[GPU] update the gops calculation (#31907)
### Description of the issue(symptom, root-cause, how it was resolved)
- DEVICE_GOPS is a GPU device property that for older devices shows GOPS
for float16, float32 and int8. For LNL and ARC I only see float32 GOPS.
- check platform versions and add missed specs.
- refer links
-- gops: https://gfxspecs.intel.com/
-- gfx version:
https://github.com/intel-innersource/drivers.gpu.specification.platforms/blob/generated_os/gen/templates/doc/listing.md
#### The code and line that caused this issue (if it is not changed
directly)
- src/plugins/intel_gpu/src/runtime/device.cpp
#### Reproduction step and snapshot (if applicable. Do not attach for
customer model)
python sample
```
import openvino as ov
try:
core = ov.Core()
for dev_id in core.available_devices:
if not 'GPU' in dev_id:
continue
FULL_DEVICE_NAME = core.get_property(dev_id, "FULL_DEVICE_NAME")
DEVICE_ARCHITECTURE = core.get_property(dev_id, "DEVICE_ARCHITECTURE")
device_gops = core.get_property(dev_id, "DEVICE_GOPS")
print(f"FULL_DEVICE_NAME: {FULL_DEVICE_NAME}")
print(f"- DEVICE_ARCHITECTURE: {DEVICE_ARCHITECTURE}")
print(f"- DEVICE_GOPS: {device_gops}\n")
except Exception as e:
print(f"An error occurred: {e}")
```
issue log
```
# 10th gen Core
FULL_DEVICE_NAME (RO): Intel(R) Core(TM) i7-1065G7 CPU @ 1.30GHz
DEVICE_ARCHITECTURE (RO): GPU: vendor=0x8086 arch=v11.0.0
DEVICE_GOPS (RO): {<Type: 'float16'>: 2252.800048828125, <Type: 'float32'>: 1126.4000244140625, <Type: 'int8_t'>: 1126.4000244140625, <Type: 'uint8_t'>: 1126.4000244140625}
# 11th gen Core
FULL_DEVICE_NAME (RO): 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz
DEVICE_ARCHITECTURE (RO): GPU: vendor=0x8086 arch=v12.0.0
DEVICE_GOPS (RO): {<Type: 'float16'>: 4147.2001953125, <Type: 'float32'>: 2073.60009765625, <Type: 'int8_t'>: 8294.400390625, <Type: 'uint8_t'>: 8294.400390625}
# LNL
FULL_DEVICE_NAME (RO): Intel(R) Core(TM) Ultra 7 258V
DEVICE_ARCHITECTURE (RO): GPU: vendor=0x8086 arch=v20.4.4
DEVICE_GOPS (RO): {<Type: 'float16'>: 0.0, <Type: 'float32'>: 1996.800048828125, <Type: 'int8_t'>: 0.0, <Type: 'uint8_t'>: 0.0}
# ARC 770
FULL_DEVICE_NAME (RO): Intel(R) Arc(TM) A770 Graphics (dGPU)
DEVICE_ARCHITECTURE (RO): GPU: vendor=0x8086 arch=v12.55.8
DEVICE_GOPS (RO): {<Type: 'float16'>: 0.0, <Type: 'float32'>: 19660.80078125, <Type: 'int8_t'>: 0.0, <Type: 'uint8_t'>: 0.0}
```
#### Checklist
- [ ] Is it a proper fix? (not a workaround)
- [ ] Did you include test case for this fix, if necessary?
- [ ] Did you review existing test that can be extended to cover this
scenario? Which test did you review?
### Tickets:
- 171761
