From 806a792b438815ec6ae15cdb0e6fedcaf7db2dd0 Mon Sep 17 00:00:00 2001 From: Bas Nieuwenhuizen Date: Sat, 11 Aug 2018 23:26:26 +0200 Subject: [PATCH] radv: Make fs key exemplars ordered to be a reverse fs_key lookup. While at it, share the exemplars and account for a non-occurring fs key. Reviewed-by: Dave Airlie --- src/amd/vulkan/radv_meta_blit.c | 21 +++------------------ src/amd/vulkan/radv_meta_blit2d.c | 19 ++----------------- src/amd/vulkan/radv_meta_clear.c | 19 ++----------------- src/amd/vulkan/radv_meta_resolve.c | 19 ++----------------- src/amd/vulkan/radv_meta_resolve_fs.c | 19 ++----------------- src/amd/vulkan/radv_pipeline.c | 27 ++++++++++++++++++++++++++- src/amd/vulkan/radv_private.h | 3 ++- 7 files changed, 39 insertions(+), 88 deletions(-) diff --git a/src/amd/vulkan/radv_meta_blit.c b/src/amd/vulkan/radv_meta_blit.c index 67c26aabdb3..f68496d3202 100644 --- a/src/amd/vulkan/radv_meta_blit.c +++ b/src/amd/vulkan/radv_meta_blit.c @@ -714,21 +714,6 @@ radv_device_finish_meta_blit_state(struct radv_device *device) state->blit.ds_layout, &state->alloc); } -static VkFormat pipeline_formats[] = { - VK_FORMAT_R8G8B8A8_UNORM, - VK_FORMAT_R8G8B8A8_UINT, - VK_FORMAT_R8G8B8A8_SINT, - VK_FORMAT_A2R10G10B10_UINT_PACK32, - VK_FORMAT_A2R10G10B10_SINT_PACK32, - VK_FORMAT_R16G16B16A16_UNORM, - VK_FORMAT_R16G16B16A16_SNORM, - VK_FORMAT_R16G16B16A16_UINT, - VK_FORMAT_R16G16B16A16_SINT, - VK_FORMAT_R32_SFLOAT, - VK_FORMAT_R32G32_SFLOAT, - VK_FORMAT_R32G32B32A32_SFLOAT -}; - static VkResult radv_device_init_meta_blit_color(struct radv_device *device, struct radv_shader_module *vs) @@ -740,8 +725,8 @@ radv_device_init_meta_blit_color(struct radv_device *device, fs_2d.nir = build_nir_copy_fragment_shader(GLSL_SAMPLER_DIM_2D); fs_3d.nir = build_nir_copy_fragment_shader(GLSL_SAMPLER_DIM_3D); - for (unsigned i = 0; i < ARRAY_SIZE(pipeline_formats); ++i) { - unsigned key = radv_format_meta_fs_key(pipeline_formats[i]); + for (unsigned i = 0; i < NUM_META_FS_KEYS; ++i) { + unsigned key = radv_format_meta_fs_key(radv_fs_key_format_exemplars[i]); for(unsigned j = 0; j < RADV_META_DST_LAYOUT_COUNT; ++j) { VkImageLayout layout = radv_meta_dst_layout_to_layout(j); result = radv_CreateRenderPass(radv_device_to_handle(device), @@ -749,7 +734,7 @@ radv_device_init_meta_blit_color(struct radv_device *device, .sType = VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO, .attachmentCount = 1, .pAttachments = &(VkAttachmentDescription) { - .format = pipeline_formats[i], + .format = radv_fs_key_format_exemplars[i], .loadOp = VK_ATTACHMENT_LOAD_OP_LOAD, .storeOp = VK_ATTACHMENT_STORE_OP_STORE, .initialLayout = layout, diff --git a/src/amd/vulkan/radv_meta_blit2d.c b/src/amd/vulkan/radv_meta_blit2d.c index cac0a4dd55f..79652856942 100644 --- a/src/amd/vulkan/radv_meta_blit2d.c +++ b/src/amd/vulkan/radv_meta_blit2d.c @@ -1239,21 +1239,6 @@ blit2d_init_stencil_only_pipeline(struct radv_device *device, return result; } -static VkFormat pipeline_formats[] = { - VK_FORMAT_R8G8B8A8_UNORM, - VK_FORMAT_R8G8B8A8_UINT, - VK_FORMAT_R8G8B8A8_SINT, - VK_FORMAT_A2R10G10B10_UINT_PACK32, - VK_FORMAT_A2R10G10B10_SINT_PACK32, - VK_FORMAT_R16G16B16A16_UNORM, - VK_FORMAT_R16G16B16A16_SNORM, - VK_FORMAT_R16G16B16A16_UINT, - VK_FORMAT_R16G16B16A16_SINT, - VK_FORMAT_R32_SFLOAT, - VK_FORMAT_R32G32_SFLOAT, - VK_FORMAT_R32G32B32A32_SFLOAT -}; - static VkResult meta_blit2d_create_pipe_layout(struct radv_device *device, int idx, @@ -1320,8 +1305,8 @@ radv_device_init_meta_blit2d_state(struct radv_device *device) if (result != VK_SUCCESS) goto fail; - for (unsigned j = 0; j < ARRAY_SIZE(pipeline_formats); ++j) { - result = blit2d_init_color_pipeline(device, src, pipeline_formats[j], log2_samples); + for (unsigned j = 0; j < NUM_META_FS_KEYS; ++j) { + result = blit2d_init_color_pipeline(device, src, radv_fs_key_format_exemplars[j], log2_samples); if (result != VK_SUCCESS) goto fail; } diff --git a/src/amd/vulkan/radv_meta_clear.c b/src/amd/vulkan/radv_meta_clear.c index d7c98497343..4f77e32b83f 100644 --- a/src/amd/vulkan/radv_meta_clear.c +++ b/src/amd/vulkan/radv_meta_clear.c @@ -757,21 +757,6 @@ fail: return false; } -static VkFormat pipeline_formats[] = { - VK_FORMAT_R8G8B8A8_UNORM, - VK_FORMAT_R8G8B8A8_UINT, - VK_FORMAT_R8G8B8A8_SINT, - VK_FORMAT_A2R10G10B10_UINT_PACK32, - VK_FORMAT_A2R10G10B10_SINT_PACK32, - VK_FORMAT_R16G16B16A16_UNORM, - VK_FORMAT_R16G16B16A16_SNORM, - VK_FORMAT_R16G16B16A16_UINT, - VK_FORMAT_R16G16B16A16_SINT, - VK_FORMAT_R32_SFLOAT, - VK_FORMAT_R32G32_SFLOAT, - VK_FORMAT_R32G32B32A32_SFLOAT -}; - VkResult radv_device_init_meta_clear_state(struct radv_device *device) { @@ -808,8 +793,8 @@ radv_device_init_meta_clear_state(struct radv_device *device) for (uint32_t i = 0; i < ARRAY_SIZE(state->clear); ++i) { uint32_t samples = 1 << i; - for (uint32_t j = 0; j < ARRAY_SIZE(pipeline_formats); ++j) { - VkFormat format = pipeline_formats[j]; + for (uint32_t j = 0; j < NUM_META_FS_KEYS; ++j) { + VkFormat format = radv_fs_key_format_exemplars[j]; unsigned fs_key = radv_format_meta_fs_key(format); assert(!state->clear[i].color_pipelines[fs_key]); diff --git a/src/amd/vulkan/radv_meta_resolve.c b/src/amd/vulkan/radv_meta_resolve.c index b049237ba65..30fed974414 100644 --- a/src/amd/vulkan/radv_meta_resolve.c +++ b/src/amd/vulkan/radv_meta_resolve.c @@ -251,21 +251,6 @@ radv_device_finish_meta_resolve_state(struct radv_device *device) } -static VkFormat pipeline_formats[] = { - VK_FORMAT_R8G8B8A8_UNORM, - VK_FORMAT_R8G8B8A8_UINT, - VK_FORMAT_R8G8B8A8_SINT, - VK_FORMAT_A2R10G10B10_UINT_PACK32, - VK_FORMAT_A2R10G10B10_SINT_PACK32, - VK_FORMAT_R16G16B16A16_UNORM, - VK_FORMAT_R16G16B16A16_SNORM, - VK_FORMAT_R16G16B16A16_UINT, - VK_FORMAT_R16G16B16A16_SINT, - VK_FORMAT_R32_SFLOAT, - VK_FORMAT_R32G32_SFLOAT, - VK_FORMAT_R32G32B32A32_SFLOAT -}; - VkResult radv_device_init_meta_resolve_state(struct radv_device *device) { @@ -278,8 +263,8 @@ radv_device_init_meta_resolve_state(struct radv_device *device) goto fail; } - for (uint32_t i = 0; i < ARRAY_SIZE(pipeline_formats); ++i) { - VkFormat format = pipeline_formats[i]; + for (uint32_t i = 0; i < NUM_META_FS_KEYS; ++i) { + VkFormat format = radv_fs_key_format_exemplars[i]; unsigned fs_key = radv_format_meta_fs_key(format); res = create_pass(device, format, &state->resolve.pass[fs_key]); if (res != VK_SUCCESS) diff --git a/src/amd/vulkan/radv_meta_resolve_fs.c b/src/amd/vulkan/radv_meta_resolve_fs.c index 76f00bfb5e3..6013503b837 100644 --- a/src/amd/vulkan/radv_meta_resolve_fs.c +++ b/src/amd/vulkan/radv_meta_resolve_fs.c @@ -156,21 +156,6 @@ static const VkPipelineVertexInputStateCreateInfo normal_vi_create_info = { .vertexAttributeDescriptionCount = 0, }; -static VkFormat pipeline_formats[] = { - VK_FORMAT_R8G8B8A8_UNORM, - VK_FORMAT_R8G8B8A8_UINT, - VK_FORMAT_R8G8B8A8_SINT, - VK_FORMAT_A2R10G10B10_UINT_PACK32, - VK_FORMAT_A2R10G10B10_SINT_PACK32, - VK_FORMAT_R16G16B16A16_UNORM, - VK_FORMAT_R16G16B16A16_SNORM, - VK_FORMAT_R16G16B16A16_UINT, - VK_FORMAT_R16G16B16A16_SINT, - VK_FORMAT_R32_SFLOAT, - VK_FORMAT_R32G32_SFLOAT, - VK_FORMAT_R32G32B32A32_SFLOAT -}; - static VkResult create_resolve_pipeline(struct radv_device *device, int samples_log2, @@ -335,8 +320,8 @@ radv_device_init_meta_resolve_fragment_state(struct radv_device *device) goto fail; for (uint32_t i = 0; i < MAX_SAMPLES_LOG2; ++i) { - for (unsigned j = 0; j < ARRAY_SIZE(pipeline_formats); ++j) { - res = create_resolve_pipeline(device, i, pipeline_formats[j]); + for (unsigned j = 0; j < NUM_META_FS_KEYS; ++j) { + res = create_resolve_pipeline(device, i, radv_fs_key_format_exemplars[j]); if (res != VK_SUCCESS) goto fail; } diff --git a/src/amd/vulkan/radv_pipeline.c b/src/amd/vulkan/radv_pipeline.c index eb58e8a1c0a..e63c481d1e7 100644 --- a/src/amd/vulkan/radv_pipeline.c +++ b/src/amd/vulkan/radv_pipeline.c @@ -565,9 +565,34 @@ format_is_int10(VkFormat format) return false; } +/* + * Ordered so that for each i, + * radv_format_meta_fs_key(radv_fs_key_format_exemplars[i]) == i. + */ +const VkFormat radv_fs_key_format_exemplars[NUM_META_FS_KEYS] = { + VK_FORMAT_R32_SFLOAT, + VK_FORMAT_R32G32_SFLOAT, + VK_FORMAT_R8G8B8A8_UNORM, + VK_FORMAT_R16G16B16A16_UNORM, + VK_FORMAT_R16G16B16A16_SNORM, + VK_FORMAT_R16G16B16A16_UINT, + VK_FORMAT_R16G16B16A16_SINT, + VK_FORMAT_R32G32B32A32_SFLOAT, + VK_FORMAT_R8G8B8A8_UINT, + VK_FORMAT_R8G8B8A8_SINT, + VK_FORMAT_A2R10G10B10_UINT_PACK32, + VK_FORMAT_A2R10G10B10_SINT_PACK32, +}; + unsigned radv_format_meta_fs_key(VkFormat format) { - unsigned col_format = si_choose_spi_color_format(format, false, false) - 1; + unsigned col_format = si_choose_spi_color_format(format, false, false); + + assert(col_format != V_028714_SPI_SHADER_32_AR); + if (col_format >= V_028714_SPI_SHADER_32_AR) + --col_format; /* Skip V_028714_SPI_SHADER_32_AR since there is no such VkFormat */ + + --col_format; /* Skip V_028714_SPI_SHADER_ZERO */ bool is_int8 = format_is_int8(format); bool is_int10 = format_is_int10(format); diff --git a/src/amd/vulkan/radv_private.h b/src/amd/vulkan/radv_private.h index a187f76be49..9374b730b52 100644 --- a/src/amd/vulkan/radv_private.h +++ b/src/amd/vulkan/radv_private.h @@ -96,7 +96,7 @@ typedef uint32_t xcb_window_t; #define MAX_DYNAMIC_STORAGE_BUFFERS 8 #define MAX_DYNAMIC_BUFFERS (MAX_DYNAMIC_UNIFORM_BUFFERS + MAX_DYNAMIC_STORAGE_BUFFERS) #define MAX_SAMPLES_LOG2 4 -#define NUM_META_FS_KEYS 13 +#define NUM_META_FS_KEYS 12 #define RADV_MAX_DRM_DEVICES 8 #define MAX_VIEWS 8 @@ -1242,6 +1242,7 @@ mesa_to_vk_shader_stage(gl_shader_stage mesa_stage) stage = __builtin_ffs(__tmp) - 1, __tmp; \ __tmp &= ~(1 << (stage))) +extern const VkFormat radv_fs_key_format_exemplars[NUM_META_FS_KEYS]; unsigned radv_format_meta_fs_key(VkFormat format); struct radv_multisample_state { -- 2.30.2