ATI Catalyst 9.12: OpenGL and OpenCL Details

With the release of GPU Caps 1.8.0 and the new Catalyst 9.12, it’s time to publish a detailed OpenGL and OpenCL API support.

Catalyst 9.12 is the first display driver to bring OpenGL 3.2 support on Radeon boards. From Cat 9.12 release notes, 11 new OpenGL extensions have been added. Actually some of them are not (still?) exposed.

New exposed extensions (Radeon HD 5870 + Vista SP2 32-bit):

• GL_ARB_vertex_array_bgra
• GL_ARB_draw_elements_base_vertex
• GL_ARB_provoking_vertex
• GL_ARB_texture_multisample
• GL_ARB_depth_clamp
• GL_ARB_geometry_shader4
• GL_ARB_sync
• GL_ARB_seamless_cube_map (also exposed by NV R195.62). There is an extension called GL_AMD_seamless_cubemap_per_texture…
• GL_ARB_texture_cube_map_array (and GL_AMD_texture_cube_map_array): yeah, this ARB extension is not yet exposed by NVIDIA drivers. AMD is on the path to take the OpenGL leadership…

Non exposed extensions:

• GL_ARB_fragment_coord_conventions (exposed by NV R190.56)
• transform_feedback2: NV has the GL_NV_transform_feedback2 extension in R195.62. ATI already supports GL_EXT_transform_feedback so transform_feedback2 should be exposed soon. Maybe thanks to these
  extensions, we’ll be able to debug GLSL shaders with glslDevil on Radeon.

There are also some new GL_AMD_xxx extensions but no documentation is currently available.

1 – Catalyst 9.12 Driver details

Here is the data for a Radeon HD 5870 under Windows Vista SP2 32-bit.

– OpenGL Renderer: ATI Radeon HD 5800 Series
– Vendor: ATI Technologies Inc.
– Vendor ID: 0x1002
– Device ID: 0x6898
– Perf Level 0 – GPU: 157 MHz
– Perf Level 0 – Memory: 300 MHz
– Perf Level 1 – GPU: 600 MHz
– Perf Level 1 – Memory: 900 MHz
– Perf Level 2 – GPU: 850 MHz
– Perf Level 2 – Memory: 1200 MHz
– Drivers Version: 8.681.0.0 – Catalyst 09.12 (11-24-2009) – atioglxx.dll
– ATI Catalyst Version String: 09.12
– ATI Catalyst Release Version String: 8.681-091124a-092498C-ATI
– GPU Codename: Cypress
– GPU Unified Shader Processors: 1600
– Video Memory Size: 1024 MB
– BIOS String: 113-C00101-101

2 – Catalyst 9.12 OpenGL details

– OpenGL Version: 3.2.9232 Compatibility Profile Context
– GLSL (OpenGL Shading Language) Version: 1.50
– ARB Texture Units: 8
– Vertex Shader Texture Units: 16
– Pixel Shader Texture Units: 16
– Geometry Shader Texture Units: 32
– Max Texture Size: 16384×16384
– Max Anisotropic Filtering Value: X16.0
– Max Point Sprite Size: 8192.0
– Max Dynamic Lights: 8
– Max Viewport Size: 16384×16384
– Max Vertex Uniform Components: 1024
– Max Fragment Uniform Components: 1024
– Max Geometry Uniform Components: 4096
– Max Varying Float: 64
– Max Vertex Bindable Uniforms: 15
– Max Fragment Bindable Uniforms: 15
– Max Geometry Bindable Uniforms: 15
– MSAA: 1X
– MSAA: 2X
– MSAA: 4X
– MSAA: 8X

OpenGL Extensions: 176

• GL_AMDX_name_gen_delete
• GL_AMDX_random_access_target
• GL_AMDX_vertex_shader_tessellator
• GL_AMD_draw_buffers_blend
• GL_AMD_performance_monitor
• GL_AMD_seamless_cubemap_per_texture
• GL_AMD_texture_compression_dxt6
• GL_AMD_texture_compression_dxt7
• GL_AMD_texture_cube_map_array
• GL_AMD_texture_texture4
• GL_AMD_vertex_shader_tessellator
• GL_ARB_color_buffer_float
• GL_ARB_copy_buffer
• GL_ARB_depth_buffer_float
• GL_ARB_depth_clamp
• GL_ARB_depth_texture
• GL_ARB_draw_buffers
• GL_ARB_draw_buffers_blend
• GL_ARB_draw_elements_base_vertex
• GL_ARB_draw_instanced
• GL_ARB_fragment_program
• GL_ARB_fragment_program_shadow
• GL_ARB_fragment_shader
• GL_ARB_framebuffer_object
• GL_ARB_framebuffer_sRGB
• GL_ARB_geometry_shader4
• GL_ARB_half_float_pixel
• GL_ARB_half_float_vertex
• GL_ARB_instanced_arrays
• GL_ARB_map_buffer_range
• GL_ARB_multisample
• GL_ARB_multitexture
• GL_ARB_occlusion_query
• GL_ARB_pixel_buffer_object
• GL_ARB_point_parameters
• GL_ARB_point_sprite
• GL_ARB_provoking_vertex
• GL_ARB_sample_shading
• GL_ARB_seamless_cube_map
• GL_ARB_shader_objects
• GL_ARB_shader_texture_lod
• GL_ARB_shading_language_100
• GL_ARB_shadow
• GL_ARB_shadow_ambient
• GL_ARB_sync
• GL_ARB_texture_border_clamp
• GL_ARB_texture_buffer_object
• GL_ARB_texture_compression
• GL_ARB_texture_compression_rgtc
• GL_ARB_texture_cube_map
• GL_ARB_texture_cube_map_array
• GL_ARB_texture_env_add
• GL_ARB_texture_env_combine
• GL_ARB_texture_env_crossbar
• GL_ARB_texture_env_dot3
• GL_ARB_texture_float
• GL_ARB_texture_gather
• GL_ARB_texture_mirrored_repeat
• GL_ARB_texture_multisample
• GL_ARB_texture_non_power_of_two
• GL_ARB_texture_query_lod
• GL_ARB_texture_rectangle
• GL_ARB_texture_rg
• GL_ARB_texture_snorm
• GL_ARB_transpose_matrix
• GL_ARB_uniform_buffer_object
• GL_ARB_vertex_array_bgra
• GL_ARB_vertex_array_object
• GL_ARB_vertex_buffer_object
• GL_ARB_vertex_program
• GL_ARB_vertex_shader
• GL_ARB_window_pos
• GL_ATI_draw_buffers
• GL_ATI_envmap_bumpmap
• GL_ATI_fragment_shader
• GL_ATI_meminfo
• GL_ATI_separate_stencil
• GL_ATI_texture_compression_3dc
• GL_ATI_texture_env_combine3
• GL_ATI_texture_float
• GL_ATI_texture_mirror_once
• GL_EXT_abgr
• GL_EXT_bgra
• GL_EXT_bindable_uniform
• GL_EXT_blend_color
• GL_EXT_blend_equation_separate
• GL_EXT_blend_func_separate
• GL_EXT_blend_minmax
• GL_EXT_blend_subtract
• GL_EXT_compiled_vertex_array
• GL_EXT_copy_buffer
• GL_EXT_copy_texture
• GL_EXT_draw_buffers2
• GL_EXT_draw_instanced
• GL_EXT_draw_range_elements
• GL_EXT_fog_coord
• GL_EXT_framebuffer_blit
• GL_EXT_framebuffer_multisample
• GL_EXT_framebuffer_object
• GL_EXT_framebuffer_sRGB
• GL_EXT_geometry_shader4
• GL_EXT_gpu_program_parameters
• GL_EXT_gpu_shader4
• GL_EXT_multi_draw_arrays
• GL_EXT_packed_depth_stencil
• GL_EXT_packed_float
• GL_EXT_packed_pixels
• GL_EXT_pixel_buffer_object
• GL_EXT_point_parameters
• GL_EXT_provoking_vertex
• GL_EXT_rescale_normal
• GL_EXT_secondary_color
• GL_EXT_separate_specular_color
• GL_EXT_shadow_funcs
• GL_EXT_stencil_wrap
• GL_EXT_subtexture
• GL_EXT_texgen_reflection
• GL_EXT_texture3D
• GL_EXT_texture_array
• GL_EXT_texture_buffer_object
• GL_EXT_texture_compression_latc
• GL_EXT_texture_compression_rgtc
• GL_EXT_texture_compression_s3tc
• GL_EXT_texture_cube_map
• GL_EXT_texture_edge_clamp
• GL_EXT_texture_env_add
• GL_EXT_texture_env_combine
• GL_EXT_texture_env_dot3
• GL_EXT_texture_filter_anisotropic
• GL_EXT_texture_integer
• GL_EXT_texture_lod
• GL_EXT_texture_lod_bias
• GL_EXT_texture_mirror_clamp
• GL_EXT_texture_object
• GL_EXT_texture_rectangle
• GL_EXT_texture_sRGB
• GL_EXT_texture_shared_exponent
• GL_EXT_texture_snorm
• GL_EXT_texture_swizzle
• GL_EXT_timer_query
• GL_EXT_transform_feedback
• GL_EXT_vertex_array
• GL_EXT_vertex_array_bgra
• GL_IBM_texture_mirrored_repeat
• GL_KTX_buffer_region
• GL_NV_blend_square
• GL_NV_conditional_render
• GL_NV_copy_depth_to_color
• GL_NV_explicit_multisample
• GL_NV_primitive_restart
• GL_NV_texgen_reflection
• GL_SGIS_generate_mipmap
• GL_SGIS_texture_edge_clamp
• GL_SGIS_texture_lod
• GL_SUN_multi_draw_arrays
• GL_WIN_swap_hint
• WGL_ARB_extensions_string
• WGL_ARB_pixel_format
• WGL_ATI_pixel_format_float
• WGL_ARB_pixel_format_float
• WGL_ARB_multisample
• WGL_EXT_swap_control
• WGL_ARB_pbuffer
• WGL_ARB_render_texture
• WGL_ARB_make_current_read
• WGL_EXT_extensions_string
• WGL_ARB_buffer_region
• WGL_EXT_framebuffer_sRGB
• WGL_ATI_render_texture_rectangle
• WGL_EXT_pixel_format_packed_float
• WGL_I3D_genlock
• WGL_NV_swap_group
• WGL_ARB_create_context
• WGL_AMD_gpu_association
• WGL_AMDX_gpu_association
• WGL_ARB_create_context_profile

3 – Catalyst 9.12 OpenCL details

– Num OpenCL platforms: 1
– Name: ATI Stream
– Version: OpenCL 1.0 ATI-Stream-v2.0-beta4
– Profile: FULL_PROFILE
– Vendor: Advanced Micro Devices, Inc.
– Num devices: 2

CL_DEVICE_NAME: Intel(R) Core(TM)2 Duo CPU E8400 @ 3.00GHz
– CL_DEVICE_VENDOR: GenuineIntel
– CL_DRIVER_VERSION: 1.0
– CL_DEVICE_PROFILE: FULL_PROFILE
– CL_DEVICE_VERSION: OpenCL 1.0 ATI-Stream-v2.0-beta4
– CL_DEVICE_TYPE: CPU
– CL_DEVICE_VENDOR_ID: 0x1002
– CL_DEVICE_MAX_COMPUTE_UNITS: 2
– CL_DEVICE_MAX_CLOCK_FREQUENCY: 3000MHz
– CL_DEVICE_ADDRESS_BITS: 32
– CL_DEVICE_MAX_MEM_ALLOC_SIZE: 524288KB
– CL_DEVICE_GLOBAL_MEM_SIZE: 1024MB
– CL_DEVICE_MAX_PARAMETER_SIZE: 4096
– CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE: 64 Bytes
– CL_DEVICE_GLOBAL_MEM_CACHE_SIZE: 64KB
– CL_DEVICE_ERROR_CORRECTION_SUPPORT: NO
– CL_DEVICE_LOCAL_MEM_TYPE: Global
– CL_DEVICE_LOCAL_MEM_SIZE: 32KB
– CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 64KB
– CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3
– CL_DEVICE_MAX_WORK_ITEM_SIZES: [1024 ; 1024 ; 1024]
– CL_DEVICE_MAX_WORK_GROUP_SIZE: 1024
– CL_DEVICE_IMAGE_SUPPORT: NO
– CL_DEVICE_MAX_READ_IMAGE_ARGS: 0
– CL_DEVICE_MAX_WRITE_IMAGE_ARGS: 0
– CL_DEVICE_IMAGE2D_MAX_WIDTH: 0
– CL_DEVICE_IMAGE2D_MAX_HEIGHT: 0
– CL_DEVICE_IMAGE3D_MAX_WIDTH: 0
– CL_DEVICE_IMAGE3D_MAX_HEIGHT: 0
– CL_DEVICE_IMAGE3D_MAX_DEPTH: 0
– CL_DEVICE_MAX_SAMPLERS: 0
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR: 16
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT: 8
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT: 4
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG: 2
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT: 4
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE: 0
– CL_DEVICE_EXTENSIONS: 4
– Extensions:
– cl_khr_global_int32_base_atomics
– cl_khr_global_int32_extended_atomics
– cl_khr_local_int32_base_atomics
– cl_khr_local_int32_extended_atomics

CL_DEVICE_NAME: Cypress
– CL_DEVICE_VENDOR: Advanced Micro Devices, Inc.
– CL_DRIVER_VERSION: CAL 1.4.515
– CL_DEVICE_PROFILE: FULL_PROFILE
– CL_DEVICE_VERSION: OpenCL 1.0 ATI-Stream-v2.0-beta4
– CL_DEVICE_TYPE: GPU
– CL_DEVICE_VENDOR_ID: 0x1002
– CL_DEVICE_MAX_COMPUTE_UNITS: 20
– CL_DEVICE_MAX_CLOCK_FREQUENCY: 850MHz
– CL_DEVICE_ADDRESS_BITS: 32
– CL_DEVICE_MAX_MEM_ALLOC_SIZE: 262144KB
– CL_DEVICE_GLOBAL_MEM_SIZE: 256MB
– CL_DEVICE_MAX_PARAMETER_SIZE: 1024
– CL_DEVICE_GLOBAL_MEM_CACHELINE_SIZE: 0 Bytes
– CL_DEVICE_GLOBAL_MEM_CACHE_SIZE: 0KB
– CL_DEVICE_ERROR_CORRECTION_SUPPORT: NO
– CL_DEVICE_LOCAL_MEM_TYPE: Local
– CL_DEVICE_LOCAL_MEM_SIZE: 16KB
– CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 64KB
– CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3
– CL_DEVICE_MAX_WORK_ITEM_SIZES: [256 ; 256 ; 256]
– CL_DEVICE_MAX_WORK_GROUP_SIZE: 256
– CL_DEVICE_IMAGE_SUPPORT: NO
– CL_DEVICE_MAX_READ_IMAGE_ARGS: 0
– CL_DEVICE_MAX_WRITE_IMAGE_ARGS: 0
– CL_DEVICE_IMAGE2D_MAX_WIDTH: 0
– CL_DEVICE_IMAGE2D_MAX_HEIGHT: 0
– CL_DEVICE_IMAGE3D_MAX_WIDTH: 0
– CL_DEVICE_IMAGE3D_MAX_HEIGHT: 0
– CL_DEVICE_IMAGE3D_MAX_DEPTH: 0
– CL_DEVICE_MAX_SAMPLERS: 0
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_CHAR: 16
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_SHORT: 8
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_INT: 4
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_LONG: 2
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_FLOAT: 4
– CL_DEVICE_PREFERRED_VECTOR_WIDTH_DOUBLE: 0
– CL_DEVICE_EXTENSIONS: 0

A more detailed description of each OpenGL extension can be found at the following address:

• OpenGL Extensions @ OpenGL

The extensions exposed by the old Catalyst drivers are HERE.