Intel^® VTune^™ Profiler 2024.0.0

Recommendations:

GPU Time, % of Elapsed time: 75.2%

GPU utilization is low. Switch to the for in-depth analysis of host activity. Poor GPU utilization can prevent the application from offloading effectively.

XVE Array Stalled/Idle: 52.4% of Elapsed time with GPU busy

GPU metrics detect some kernel issues. Use GPU Compute/Media Hotspots (preview) to understand how well your application runs on the specified hardware.

Elapsed Time: 36.890s

GPU Time, % of Elapsed time: 75.2%

GPU utilization is low. Consider offloading more work to the GPU to increase overall application performance.

GPU Time, % of Elapsed time:
GPU Adapter GPU Engine GPU Time GPU Time, % of Elapsed time(%)
GPU 1 Render and GPGPU 27.734s 75.2%

GPU Adapter	GPU Engine	GPU Time	GPU Time, % of Elapsed time(%)
GPU 1	Render and GPGPU	27.734s	75.2%

Top Hotspots when GPU was idle:

Function	Module	CPU Time
asm_exc_page_fault	vmlinux	2.920s
[Skipped stack frame(s)]	[Unknown]	1.644s
operator new	libc++abi.so	1.484s
func@0x13f9b0	libze_intel_gpu.so.1.3.27191.42	1.434s
memcmp	libc-dynamic.so	1.420s
[Others]	N/A	15.764s

Hottest Host Tasks:

Host Task	Task Time	% of Elapsed Time(%)	Task Count
zeEventHostSynchronize	21.643s	58.7%	14
zeCommandListAppendMemoryCopy	6.066s	16.4%	1
zeModuleCreate	0.259s	0.7%	1
zeCommandListAppendMemoryCopyRegion	0.071s	0.2%	5
zeCommandListCreateImmediate	0.001s	0.0%	3
[Others]	0.001s	0.0%	105

Hottest GPU Computing Tasks:

Computing Task	Total Time	Execution Time	% of Total Time(%)	SIMD Width
iso3dfd(sycl::_V1::queue&, float, float, float, float, unsigned long, unsigned long, unsigned long, unsigned long)::{lambda(sycl::_V1::handler&)#1}::operator()(sycl::_V1::handler&) const::{lambda(sycl::_V1::id<(int)3>)#1}	27.791s	14.766s	53.1%	32

Collection and Platform Info:
- Application Command Line: ./build/src/2_GPU_basic "1024" "1024" "1024" "100"
- Operating System: 5.15.0-100-generic DISTRIB_ID=Ubuntu DISTRIB_RELEASE=22.04 DISTRIB_CODENAME=jammy DISTRIB_DESCRIPTION="Ubuntu 22.04.4 LTS"
- Computer Name: idc-beta-batch-pvc-node-06
- Result Size: 320.1 MB
- Collection start time: 23:42:59 14/03/2024 UTC
- Collection stop time: 23:43:35 14/03/2024 UTC
- Collector Type: Event-based sampling driver,Driverless Perf system-wide sampling,User-mode sampling and tracing
- CPU:
  - Name: Intel(R) Xeon(R) Processor code named Sapphirerapids
  - Frequency: 2.000 GHz
  - Logical CPU Count: 224
  - LLC size: 110.1 MB
- GPU:
  - GPU 0: 0:41:0.0 : Display controller: Intel Corporation Device 0x0bda:
    BDF: 0:41:0:0
    XVE Count: 448
    Max XVE Thread Count: 8
    Max Core Frequency: 1.550 GHz
  - GPU 1: 0:58:0.0 : Display controller: Intel Corporation Device 0x0bda:
    BDF: 0:58:0:0
    XVE Count: 448
    Max XVE Thread Count: 8
    Max Core Frequency: 1.550 GHz
  - GPU 2: 0:154:0.0 : Display controller: Intel Corporation Device 0x0bda:
    BDF: 0:154:0:0
    XVE Count: 448
    Max XVE Thread Count: 8
    Max Core Frequency: 1.550 GHz
  - GPU 3: 0:202:0.0 : Display controller: Intel Corporation Device 0x0bda:
    BDF: 0:202:0:0
    XVE Count: 448
    Max XVE Thread Count: 8
    Max Core Frequency: 1.550 GHz