VK_INTEL_performance_query

// A previously created device
VkDevice device;

// A queue derived from the device
VkQueue queue;

VkInitializePerformanceApiInfoINTEL performanceApiInfoIntel = {
  VK_STRUCTURE_TYPE_INITIALIZE_PERFORMANCE_API_INFO_INTEL,
  NULL,
  NULL
};

vkInitializePerformanceApiINTEL(
  device,
  &performanceApiInfoIntel);

VkQueryPoolPerformanceQueryCreateInfoINTEL queryPoolIntel = {
  VK_STRUCTURE_TYPE_QUERY_POOL_CREATE_INFO_INTEL,
  NULL,
  VK_QUERY_POOL_SAMPLING_MODE_MANUAL_INTEL,
};

VkQueryPoolCreateInfo queryPoolCreateInfo = {
  VK_STRUCTURE_TYPE_QUERY_POOL_CREATE_INFO,
  &queryPoolIntel,
  0,
  VK_QUERY_TYPE_PERFORMANCE_QUERY_INTEL,
  1,
  0
};

VkQueryPool queryPool;

VkResult result = vkCreateQueryPool(
  device,
  &queryPoolCreateInfo,
  NULL,
  &queryPool);

assert(VK_SUCCESS == result);

// A command buffer we want to record counters on
VkCommandBuffer commandBuffer;

VkCommandBufferBeginInfo commandBufferBeginInfo = {
  VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO,
  NULL,
  VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT,
  NULL
};

result = vkBeginCommandBuffer(commandBuffer, &commandBufferBeginInfo);

assert(VK_SUCCESS == result);

vkCmdResetQueryPool(
  commandBuffer,
  queryPool,
  0,
  1);

vkCmdBeginQuery(
  commandBuffer,
  queryPool,
  0,
  0);

// Perform the commands you want to get performance information on
// ...

// Perform a barrier to ensure all previous commands were complete before
// ending the query
vkCmdPipelineBarrier(commandBuffer,
  VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT,
  VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT,
  0,
  0,
  NULL,
  0,
  NULL,
  0,
  NULL);

vkCmdEndQuery(
  commandBuffer,
  queryPool,
  0);

result = vkEndCommandBuffer(commandBuffer);

assert(VK_SUCCESS == result);

VkPerformanceConfigurationAcquireInfoINTEL performanceConfigurationAcquireInfo = {
  VK_STRUCTURE_TYPE_PERFORMANCE_CONFIGURATION_ACQUIRE_INFO_INTEL,
  NULL,
  VK_PERFORMANCE_CONFIGURATION_TYPE_COMMAND_QUEUE_METRICS_DISCOVERY_ACTIVATED_INTEL
};

VkPerformanceConfigurationINTEL performanceConfigurationIntel;

result = vkAcquirePerformanceConfigurationINTEL(
  device,
  &performanceConfigurationAcquireInfo,
  &performanceConfigurationIntel);

vkQueueSetPerformanceConfigurationINTEL(queue, performanceConfigurationIntel);

assert(VK_SUCCESS == result);

// Submit the command buffer and wait for its completion
// ...

result = vkReleasePerformanceConfigurationINTEL(
  device,
  performanceConfigurationIntel);

assert(VK_SUCCESS == result);

// Get the report size from metrics-discovery's QueryReportSize

result = vkGetQueryPoolResults(
  device,
  queryPool,
  0, 1, QueryReportSize,
  data, QueryReportSize, 0);

assert(VK_SUCCESS == result);

// The data can then be passed back to metrics-discovery from which
// human readable values can be queried.