "amdgpu: LLVM 3.6.1 is required, got LLVM %i.%i.%i\n",
|
||||
HAVE_LLVM >> 8, HAVE_LLVM & 255, MESA_LLVM_VERSION_PATCH);
|
||||
goto fail;
|
||||
|
|
|
|||
|
|
@ -387,6 +387,9 @@ struct brw_wm_prog_data {
|
|||
bool uses_pos_offset;
|
||||
bool uses_omask;
|
||||
bool uses_kill;
|
||||
bool uses_src_depth;
|
||||
bool uses_src_w;
|
||||
bool uses_sample_mask;
|
||||
bool pulls_bary;
|
||||
uint32_t prog_offset_16;
|
||||
|
||||
|
|
@ -626,6 +629,8 @@ struct brw_gs_prog_data
|
|||
{
|
||||
struct brw_vue_prog_data base;
|
||||
|
||||
unsigned vertices_in;
|
||||
|
||||
/**
|
||||
* Size of an output vertex, measured in HWORDS (32 bytes).
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -4790,7 +4790,7 @@ fs_visitor::dump_instruction(backend_instruction *be_inst, FILE *file)
|
|||
case IMM:
|
||||
switch (inst->src[i].type) {
|
||||
case BRW_REGISTER_TYPE_F:
|
||||
fprintf(file, "%ff", inst->src[i].f);
|
||||
fprintf(file, "%-gf", inst->src[i].f);
|
||||
break;
|
||||
case BRW_REGISTER_TYPE_W:
|
||||
case BRW_REGISTER_TYPE_D:
|
||||
|
|
@ -4898,10 +4898,12 @@ fs_visitor::get_instruction_generating_reg(fs_inst *start,
|
|||
}
|
||||
|
||||
void
|
||||
fs_visitor::setup_payload_gen6()
|
||||
fs_visitor::setup_fs_payload_gen6()
|
||||
{
|
||||
bool uses_depth =
|
||||
(nir->info.inputs_read & (1 << VARYING_SLOT_POS)) != 0;
|
||||
assert(stage == MESA_SHADER_FRAGMENT);
|
||||
brw_wm_prog_data *prog_data = (brw_wm_prog_data*) this->prog_data;
|
||||
brw_wm_prog_key *key = (brw_wm_prog_key*) this->key;
|
||||
|
||||
unsigned barycentric_interp_modes =
|
||||
(stage == MESA_SHADER_FRAGMENT) ?
|
||||
((brw_wm_prog_data*) this->prog_data)->barycentric_interp_modes : 0;
|
||||
|
|
@ -4930,7 +4932,9 @@ fs_visitor::setup_payload_gen6()
|
|||
}
|
||||
|
||||
/* R27: interpolated depth if uses source depth */
|
||||
if (uses_depth) {
|
||||
prog_data->uses_src_depth =
|
||||
(nir->info.inputs_read & (1 << VARYING_SLOT_POS)) != 0;
|
||||
if (prog_data->uses_src_depth) {
|
||||
payload.source_depth_reg = payload.num_regs;
|
||||
payload.num_regs++;
|
||||
if (dispatch_width == 16) {
|
||||
|
|
@ -4938,8 +4942,11 @@ fs_visitor::setup_payload_gen6()
|
|||
payload.num_regs++;
|
||||
}
|
||||
}
|
||||
|
||||
/* R29: interpolated W set if GEN6_WM_USES_SOURCE_W. */
|
||||
if (uses_depth) {
|
||||
prog_data->uses_src_w =
|
||||
(nir->info.inputs_read & (1 << VARYING_SLOT_POS)) != 0;
|
||||
if (prog_data->uses_src_w) {
|
||||
payload.source_w_reg = payload.num_regs;
|
||||
payload.num_regs++;
|
||||
if (dispatch_width == 16) {
|
||||
|
|
@ -4948,19 +4955,17 @@ fs_visitor::setup_payload_gen6()
|
|||
}
|
||||
}
|
||||
|
||||
if (stage == MESA_SHADER_FRAGMENT) {
|
||||
brw_wm_prog_data *prog_data = (brw_wm_prog_data*) this->prog_data;
|
||||
brw_wm_prog_key *key = (brw_wm_prog_key*) this->key;
|
||||
prog_data->uses_pos_offset = key->compute_pos_offset;
|
||||
/* R31: MSAA position offsets. */
|
||||
if (prog_data->uses_pos_offset) {
|
||||
payload.sample_pos_reg = payload.num_regs;
|
||||
payload.num_regs++;
|
||||
}
|
||||
prog_data->uses_pos_offset = key->compute_pos_offset;
|
||||
/* R31: MSAA position offsets. */
|
||||
if (prog_data->uses_pos_offset) {
|
||||
payload.sample_pos_reg = payload.num_regs;
|
||||
payload.num_regs++;
|
||||
}
|
||||
|
||||
/* R32: MSAA input coverage mask */
|
||||
if (nir->info.system_values_read & SYSTEM_BIT_SAMPLE_MASK_IN) {
|
||||
prog_data->uses_sample_mask =
|
||||
(nir->info.system_values_read & SYSTEM_BIT_SAMPLE_MASK_IN) != 0;
|
||||
if (prog_data->uses_sample_mask) {
|
||||
assert(devinfo->gen >= 7);
|
||||
payload.sample_mask_in_reg = payload.num_regs;
|
||||
payload.num_regs++;
|
||||
|
|
@ -5397,9 +5402,9 @@ fs_visitor::run_fs(bool do_rep_send)
|
|||
assert(stage == MESA_SHADER_FRAGMENT);
|
||||
|
||||
if (devinfo->gen >= 6)
|
||||
setup_payload_gen6();
|
||||
setup_fs_payload_gen6();
|
||||
else
|
||||
setup_payload_gen4();
|
||||
setup_fs_payload_gen4();
|
||||
|
||||
if (0) {
|
||||
emit_dummy_fs();
|
||||
|
|
|
|||
|
|
@ -115,8 +115,8 @@ public:
|
|||
bool run_cs();
|
||||
void optimize();
|
||||
void allocate_registers();
|
||||
void setup_payload_gen4();
|
||||
void setup_payload_gen6();
|
||||
void setup_fs_payload_gen4();
|
||||
void setup_fs_payload_gen6();
|
||||
void setup_vs_payload();
|
||||
void setup_gs_payload();
|
||||
void setup_cs_payload();
|
||||
|
|
|
|||
|
|
@ -27,6 +27,7 @@
|
|||
#include "brw_nir.h"
|
||||
#include "brw_program.h"
|
||||
#include "compiler/glsl/ir_optimization.h"
|
||||
#include "compiler/glsl/program.h"
|
||||
#include "program/program.h"
|
||||
#include "main/shaderapi.h"
|
||||
#include "main/uniforms.h"
|
||||
|
|
@ -259,5 +260,6 @@ brw_link_shader(struct gl_context *ctx, struct gl_shader_program *shProg)
|
|||
if (brw->precompile && !brw_shader_precompile(ctx, shProg))
|
||||
return false;
|
||||
|
||||
build_program_resource_list(shProg);
|
||||
return true;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -773,6 +773,8 @@ brw_compile_gs(const struct brw_compiler *compiler, void *log_data,
|
|||
prog_data->output_topology =
|
||||
get_hw_prim_for_gl_prim(shader->info.gs.output_primitive);
|
||||
|
||||
prog_data->vertices_in = shader->info.gs.vertices_in;
|
||||
|
||||
/* The GLSL linker will have already matched up GS inputs and the outputs
|
||||
* of prior stages. The driver does extend VS outputs in some cases, but
|
||||
* only for legacy OpenGL or Gen4-5 hardware, neither of which offer
|
||||
|
|
|
|||
|
|
@ -120,15 +120,14 @@ static const struct {
|
|||
* \param line_aa AA_NEVER, AA_ALWAYS or AA_SOMETIMES
|
||||
* \param lookup bitmask of IZ_* flags
|
||||
*/
|
||||
void fs_visitor::setup_payload_gen4()
|
||||
void fs_visitor::setup_fs_payload_gen4()
|
||||
{
|
||||
assert(stage == MESA_SHADER_FRAGMENT);
|
||||
brw_wm_prog_data *prog_data = (brw_wm_prog_data*) this->prog_data;
|
||||
brw_wm_prog_key *key = (brw_wm_prog_key*) this->key;
|
||||
GLuint reg = 2;
|
||||
bool kill_stats_promoted_workaround = false;
|
||||
int lookup = key->iz_lookup;
|
||||
bool uses_depth =
|
||||
(nir->info.inputs_read & (1 << VARYING_SLOT_POS)) != 0;
|
||||
|
||||
assert(lookup < IZ_BIT_MAX);
|
||||
|
||||
|
|
@ -143,7 +142,9 @@ void fs_visitor::setup_payload_gen4()
|
|||
kill_stats_promoted_workaround = true;
|
||||
}
|
||||
|
||||
if (wm_iz_table[lookup].sd_present || uses_depth ||
|
||||
prog_data->uses_src_depth =
|
||||
(nir->info.inputs_read & (1 << VARYING_SLOT_POS)) != 0;
|
||||
if (wm_iz_table[lookup].sd_present || prog_data->uses_src_depth ||
|
||||
kill_stats_promoted_workaround) {
|
||||
payload.source_depth_reg = reg;
|
||||
reg += 2;
|
||||
|
|
|
|||
|
|
@ -175,8 +175,7 @@ brw_upload_wm_unit(struct brw_context *brw)
|
|||
}
|
||||
|
||||
/* BRW_NEW_FRAGMENT_PROGRAM */
|
||||
wm->wm5.program_uses_depth = (fp->Base.InputsRead &
|
||||
(1 << VARYING_SLOT_POS)) != 0;
|
||||
wm->wm5.program_uses_depth = prog_data->uses_src_depth;
|
||||
wm->wm5.program_computes_depth = (fp->Base.OutputsWritten &
|
||||
BITFIELD64_BIT(FRAG_RESULT_DEPTH)) != 0;
|
||||
/* _NEW_BUFFERS
|
||||
|
|
|
|||
|
|
@ -37,9 +37,6 @@ static void
|
|||
upload_wm_state(struct brw_context *brw)
|
||||
{
|
||||
struct gl_context *ctx = &brw->ctx;
|
||||
/* BRW_NEW_FRAGMENT_PROGRAM */
|
||||
const struct brw_fragment_program *fp =
|
||||
brw_fragment_program_const(brw->fragment_program);
|
||||
/* BRW_NEW_FS_PROG_DATA */
|
||||
const struct brw_wm_prog_data *prog_data = brw->wm.prog_data;
|
||||
bool writes_depth = prog_data->computed_depth_mode != BRW_PSCDEPTH_OFF;
|
||||
|
|
@ -61,8 +58,11 @@ upload_wm_state(struct brw_context *brw)
|
|||
if (ctx->Polygon.StippleFlag)
|
||||
dw1 |= GEN7_WM_POLYGON_STIPPLE_ENABLE;
|
||||
|
||||
if (fp->program.Base.InputsRead & VARYING_BIT_POS)
|
||||
dw1 |= GEN7_WM_USES_SOURCE_DEPTH | GEN7_WM_USES_SOURCE_W;
|
||||
if (prog_data->uses_src_depth)
|
||||
dw1 |= GEN7_WM_USES_SOURCE_DEPTH;
|
||||
|
||||
if (prog_data->uses_src_w)
|
||||
dw1 |= GEN7_WM_USES_SOURCE_W;
|
||||
|
||||
dw1 |= prog_data->computed_depth_mode << GEN7_WM_COMPUTED_DEPTH_MODE_SHIFT;
|
||||
dw1 |= prog_data->barycentric_interp_modes <<
|
||||
|
|
@ -100,7 +100,7 @@ upload_wm_state(struct brw_context *brw)
|
|||
dw2 |= GEN7_WM_MSDISPMODE_PERSAMPLE;
|
||||
}
|
||||
|
||||
if (fp->program.Base.SystemValuesRead & SYSTEM_BIT_SAMPLE_MASK_IN) {
|
||||
if (prog_data->uses_sample_mask) {
|
||||
dw1 |= GEN7_WM_USES_INPUT_COVERAGE_MASK;
|
||||
}
|
||||
|
||||
|
|
@ -138,7 +138,6 @@ const struct brw_tracked_state gen7_wm_state = {
|
|||
_NEW_MULTISAMPLE |
|
||||
_NEW_POLYGON,
|
||||
.brw = BRW_NEW_BATCH |
|
||||
BRW_NEW_FRAGMENT_PROGRAM |
|
||||
BRW_NEW_FS_PROG_DATA,
|
||||
},
|
||||
.emit = upload_wm_state,
|
||||
|
|
|
|||
|
|
@ -48,7 +48,7 @@ gen8_upload_gs_state(struct brw_context *brw)
|
|||
OUT_BATCH(_3DSTATE_GS << 16 | (10 - 2));
|
||||
OUT_BATCH(stage_state->prog_offset);
|
||||
OUT_BATCH(0);
|
||||
OUT_BATCH(brw->geometry_program->VerticesIn |
|
||||
OUT_BATCH(brw->gs.prog_data->vertices_in |
|
||||
((ALIGN(stage_state->sampler_count, 4)/4) <<
|
||||
GEN6_GS_SAMPLER_COUNT_SHIFT) |
|
||||
((prog_data->base.binding_table.size_bytes / 4) <<
|
||||
|
|
|
|||
|
|
@ -46,14 +46,17 @@ gen8_upload_ps_extra(struct brw_context *brw,
|
|||
if (prog_data->num_varying_inputs != 0)
|
||||
dw1 |= GEN8_PSX_ATTRIBUTE_ENABLE;
|
||||
|
||||
if (fp->Base.InputsRead & VARYING_BIT_POS)
|
||||
dw1 |= GEN8_PSX_USES_SOURCE_DEPTH | GEN8_PSX_USES_SOURCE_W;
|
||||
if (prog_data->uses_src_depth)
|
||||
dw1 |= GEN8_PSX_USES_SOURCE_DEPTH;
|
||||
|
||||
if (prog_data->uses_src_w)
|
||||
dw1 |= GEN8_PSX_USES_SOURCE_W;
|
||||
|
||||
if (multisampled_fbo &&
|
||||
_mesa_get_min_invocations_per_fragment(ctx, fp, false) > 1)
|
||||
dw1 |= GEN8_PSX_SHADER_IS_PER_SAMPLE;
|
||||
|
||||
if (fp->Base.SystemValuesRead & SYSTEM_BIT_SAMPLE_MASK_IN) {
|
||||
if (prog_data->uses_sample_mask) {
|
||||
if (brw->gen >= 9)
|
||||
dw1 |= BRW_PSICMS_INNER << GEN9_PSX_SHADER_NORMAL_COVERAGE_MASK_SHIFT;
|
||||
else
|
||||
|
|
|
|||
|
|
@ -346,7 +346,8 @@ intelInitExtensions(struct gl_context *ctx)
|
|||
ctx->Extensions.ARB_transform_feedback3 = true;
|
||||
ctx->Extensions.ARB_transform_feedback_instanced = true;
|
||||
|
||||
if (ctx->Const.MaxComputeWorkGroupSize[0] >= 1024)
|
||||
if ((brw->gen >= 8 || brw->intelScreen->cmd_parser_version >= 5) &&
|
||||
ctx->Const.MaxComputeWorkGroupSize[0] >= 1024)
|
||||
ctx->Extensions.ARB_compute_shader = true;
|
||||
|
||||
if (brw->intelScreen->cmd_parser_version >= 2)
|
||||
|
|
|
|||
|
|
@ -31,6 +31,7 @@
|
|||
|
||||
#include <stdio.h>
|
||||
#include "main/compiler.h"
|
||||
#include "main/macros.h"
|
||||
#include "main/mtypes.h"
|
||||
#include "main/shaderapi.h"
|
||||
#include "main/shaderobj.h"
|
||||
|
|
@ -3009,6 +3010,7 @@ _mesa_ir_link_shader(struct gl_context *ctx, struct gl_shader_program *prog)
|
|||
_mesa_reference_program(ctx, &linked_prog, NULL);
|
||||
}
|
||||
|
||||
build_program_resource_list(prog);
|
||||
return prog->LinkStatus;
|
||||
}
|
||||
|
||||
|
|
@ -3037,8 +3039,6 @@ _mesa_glsl_link_shader(struct gl_context *ctx, struct gl_shader_program *prog)
|
|||
if (prog->LinkStatus) {
|
||||
if (!ctx->Driver.LinkShader(ctx, prog)) {
|
||||
prog->LinkStatus = GL_FALSE;
|
||||
} else {
|
||||
build_program_resource_list(prog);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -172,7 +172,8 @@ update_gp( struct st_context *st )
|
|||
stgp = st_geometry_program(st->ctx->GeometryProgram._Current);
|
||||
assert(stgp->Base.Base.Target == GL_GEOMETRY_PROGRAM_NV);
|
||||
|
||||
st->gp_variant = st_get_basic_variant(st, &stgp->tgsi, &stgp->variants);
|
||||
st->gp_variant = st_get_basic_variant(st, PIPE_SHADER_GEOMETRY,
|
||||
&stgp->tgsi, &stgp->variants);
|
||||
|
||||
st_reference_geomprog(st, &st->gp, stgp);
|
||||
|
||||
|
|
@ -204,7 +205,8 @@ update_tcp( struct st_context *st )
|
|||
sttcp = st_tessctrl_program(st->ctx->TessCtrlProgram._Current);
|
||||
assert(sttcp->Base.Base.Target == GL_TESS_CONTROL_PROGRAM_NV);
|
||||
|
||||
st->tcp_variant = st_get_basic_variant(st, &sttcp->tgsi, &sttcp->variants);
|
||||
st->tcp_variant = st_get_basic_variant(st, PIPE_SHADER_TESS_CTRL,
|
||||
&sttcp->tgsi, &sttcp->variants);
|
||||
|
||||
st_reference_tesscprog(st, &st->tcp, sttcp);
|
||||
|
||||
|
|
@ -236,7 +238,8 @@ update_tep( struct st_context *st )
|
|||
sttep = st_tesseval_program(st->ctx->TessEvalProgram._Current);
|
||||
assert(sttep->Base.Base.Target == GL_TESS_EVALUATION_PROGRAM_NV);
|
||||
|
||||
st->tep_variant = st_get_basic_variant(st, &sttep->tgsi, &sttep->variants);
|
||||
st->tep_variant = st_get_basic_variant(st, PIPE_SHADER_TESS_EVAL,
|
||||
&sttep->tgsi, &sttep->variants);
|
||||
|
||||
st_reference_tesseprog(st, &st->tep, sttep);
|
||||
|
||||
|
|
|
|||
|
|
@ -34,6 +34,7 @@
|
|||
|
||||
#include "compiler/glsl/glsl_parser_extras.h"
|
||||
#include "compiler/glsl/ir_optimization.h"
|
||||
#include "compiler/glsl/program.h"
|
||||
|
||||
#include "main/errors.h"
|
||||
#include "main/shaderobj.h"
|
||||
|
|
@ -6148,6 +6149,10 @@ get_mesa_program(struct gl_context *ctx,
|
|||
prog->OutputsWritten, 0ULL, prog->PatchOutputsWritten);
|
||||
count_resources(v, prog);
|
||||
|
||||
/* The GLSL IR won't be needed anymore. */
|
||||
ralloc_free(shader->ir);
|
||||
shader->ir = NULL;
|
||||
|
||||
/* This must be done before the uniform storage is associated. */
|
||||
if (shader->Type == GL_FRAGMENT_SHADER &&
|
||||
(prog->InputsRead & VARYING_BIT_POS ||
|
||||
|
|
@ -6380,6 +6385,8 @@ st_link_shader(struct gl_context *ctx, struct gl_shader_program *prog)
|
|||
validate_ir_tree(ir);
|
||||
}
|
||||
|
||||
build_program_resource_list(prog);
|
||||
|
||||
for (unsigned i = 0; i < MESA_SHADER_STAGES; i++) {
|
||||
struct gl_program *linked_prog;
|
||||
|
||||
|
|
|
|||
|
|
@ -1271,6 +1271,7 @@ st_translate_geometry_program(struct st_context *st,
|
|||
*/
|
||||
struct st_basic_variant *
|
||||
st_get_basic_variant(struct st_context *st,
|
||||
unsigned pipe_shader,
|
||||
struct pipe_shader_state *tgsi,
|
||||
struct st_basic_variant **variants)
|
||||
{
|
||||
|
|
@ -1293,7 +1294,22 @@ st_get_basic_variant(struct st_context *st,
|
|||
v = CALLOC_STRUCT(st_basic_variant);
|
||||
if (v) {
|
||||
/* fill in new variant */
|
||||
v->driver_shader = pipe->create_gs_state(pipe, tgsi);
|
||||
switch (pipe_shader) {
|
||||
case PIPE_SHADER_TESS_CTRL:
|
||||
v->driver_shader = pipe->create_tcs_state(pipe, tgsi);
|
||||
break;
|
||||
case PIPE_SHADER_TESS_EVAL:
|
||||
v->driver_shader = pipe->create_tes_state(pipe, tgsi);
|
||||
break;
|
||||
case PIPE_SHADER_GEOMETRY:
|
||||
v->driver_shader = pipe->create_gs_state(pipe, tgsi);
|
||||
break;
|
||||
default:
|
||||
assert(!"unhandled shader type");
|
||||
free(v);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
v->key = key;
|
||||
|
||||
/* insert into list */
|
||||
|
|
@ -1587,19 +1603,19 @@ st_precompile_shader_variant(struct st_context *st,
|
|||
|
||||
case GL_TESS_CONTROL_PROGRAM_NV: {
|
||||
struct st_tessctrl_program *p = (struct st_tessctrl_program *)prog;
|
||||
st_get_basic_variant(st, &p->tgsi, &p->variants);
|
||||
st_get_basic_variant(st, PIPE_SHADER_TESS_CTRL, &p->tgsi, &p->variants);
|
||||
break;
|
||||
}
|
||||
|
||||
case GL_TESS_EVALUATION_PROGRAM_NV: {
|
||||
struct st_tesseval_program *p = (struct st_tesseval_program *)prog;
|
||||
st_get_basic_variant(st, &p->tgsi, &p->variants);
|
||||
st_get_basic_variant(st, PIPE_SHADER_TESS_EVAL, &p->tgsi, &p->variants);
|
||||
break;
|
||||
}
|
||||
|
||||
case GL_GEOMETRY_PROGRAM_NV: {
|
||||
struct st_geometry_program *p = (struct st_geometry_program *)prog;
|
||||
st_get_basic_variant(st, &p->tgsi, &p->variants);
|
||||
st_get_basic_variant(st, PIPE_SHADER_GEOMETRY, &p->tgsi, &p->variants);
|
||||
break;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -352,6 +352,7 @@ st_get_fp_variant(struct st_context *st,
|
|||
|
||||
extern struct st_basic_variant *
|
||||
st_get_basic_variant(struct st_context *st,
|
||||
unsigned pipe_shader,
|
||||
struct pipe_shader_state *tgsi,
|
||||
struct st_basic_variant **variants);
|
||||
|
||||
|
|
|
|||
|
|
@ -38,7 +38,7 @@ libmesautil_la_CPPFLAGS = \
|
|||
-I$(top_srcdir)/src/gallium/auxiliary \
|
||||
$(SHA1_CFLAGS) \
|
||||
$(VISIBILITY_CFLAGS) \
|
||||
$(MSVC2008_COMPAT_CFLAGS)
|
||||
$(MSVC2013_COMPAT_CFLAGS)
|
||||
|
||||
libmesautil_la_SOURCES = \
|
||||
$(MESA_UTIL_FILES) \
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ from sys import executable as python_cmd
|
|||
|
||||
env = env.Clone()
|
||||
|
||||
env.MSVC2008Compat()
|
||||
env.MSVC2013Compat()
|
||||
|
||||
env.Prepend(CPPPATH = [
|
||||
'#include',
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue