device->has_scissor_bug = device->rad_info.family == CHIP_VEGA10 ||
device->rad_info.family == CHIP_RAVEN;
+ device->has_tc_compat_zrange_bug = device->rad_info.chip_class < GFX10;
+
/* Out-of-order primitive rasterization. */
device->has_out_of_order_rast = device->rad_info.chip_class >= GFX8 &&
device->rad_info.max_se >= 2;
(device->rad_info.chip_class >= GFX8 &&
device->rad_info.me_fw_feature >= 41);
- device->has_dcc_constant_encode = device->rad_info.family == CHIP_RAVEN2;
+ device->has_dcc_constant_encode = device->rad_info.family == CHIP_RAVEN2 ||
+ device->rad_info.chip_class >= GFX10;
device->use_shader_ballot = device->instance->perftest_flags & RADV_PERFTEST_SHADER_BALLOT;
+ /* Determine the number of threads per wave for all stages. */
+ device->cs_wave_size = 64;
+ device->ps_wave_size = 64;
+ device->ge_wave_size = 64;
+
+ if (device->rad_info.chip_class >= GFX10) {
+ if (device->instance->perftest_flags & RADV_PERFTEST_CS_WAVE_32)
+ device->cs_wave_size = 32;
+
+ /* For pixel shaders, wave64 is recommanded. */
+ if (device->instance->perftest_flags & RADV_PERFTEST_PS_WAVE_32)
+ device->ps_wave_size = 32;
+
+ if (device->instance->perftest_flags & RADV_PERFTEST_GE_WAVE_32)
+ device->ge_wave_size = 32;
+ }
+
radv_physical_device_init_mem_types(device);
radv_fill_device_extension_table(device, &device->supported_extensions);
{"nothreadllvm", RADV_DEBUG_NOTHREADLLVM},
{"nobinning", RADV_DEBUG_NOBINNING},
{"noloadstoreopt", RADV_DEBUG_NO_LOAD_STORE_OPT},
+ {"nongg", RADV_DEBUG_NO_NGG},
{NULL, 0}
};
{"bolist", RADV_PERFTEST_BO_LIST},
{"shader_ballot", RADV_PERFTEST_SHADER_BALLOT},
{"tccompatcmask", RADV_PERFTEST_TC_COMPAT_CMASK},
+ {"cswave32", RADV_PERFTEST_CS_WAVE_32},
+ {"pswave32", RADV_PERFTEST_PS_WAVE_32},
+ {"gewave32", RADV_PERFTEST_GE_WAVE_32},
{NULL, 0}
};
case VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_SHADER_ATOMIC_INT64_FEATURES_KHR: {
VkPhysicalDeviceShaderAtomicInt64FeaturesKHR *features =
(VkPhysicalDeviceShaderAtomicInt64FeaturesKHR *)ext;
- /* TODO: Enable this once the driver supports 64-bit
- * compare&swap atomic operations.
- */
- features->shaderBufferInt64Atomics = false;
- features->shaderSharedInt64Atomics = false;
+ features->shaderBufferInt64Atomics = HAVE_LLVM >= 0x0900;
+ features->shaderSharedInt64Atomics = HAVE_LLVM >= 0x0900;
break;
}
case VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_INLINE_UNIFORM_BLOCK_FEATURES_EXT: {
features->uniformBufferStandardLayout = true;
break;
}
+ case VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_INDEX_TYPE_UINT8_FEATURES_EXT: {
+ VkPhysicalDeviceIndexTypeUint8FeaturesEXT *features =
+ (VkPhysicalDeviceIndexTypeUint8FeaturesEXT *)ext;
+ features->indexTypeUint8 = pdevice->rad_info.chip_class >= GFX8;
+ break;
+ }
default:
break;
}
(VkPhysicalDeviceDriverPropertiesKHR *) ext;
driver_props->driverID = VK_DRIVER_ID_MESA_RADV_KHR;
- memset(driver_props->driverName, 0, VK_MAX_DRIVER_NAME_SIZE_KHR);
- strcpy(driver_props->driverName, "radv");
-
- memset(driver_props->driverInfo, 0, VK_MAX_DRIVER_INFO_SIZE_KHR);
+ snprintf(driver_props->driverName, VK_MAX_DRIVER_NAME_SIZE_KHR, "radv");
snprintf(driver_props->driverInfo, VK_MAX_DRIVER_INFO_SIZE_KHR,
"Mesa " PACKAGE_VERSION MESA_GIT_SHA1
" (LLVM " MESA_LLVM_VERSION_STRING ")");
device->scratch_waves = MAX2(32 * physical_device->rad_info.num_good_compute_units,
max_threads_per_block / 64);
- device->dispatch_initiator = S_00B800_COMPUTE_SHADER_EN(1);
+ device->dispatch_initiator = S_00B800_COMPUTE_SHADER_EN(1) |
+ S_00B800_CS_W32_EN(device->physical_device->cs_wave_size == 32);
if (device->physical_device->rad_info.chip_class >= GFX7) {
/* If the KMD allows it (there is a KMD hw register for it),
index stride 64 */
desc[0] = esgs_va;
desc[1] = S_008F04_BASE_ADDRESS_HI(esgs_va >> 32) |
- S_008F04_STRIDE(0) |
S_008F04_SWIZZLE_ENABLE(true);
desc[2] = esgs_ring_size;
desc[3] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
S_008F0C_DST_SEL_Z(V_008F0C_SQ_SEL_Z) |
S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W) |
- S_008F0C_ELEMENT_SIZE(1) |
S_008F0C_INDEX_STRIDE(3) |
- S_008F0C_ADD_TID_ENABLE(true);
+ S_008F0C_ADD_TID_ENABLE(1);
if (queue->device->physical_device->rad_info.chip_class >= GFX10) {
desc[3] |= S_008F0C_FORMAT(V_008F0C_IMG_FORMAT_32_FLOAT) |
S_008F0C_RESOURCE_LEVEL(1);
} else {
desc[3] |= S_008F0C_NUM_FORMAT(V_008F0C_BUF_NUM_FORMAT_FLOAT) |
- S_008F0C_DATA_FORMAT(V_008F0C_BUF_DATA_FORMAT_32);
+ S_008F0C_DATA_FORMAT(V_008F0C_BUF_DATA_FORMAT_32) |
+ S_008F0C_ELEMENT_SIZE(1);
}
/* GS entry for ES->GS ring */
/* stride 0, num records - size, elsize0,
index stride 0 */
desc[4] = esgs_va;
- desc[5] = S_008F04_BASE_ADDRESS_HI(esgs_va >> 32)|
- S_008F04_STRIDE(0) |
- S_008F04_SWIZZLE_ENABLE(false);
+ desc[5] = S_008F04_BASE_ADDRESS_HI(esgs_va >> 32);
desc[6] = esgs_ring_size;
desc[7] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
S_008F0C_DST_SEL_Z(V_008F0C_SQ_SEL_Z) |
- S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W) |
- S_008F0C_ELEMENT_SIZE(0) |
- S_008F0C_INDEX_STRIDE(0) |
- S_008F0C_ADD_TID_ENABLE(false);
+ S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W);
if (queue->device->physical_device->rad_info.chip_class >= GFX10) {
desc[7] |= S_008F0C_FORMAT(V_008F0C_IMG_FORMAT_32_FLOAT) |
/* stride 0, num records - size, elsize0,
index stride 0 */
desc[0] = gsvs_va;
- desc[1] = S_008F04_BASE_ADDRESS_HI(gsvs_va >> 32)|
- S_008F04_STRIDE(0) |
- S_008F04_SWIZZLE_ENABLE(false);
+ desc[1] = S_008F04_BASE_ADDRESS_HI(gsvs_va >> 32);
desc[2] = gsvs_ring_size;
desc[3] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
S_008F0C_DST_SEL_Z(V_008F0C_SQ_SEL_Z) |
- S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W) |
- S_008F0C_ELEMENT_SIZE(0) |
- S_008F0C_INDEX_STRIDE(0) |
- S_008F0C_ADD_TID_ENABLE(false);
+ S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W);
if (queue->device->physical_device->rad_info.chip_class >= GFX10) {
desc[3] |= S_008F0C_FORMAT(V_008F0C_IMG_FORMAT_32_FLOAT) |
elsize 4, index stride 16 */
/* shader will patch stride and desc[2] */
desc[4] = gsvs_va;
- desc[5] = S_008F04_BASE_ADDRESS_HI(gsvs_va >> 32)|
- S_008F04_STRIDE(0) |
- S_008F04_SWIZZLE_ENABLE(true);
+ desc[5] = S_008F04_BASE_ADDRESS_HI(gsvs_va >> 32) |
+ S_008F04_SWIZZLE_ENABLE(1);
desc[6] = 0;
desc[7] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
S_008F0C_DST_SEL_Z(V_008F0C_SQ_SEL_Z) |
S_008F0C_DST_SEL_W(V_008F0C_SQ_SEL_W) |
- S_008F0C_ELEMENT_SIZE(1) |
S_008F0C_INDEX_STRIDE(1) |
S_008F0C_ADD_TID_ENABLE(true);
S_008F0C_RESOURCE_LEVEL(1);
} else {
desc[7] |= S_008F0C_NUM_FORMAT(V_008F0C_BUF_NUM_FORMAT_FLOAT) |
- S_008F0C_DATA_FORMAT(V_008F0C_BUF_DATA_FORMAT_32);
+ S_008F0C_DATA_FORMAT(V_008F0C_BUF_DATA_FORMAT_32) |
+ S_008F0C_ELEMENT_SIZE(1);
}
}
uint64_t tess_offchip_va = tess_va + tess_offchip_ring_offset;
desc[0] = tess_va;
- desc[1] = S_008F04_BASE_ADDRESS_HI(tess_va >> 32) |
- S_008F04_STRIDE(0) |
- S_008F04_SWIZZLE_ENABLE(false);
+ desc[1] = S_008F04_BASE_ADDRESS_HI(tess_va >> 32);
desc[2] = tess_factor_ring_size;
desc[3] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
}
desc[4] = tess_offchip_va;
- desc[5] = S_008F04_BASE_ADDRESS_HI(tess_offchip_va >> 32) |
- S_008F04_STRIDE(0) |
- S_008F04_SWIZZLE_ENABLE(false);
+ desc[5] = S_008F04_BASE_ADDRESS_HI(tess_offchip_va >> 32);
desc[6] = tess_offchip_ring_size;
desc[7] = S_008F0C_DST_SEL_X(V_008F0C_SQ_SEL_X) |
S_008F0C_DST_SEL_Y(V_008F0C_SQ_SEL_Y) |
*
* Follow AMDVLK here.
*/
- if (device->physical_device->rad_info.family == CHIP_VEGA10 ||
- device->physical_device->rad_info.chip_class == GFX7 ||
- device->physical_device->rad_info.chip_class == GFX6)
+ if (device->physical_device->rad_info.chip_class >= GFX10) {
+ max_offchip_buffers_per_se = 256;
+ } else if (device->physical_device->rad_info.family == CHIP_VEGA10 ||
+ device->physical_device->rad_info.chip_class == GFX7 ||
+ device->physical_device->rad_info.chip_class == GFX6)
--max_offchip_buffers_per_se;
max_offchip_buffers = max_offchip_buffers_per_se *
case GFX7:
case GFX8:
case GFX9:
- default:
max_offchip_buffers = MIN2(max_offchip_buffers, 508);
break;
+ case GFX10:
+ break;
+ default:
+ break;
}
*max_offchip_buffers_p = max_offchip_buffers;
if (queue->device->physical_device->rad_info.chip_class >= GFX10) {
uint32_t regs[] = {R_00B030_SPI_SHADER_USER_DATA_PS_0,
R_00B130_SPI_SHADER_USER_DATA_VS_0,
- R_00B230_SPI_SHADER_USER_DATA_GS_0,
- R_00B430_SPI_SHADER_USER_DATA_HS_0};
+ R_00B208_SPI_SHADER_USER_DATA_ADDR_LO_GS,
+ R_00B408_SPI_SHADER_USER_DATA_ADDR_LO_HS};
for (int i = 0; i < ARRAY_SIZE(regs); ++i) {
radv_emit_shader_pointer(queue->device, cs, regs[i],
va, true);
}
- } else if (queue->device->physical_device->rad_info.chip_class >= GFX9) {
+ } else if (queue->device->physical_device->rad_info.chip_class == GFX9) {
uint32_t regs[] = {R_00B030_SPI_SHADER_USER_DATA_PS_0,
R_00B130_SPI_SHADER_USER_DATA_VS_0,
R_00B208_SPI_SHADER_USER_DATA_ADDR_LO_GS,
if (esgs_ring_bo || gsvs_ring_bo || tess_rings_bo) {
radeon_emit(cs, PKT3(PKT3_EVENT_WRITE, 0, 0));
radeon_emit(cs, EVENT_TYPE(V_028A90_VS_PARTIAL_FLUSH) | EVENT_INDEX(4));
+
radeon_emit(cs, PKT3(PKT3_EVENT_WRITE, 0, 0));
radeon_emit(cs, EVENT_TYPE(V_028A90_VGT_FLUSH) | EVENT_INDEX(0));
}
cb->cb_color_pitch = S_028C64_TILE_MAX(pitch_tile_max);
cb->cb_color_slice = S_028C68_TILE_MAX(slice_tile_max);
- cb->cb_color_cmask_slice = iview->image->cmask.slice_tile_max;
+ cb->cb_color_cmask_slice = surf->u.legacy.cmask_slice_tile_max;
cb->cb_color_attrib |= S_028C74_TILE_MODE_INDEX(tile_mode_index);
if (radv_image_has_fmask(iview->image)) {
if (device->physical_device->rad_info.chip_class >= GFX7)
- cb->cb_color_pitch |= S_028C64_FMASK_TILE_MAX(iview->image->fmask.pitch_in_pixels / 8 - 1);
- cb->cb_color_attrib |= S_028C74_FMASK_TILE_MODE_INDEX(iview->image->fmask.tile_mode_index);
- cb->cb_color_fmask_slice = S_028C88_TILE_MAX(iview->image->fmask.slice_tile_max);
+ cb->cb_color_pitch |= S_028C64_FMASK_TILE_MAX(surf->u.legacy.fmask.pitch_in_pixels / 8 - 1);
+ cb->cb_color_attrib |= S_028C74_FMASK_TILE_MODE_INDEX(surf->u.legacy.fmask.tiling_index);
+ cb->cb_color_fmask_slice = S_028C88_TILE_MAX(surf->u.legacy.fmask.slice_tile_max);
} else {
/* This must be set for fast clear to work without FMASK. */
if (device->physical_device->rad_info.chip_class >= GFX7)
/* CMASK variables */
va = radv_buffer_get_va(iview->bo) + iview->image->offset;
- va += iview->image->cmask.offset;
+ va += iview->image->cmask_offset;
cb->cb_color_cmask = va >> 8;
va = radv_buffer_get_va(iview->bo) + iview->image->offset;
device->physical_device->rad_info.chip_class <= GFX8)
va += plane->surface.u.legacy.level[iview->base_mip].dcc_offset;
+ unsigned dcc_tile_swizzle = surf->tile_swizzle;
+ dcc_tile_swizzle &= (surf->dcc_alignment - 1) >> 8;
+
cb->cb_dcc_base = va >> 8;
- cb->cb_dcc_base |= surf->tile_swizzle;
+ cb->cb_dcc_base |= dcc_tile_swizzle;
/* GFX10 field has the same base shift as the GFX6 field. */
uint32_t max_slice = radv_surface_max_layer_count(iview) - 1;
}
if (radv_image_has_fmask(iview->image)) {
- va = radv_buffer_get_va(iview->bo) + iview->image->offset + iview->image->fmask.offset;
+ va = radv_buffer_get_va(iview->bo) + iview->image->offset + iview->image->fmask_offset;
cb->cb_color_fmask = va >> 8;
- cb->cb_color_fmask |= iview->image->fmask.tile_swizzle;
+ cb->cb_color_fmask |= surf->fmask_tile_swizzle;
} else {
cb->cb_color_fmask = cb->cb_color_base;
}
if (radv_image_has_fmask(iview->image)) {
cb->cb_color_info |= S_028C70_COMPRESSION(1);
if (device->physical_device->rad_info.chip_class == GFX6) {
- unsigned fmask_bankh = util_logbase2(iview->image->fmask.bank_height);
+ unsigned fmask_bankh = util_logbase2(surf->u.legacy.fmask.bankh);
cb->cb_color_attrib |= S_028C74_FMASK_BANK_HEIGHT(fmask_bankh);
}
projects / mesa.git / blobdiff