From c5c38e831ee8113cf97fb5308fbb687464ae2f0e Mon Sep 17 00:00:00 2001
From: Marek Olšák <marek.olsak@amd.com>
Date: Mon, 6 Aug 2018 07:05:19 -0400
Subject: mesa: implement ARB/KHR_parallel_shader_compile

Tested by piglit.
---
 docs/features.txt                       |  2 +-
 docs/relnotes/19.0.0.html               |  2 ++
 src/mapi/glapi/gen/gl_API.xml           | 15 ++++++++++++++-
 src/mesa/main/dd.h                      |  7 +++++++
 src/mesa/main/extensions_table.h        |  2 ++
 src/mesa/main/get_hash_params.py        |  3 +++
 src/mesa/main/hint.c                    | 12 ++++++++++++
 src/mesa/main/hint.h                    |  4 ++++
 src/mesa/main/mtypes.h                  |  1 +
 src/mesa/main/shaderapi.c               | 10 ++++++++++
 src/mesa/main/tests/dispatch_sanity.cpp |  5 +++++
 11 files changed, 61 insertions(+), 2 deletions(-)

diff --git a/docs/features.txt b/docs/features.txt
index 038bbfc45a6..201e600adff 100644
--- a/docs/features.txt
+++ b/docs/features.txt
@@ -302,7 +302,7 @@ Khronos, ARB, and OES extensions that are not part of any OpenGL or OpenGL ES ve
   GL_ARB_ES3_2_compatibility                            DONE (i965/gen8+, radeonsi, virgl)
   GL_ARB_fragment_shader_interlock                      DONE (i965)
   GL_ARB_gpu_shader_int64                               DONE (i965/gen8+, nvc0, radeonsi, softpipe, llvmpipe)
-  GL_ARB_parallel_shader_compile                        not started, but Chia-I Wu did some related work in 2014
+  GL_ARB_parallel_shader_compile                        DONE (all drivers)
   GL_ARB_post_depth_coverage                            DONE (i965, nvc0)
   GL_ARB_robustness_isolation                           not started
   GL_ARB_sample_locations                               DONE (nvc0)
diff --git a/docs/relnotes/19.0.0.html b/docs/relnotes/19.0.0.html
index ea22d660f37..b0a3cc6c29f 100644
--- a/docs/relnotes/19.0.0.html
+++ b/docs/relnotes/19.0.0.html
@@ -41,11 +41,13 @@ Compatibility contexts may report a lower version depending on each driver.
 
 <ul>
 <li>GL_AMD_texture_texture4 on all GL 4.0 drivers.</li>
+<li>GL_ARB_parallel_shader_compile on all drivers.</li>
 <li>GL_EXT_shader_implicit_conversions on all drivers (ES extension).</li>
 <li>GL_EXT_texture_compression_bptc on all GL 4.0 drivers (ES extension).</li>
 <li>GL_EXT_texture_compression_rgtc on all GL 3.0 drivers (ES extension).</li>
 <li>GL_EXT_render_snorm on gallium drivers (ES extension).</li>
 <li>GL_EXT_texture_view on drivers supporting texture views (ES extension).</li>
+<li>GL_KHR_parallel_shader_compile on all drivers.</li>
 <li>GL_OES_texture_view on drivers supporting texture views (ES extension).</li>
 <li>GL_NV_shader_atomic_float on nvc0 (Fermi/Kepler only).</li>
 <li>Shader-based software implementations of GL_ARB_gpu_shader_fp64, GL_ARB_gpu_shader_int64, GL_ARB_vertex_attrib_64bit, and GL_ARB_shader_ballot on i965.</li>
diff --git a/src/mapi/glapi/gen/gl_API.xml b/src/mapi/glapi/gen/gl_API.xml
index 929e5f6b024..9b8998532d5 100644
--- a/src/mapi/glapi/gen/gl_API.xml
+++ b/src/mapi/glapi/gen/gl_API.xml
@@ -8400,7 +8400,20 @@
 
 <xi:include href="ARB_gpu_shader_int64.xml" xmlns:xi="http://www.w3.org/2001/XInclude"/>
 
-<!-- ARB extension 179 - 189 -->
+<category name="ARB_parallel_shader_compile" number="179">
+    <enum name="MAX_SHADER_COMPILER_THREADS_ARB"   value="0x91B0"/>
+    <enum name="COMPLETION_STATUS_ARB"             value="0x91B1"/>
+
+    <function name="MaxShaderCompilerThreadsKHR" es2="2.0">
+        <param name="count" type="GLuint"/>
+    </function>
+
+    <function name="MaxShaderCompilerThreadsARB" alias="MaxShaderCompilerThreadsKHR">
+        <param name="count" type="GLuint"/>
+    </function>
+</category>
+
+<!-- ARB extension 180 - 189 -->
 
 <xi:include href="ARB_gl_spirv.xml" xmlns:xi="http://www.w3.org/2001/XInclude"/>
 
diff --git a/src/mesa/main/dd.h b/src/mesa/main/dd.h
index 1214eeaa474..8251af3f667 100644
--- a/src/mesa/main/dd.h
+++ b/src/mesa/main/dd.h
@@ -1298,6 +1298,13 @@ struct dd_function_table {
    void (*ShaderCacheSerializeDriverBlob)(struct gl_context *ctx,
                                           struct gl_program *prog);
    /*@}*/
+
+   /**
+    * \name Set the number of compiler threads for ARB_parallel_shader_compile
+    */
+   void (*SetMaxShaderCompilerThreads)(struct gl_context *ctx, unsigned count);
+   bool (*GetShaderProgramCompletionStatus)(struct gl_context *ctx,
+                                            struct gl_shader_program *shprog);
 };
 
 
diff --git a/src/mesa/main/extensions_table.h b/src/mesa/main/extensions_table.h
index a9773f701b6..f7eb62108f2 100644
--- a/src/mesa/main/extensions_table.h
+++ b/src/mesa/main/extensions_table.h
@@ -99,6 +99,7 @@ EXT(ARB_multisample                         , dummy_true
 EXT(ARB_multitexture                        , dummy_true                             , GLL,  x ,  x ,  x , 1998)
 EXT(ARB_occlusion_query                     , ARB_occlusion_query                    , GLL,  x ,  x ,  x , 2001)
 EXT(ARB_occlusion_query2                    , ARB_occlusion_query2                   , GLL, GLC,  x ,  x , 2003)
+EXT(ARB_parallel_shader_compile             , dummy_true                             , GLL, GLC,  x ,  x , 2015)
 EXT(ARB_pipeline_statistics_query           , ARB_pipeline_statistics_query          , GLL, GLC,  x ,  x , 2014)
 EXT(ARB_pixel_buffer_object                 , EXT_pixel_buffer_object                , GLL, GLC,  x ,  x , 2004)
 EXT(ARB_point_parameters                    , EXT_point_parameters                   , GLL,  x ,  x ,  x , 1997)
@@ -337,6 +338,7 @@ EXT(KHR_blend_equation_advanced_coherent    , KHR_blend_equation_advanced_cohere
 EXT(KHR_context_flush_control               , dummy_true                             , GLL, GLC,  x , ES2, 2014)
 EXT(KHR_debug                               , dummy_true                             , GLL, GLC,  11, ES2, 2012)
 EXT(KHR_no_error                            , dummy_true                             , GLL, GLC, ES1, ES2, 2015)
+EXT(KHR_parallel_shader_compile             , dummy_true                             , GLL, GLC,  x , ES2, 2017)
 EXT(KHR_robust_buffer_access_behavior       , ARB_robust_buffer_access_behavior      , GLL, GLC,  x , ES2, 2014)
 EXT(KHR_robustness                          , KHR_robustness                         , GLL, GLC,  x , ES2, 2012)
 EXT(KHR_texture_compression_astc_hdr        , KHR_texture_compression_astc_hdr       , GLL, GLC,  x , ES2, 2012)
diff --git a/src/mesa/main/get_hash_params.py b/src/mesa/main/get_hash_params.py
index 8b351bcd2d2..60ec1a8598c 100644
--- a/src/mesa/main/get_hash_params.py
+++ b/src/mesa/main/get_hash_params.py
@@ -280,6 +280,9 @@ descriptor=[
 # GL_ARB_draw_buffers
   [ "MAX_DRAW_BUFFERS_ARB", "CONTEXT_INT(Const.MaxDrawBuffers), NO_EXTRA" ],
 
+# GL_ARB_parallel_shader_compile
+  [ "MAX_SHADER_COMPILER_THREADS_ARB", "CONTEXT_INT(Hint.MaxShaderCompilerThreads), NO_EXTRA" ],
+
 # GL_EXT_framebuffer_object / GL_NV_fbo_color_attachments
   [ "MAX_COLOR_ATTACHMENTS", "CONTEXT_INT(Const.MaxColorAttachments), NO_EXTRA" ],
 
diff --git a/src/mesa/main/hint.c b/src/mesa/main/hint.c
index 5d0c15d35ab..2bcaeebc4aa 100644
--- a/src/mesa/main/hint.c
+++ b/src/mesa/main/hint.c
@@ -130,6 +130,17 @@ invalid_target:
    return;
 }
 
+/* GL_ARB_parallel_shader_compile */
+void GLAPIENTRY
+_mesa_MaxShaderCompilerThreadsKHR(GLuint count)
+{
+   GET_CURRENT_CONTEXT(ctx);
+
+   ctx->Hint.MaxShaderCompilerThreads = count;
+
+   if (ctx->Driver.SetMaxShaderCompilerThreads)
+      ctx->Driver.SetMaxShaderCompilerThreads(ctx, count);
+}
 
 /**********************************************************************/
 /*****                      Initialization                        *****/
@@ -146,4 +157,5 @@ void _mesa_init_hint( struct gl_context * ctx )
    ctx->Hint.TextureCompression = GL_DONT_CARE;
    ctx->Hint.GenerateMipmap = GL_DONT_CARE;
    ctx->Hint.FragmentShaderDerivative = GL_DONT_CARE;
+   ctx->Hint.MaxShaderCompilerThreads = 0xffffffff;
 }
diff --git a/src/mesa/main/hint.h b/src/mesa/main/hint.h
index 87febfeecc0..2d7c710af26 100644
--- a/src/mesa/main/hint.h
+++ b/src/mesa/main/hint.h
@@ -43,6 +43,10 @@ struct gl_context;
 extern void GLAPIENTRY
 _mesa_Hint( GLenum target, GLenum mode );
 
+/* GL_KHR_parallel_shader_compile */
+extern void GLAPIENTRY
+_mesa_MaxShaderCompilerThreadsKHR(GLuint count);
+
 extern void 
 _mesa_init_hint( struct gl_context * ctx );
 
diff --git a/src/mesa/main/mtypes.h b/src/mesa/main/mtypes.h
index 96f30d4a4d5..c1dc52b2ec4 100644
--- a/src/mesa/main/mtypes.h
+++ b/src/mesa/main/mtypes.h
@@ -603,6 +603,7 @@ struct gl_hint_attrib
    GLenum16 TextureCompression;   /**< GL_ARB_texture_compression */
    GLenum16 GenerateMipmap;       /**< GL_SGIS_generate_mipmap */
    GLenum16 FragmentShaderDerivative; /**< GL_ARB_fragment_shader */
+   GLuint MaxShaderCompilerThreads; /**< GL_ARB_parallel_shader_compile */
 };
 
 
diff --git a/src/mesa/main/shaderapi.c b/src/mesa/main/shaderapi.c
index 2ea8d965aba..01342c04e8f 100644
--- a/src/mesa/main/shaderapi.c
+++ b/src/mesa/main/shaderapi.c
@@ -689,6 +689,12 @@ get_programiv(struct gl_context *ctx, GLuint program, GLenum pname,
    case GL_DELETE_STATUS:
       *params = shProg->DeletePending;
       return;
+   case GL_COMPLETION_STATUS_ARB:
+      if (ctx->Driver.GetShaderProgramCompletionStatus)
+         *params = ctx->Driver.GetShaderProgramCompletionStatus(ctx, shProg);
+      else
+         *params = GL_TRUE;
+      return;
    case GL_LINK_STATUS:
       *params = shProg->data->LinkStatus ? GL_TRUE : GL_FALSE;
       return;
@@ -960,6 +966,10 @@ get_shaderiv(struct gl_context *ctx, GLuint name, GLenum pname, GLint *params)
    case GL_DELETE_STATUS:
       *params = shader->DeletePending;
       break;
+   case GL_COMPLETION_STATUS_ARB:
+      /* _mesa_glsl_compile_shader is not offloaded to other threads. */
+      *params = GL_TRUE;
+      return;
    case GL_COMPILE_STATUS:
       *params = shader->CompileStatus ? GL_TRUE : GL_FALSE;
       break;
diff --git a/src/mesa/main/tests/dispatch_sanity.cpp b/src/mesa/main/tests/dispatch_sanity.cpp
index 672e4ce892a..37edfee587d 100644
--- a/src/mesa/main/tests/dispatch_sanity.cpp
+++ b/src/mesa/main/tests/dispatch_sanity.cpp
@@ -1198,6 +1198,8 @@ const struct function common_desktop_functions_possible[] = {
    { "glRenderbufferStorageMultisampleAdvancedAMD", 11, -1 },
    { "glNamedRenderbufferStorageMultisampleAdvancedAMD", 11, -1 },
 
+   { "glMaxShaderCompilerThreadsKHR", 11, -1 },
+
    { NULL, 0, -1 }
 };
 
@@ -2244,6 +2246,9 @@ const struct function gles2_functions_possible[] = {
    { "glRenderbufferStorageMultisampleEXT", 20, -1 },
    { "glFramebufferTexture2DMultisampleEXT", 20, -1 },
 
+   /* GL_KHR_parallel_shader_compile */
+   { "glMaxShaderCompilerThreadsKHR", 20, -1 },
+
    { NULL, 0, -1 }
 };
 
-- 
cgit v1.2.3