1/* 2 * Copyright 2015 Intel Corporation 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice (including the next 12 * paragraph) shall be included in all copies or substantial portions of the 13 * Software. 14 * 15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS 21 * IN THE SOFTWARE. 22 */ 23 24#include "isl_priv.h" 25#include "compiler/brw_compiler.h" 26 27bool 28isl_is_storage_image_format(enum isl_format format) 29{ 30 /* XXX: Maybe we should put this in the CSV? */ 31 32 switch (format) { 33 case ISL_FORMAT_R32G32B32A32_UINT: 34 case ISL_FORMAT_R32G32B32A32_SINT: 35 case ISL_FORMAT_R32G32B32A32_FLOAT: 36 case ISL_FORMAT_R32_UINT: 37 case ISL_FORMAT_R32_SINT: 38 case ISL_FORMAT_R32_FLOAT: 39 case ISL_FORMAT_R16G16B16A16_UINT: 40 case ISL_FORMAT_R16G16B16A16_SINT: 41 case ISL_FORMAT_R16G16B16A16_FLOAT: 42 case ISL_FORMAT_R32G32_UINT: 43 case ISL_FORMAT_R32G32_SINT: 44 case ISL_FORMAT_R32G32_FLOAT: 45 case ISL_FORMAT_R8G8B8A8_UINT: 46 case ISL_FORMAT_R8G8B8A8_SINT: 47 case ISL_FORMAT_R16G16_UINT: 48 case ISL_FORMAT_R16G16_SINT: 49 case ISL_FORMAT_R16G16_FLOAT: 50 case ISL_FORMAT_R8G8_UINT: 51 case ISL_FORMAT_R8G8_SINT: 52 case ISL_FORMAT_R16_UINT: 53 case ISL_FORMAT_R16_FLOAT: 54 case ISL_FORMAT_R16_SINT: 55 case ISL_FORMAT_R8_UINT: 56 case ISL_FORMAT_R8_SINT: 57 case ISL_FORMAT_R10G10B10A2_UINT: 58 case ISL_FORMAT_R10G10B10A2_UNORM: 59 case ISL_FORMAT_R11G11B10_FLOAT: 60 case ISL_FORMAT_R16G16B16A16_UNORM: 61 case ISL_FORMAT_R16G16B16A16_SNORM: 62 case ISL_FORMAT_R8G8B8A8_UNORM: 63 case ISL_FORMAT_R8G8B8A8_SNORM: 64 case ISL_FORMAT_R16G16_UNORM: 65 case ISL_FORMAT_R16G16_SNORM: 66 case ISL_FORMAT_R8G8_UNORM: 67 case ISL_FORMAT_R8G8_SNORM: 68 case ISL_FORMAT_R16_UNORM: 69 case ISL_FORMAT_R16_SNORM: 70 case ISL_FORMAT_R8_UNORM: 71 case ISL_FORMAT_R8_SNORM: 72 return true; 73 default: 74 return false; 75 } 76} 77 78enum isl_format 79isl_lower_storage_image_format(const struct intel_device_info *devinfo, 80 enum isl_format format) 81{ 82 switch (format) { 83 /* These are never lowered. Up to BDW we'll have to fall back to untyped 84 * surface access for 128bpp formats. 85 */ 86 case ISL_FORMAT_R32G32B32A32_UINT: 87 case ISL_FORMAT_R32G32B32A32_SINT: 88 case ISL_FORMAT_R32G32B32A32_FLOAT: 89 case ISL_FORMAT_R32_UINT: 90 case ISL_FORMAT_R32_SINT: 91 return format; 92 93 /* The Skylake PRM's "Surface Formats" section says: 94 * 95 * "The surface format for the typed atomic integer operations must 96 * be R32_UINT or R32_SINT." 97 */ 98 case ISL_FORMAT_R32_FLOAT: 99 return ISL_FORMAT_R32_UINT; 100 101 /* From HSW to BDW the only 64bpp format supported for typed access is 102 * RGBA_UINT16. IVB falls back to untyped. 103 */ 104 case ISL_FORMAT_R16G16B16A16_UINT: 105 case ISL_FORMAT_R16G16B16A16_SINT: 106 case ISL_FORMAT_R16G16B16A16_FLOAT: 107 case ISL_FORMAT_R32G32_UINT: 108 case ISL_FORMAT_R32G32_SINT: 109 case ISL_FORMAT_R32G32_FLOAT: 110 return (devinfo->ver >= 9 ? format : 111 devinfo->verx10 >= 75 ? 112 ISL_FORMAT_R16G16B16A16_UINT : 113 ISL_FORMAT_R32G32_UINT); 114 115 /* Up to BDW no SINT or FLOAT formats of less than 32 bits per component 116 * are supported. IVB doesn't support formats with more than one component 117 * for typed access. For 8 and 16 bpp formats IVB relies on the 118 * undocumented behavior that typed reads from R_UINT8 and R_UINT16 119 * surfaces actually do a 32-bit misaligned read. The alternative would be 120 * to use two surface state entries with different formats for each image, 121 * one for reading (using R_UINT32) and another one for writing (using 122 * R_UINT8 or R_UINT16), but that would complicate the shaders we generate 123 * even more. 124 */ 125 case ISL_FORMAT_R8G8B8A8_UINT: 126 case ISL_FORMAT_R8G8B8A8_SINT: 127 return (devinfo->ver >= 9 ? format : 128 devinfo->verx10 >= 75 ? 129 ISL_FORMAT_R8G8B8A8_UINT : ISL_FORMAT_R32_UINT); 130 131 case ISL_FORMAT_R16G16_UINT: 132 case ISL_FORMAT_R16G16_SINT: 133 case ISL_FORMAT_R16G16_FLOAT: 134 return (devinfo->ver >= 9 ? format : 135 devinfo->verx10 >= 75 ? 136 ISL_FORMAT_R16G16_UINT : ISL_FORMAT_R32_UINT); 137 138 case ISL_FORMAT_R8G8_UINT: 139 case ISL_FORMAT_R8G8_SINT: 140 return (devinfo->ver >= 9 ? format : 141 devinfo->verx10 >= 75 ? 142 ISL_FORMAT_R8G8_UINT : ISL_FORMAT_R16_UINT); 143 144 case ISL_FORMAT_R16_UINT: 145 case ISL_FORMAT_R16_FLOAT: 146 case ISL_FORMAT_R16_SINT: 147 return (devinfo->ver >= 9 ? format : ISL_FORMAT_R16_UINT); 148 149 case ISL_FORMAT_R8_UINT: 150 case ISL_FORMAT_R8_SINT: 151 return (devinfo->ver >= 9 ? format : ISL_FORMAT_R8_UINT); 152 153 /* Neither the 2/10/10/10 nor the 11/11/10 packed formats are supported 154 * by the hardware. 155 */ 156 case ISL_FORMAT_R10G10B10A2_UINT: 157 case ISL_FORMAT_R10G10B10A2_UNORM: 158 case ISL_FORMAT_R11G11B10_FLOAT: 159 return ISL_FORMAT_R32_UINT; 160 161 /* No normalized fixed-point formats are supported by the hardware. */ 162 case ISL_FORMAT_R16G16B16A16_UNORM: 163 case ISL_FORMAT_R16G16B16A16_SNORM: 164 return (devinfo->ver >= 11 ? format : 165 devinfo->verx10 >= 75 ? 166 ISL_FORMAT_R16G16B16A16_UINT : 167 ISL_FORMAT_R32G32_UINT); 168 169 case ISL_FORMAT_R8G8B8A8_UNORM: 170 case ISL_FORMAT_R8G8B8A8_SNORM: 171 return (devinfo->ver >= 11 ? format : 172 devinfo->verx10 >= 75 ? 173 ISL_FORMAT_R8G8B8A8_UINT : ISL_FORMAT_R32_UINT); 174 175 case ISL_FORMAT_R16G16_UNORM: 176 case ISL_FORMAT_R16G16_SNORM: 177 return (devinfo->ver >= 11 ? format : 178 devinfo->verx10 >= 75 ? 179 ISL_FORMAT_R16G16_UINT : ISL_FORMAT_R32_UINT); 180 181 case ISL_FORMAT_R8G8_UNORM: 182 case ISL_FORMAT_R8G8_SNORM: 183 return (devinfo->ver >= 11 ? format : 184 devinfo->verx10 >= 75 ? 185 ISL_FORMAT_R8G8_UINT : ISL_FORMAT_R16_UINT); 186 187 case ISL_FORMAT_R16_UNORM: 188 case ISL_FORMAT_R16_SNORM: 189 return (devinfo->ver >= 11 ? format : ISL_FORMAT_R16_UINT); 190 191 case ISL_FORMAT_R8_UNORM: 192 case ISL_FORMAT_R8_SNORM: 193 return (devinfo->ver >= 11 ? format : ISL_FORMAT_R8_UINT); 194 195 default: 196 assert(!"Unknown image format"); 197 return ISL_FORMAT_UNSUPPORTED; 198 } 199} 200 201bool 202isl_has_matching_typed_storage_image_format(const struct intel_device_info *devinfo, 203 enum isl_format fmt) 204{ 205 if (devinfo->ver >= 9) { 206 return true; 207 } else if (devinfo->verx10 >= 75) { 208 return isl_format_get_layout(fmt)->bpb <= 64; 209 } else { 210 return isl_format_get_layout(fmt)->bpb <= 32; 211 } 212} 213 214static const struct brw_image_param image_param_defaults = { 215 /* Set the swizzling shifts to all-ones to effectively disable 216 * swizzling -- See emit_address_calculation() in 217 * brw_fs_surface_builder.cpp for a more detailed explanation of 218 * these parameters. 219 */ 220 .swizzling = { 0xff, 0xff }, 221}; 222 223void 224isl_surf_fill_image_param(const struct isl_device *dev, 225 struct brw_image_param *param, 226 const struct isl_surf *surf, 227 const struct isl_view *view) 228{ 229 *param = image_param_defaults; 230 231 if (surf->dim != ISL_SURF_DIM_3D) { 232 assert(view->base_array_layer + view->array_len <= 233 surf->logical_level0_px.array_len); 234 } 235 param->size[0] = isl_minify(surf->logical_level0_px.w, view->base_level); 236 param->size[1] = surf->dim == ISL_SURF_DIM_1D ? 237 view->array_len : 238 isl_minify(surf->logical_level0_px.h, view->base_level); 239 param->size[2] = surf->dim == ISL_SURF_DIM_2D ? 240 view->array_len : 241 isl_minify(surf->logical_level0_px.d, view->base_level); 242 243 uint32_t tile_z_el, phys_array_layer; 244 isl_surf_get_image_offset_el(surf, view->base_level, 245 surf->dim == ISL_SURF_DIM_3D ? 246 0 : view->base_array_layer, 247 surf->dim == ISL_SURF_DIM_3D ? 248 view->base_array_layer : 0, 249 ¶m->offset[0], ¶m->offset[1], 250 &tile_z_el, &phys_array_layer); 251 assert(tile_z_el == 0); 252 assert(phys_array_layer == 0); 253 254 const int cpp = isl_format_get_layout(surf->format)->bpb / 8; 255 param->stride[0] = cpp; 256 param->stride[1] = surf->row_pitch_B / cpp; 257 258 const struct isl_extent3d image_align_sa = 259 isl_surf_get_image_alignment_sa(surf); 260 if (ISL_GFX_VER(dev) < 9 && surf->dim == ISL_SURF_DIM_3D) { 261 param->stride[2] = isl_align_npot(param->size[0], image_align_sa.w); 262 param->stride[3] = isl_align_npot(param->size[1], image_align_sa.h); 263 } else { 264 param->stride[2] = 0; 265 param->stride[3] = isl_surf_get_array_pitch_el_rows(surf); 266 } 267 268 switch (surf->tiling) { 269 case ISL_TILING_LINEAR: 270 /* image_param_defaults is good enough */ 271 break; 272 273 case ISL_TILING_X: 274 /* An X tile is a rectangular block of 512x8 bytes. */ 275 param->tiling[0] = isl_log2u(512 / cpp); 276 param->tiling[1] = isl_log2u(8); 277 278 if (dev->has_bit6_swizzling) { 279 /* Right shifts required to swizzle bits 9 and 10 of the memory 280 * address with bit 6. 281 */ 282 param->swizzling[0] = 3; 283 param->swizzling[1] = 4; 284 } 285 break; 286 287 case ISL_TILING_Y0: 288 /* The layout of a Y-tiled surface in memory isn't really fundamentally 289 * different to the layout of an X-tiled surface, we simply pretend that 290 * the surface is broken up in a number of smaller 16Bx32 tiles, each 291 * one arranged in X-major order just like is the case for X-tiling. 292 */ 293 param->tiling[0] = isl_log2u(16 / cpp); 294 param->tiling[1] = isl_log2u(32); 295 296 if (dev->has_bit6_swizzling) { 297 /* Right shift required to swizzle bit 9 of the memory address with 298 * bit 6. 299 */ 300 param->swizzling[0] = 3; 301 param->swizzling[1] = 0xff; 302 } 303 break; 304 305 default: 306 assert(!"Unhandled storage image tiling"); 307 } 308 309 /* 3D textures are arranged in 2D in memory with 2^lod slices per row. The 310 * address calculation algorithm (emit_address_calculation() in 311 * brw_fs_surface_builder.cpp) handles this as a sort of tiling with 312 * modulus equal to the LOD. 313 */ 314 param->tiling[2] = (ISL_GFX_VER(dev) < 9 && surf->dim == ISL_SURF_DIM_3D ? 315 view->base_level : 0); 316} 317 318void 319isl_buffer_fill_image_param(const struct isl_device *dev, 320 struct brw_image_param *param, 321 enum isl_format format, 322 uint64_t size) 323{ 324 *param = image_param_defaults; 325 326 param->stride[0] = isl_format_get_layout(format)->bpb / 8; 327 param->size[0] = size / param->stride[0]; 328} 329