Core vs thread
A core is a physical execution unit; a thread is a logical stream of work, and one core can expose two threads via simultaneous multithreading.
Also known as physical core, logical processor, logical core
Not measurable from a browser
A browser cannot read temperatures, power draw, fan speed, VRAM capacity, clock frequency or native FLOPS. For a direct reading use a native monitor such as HWiNFO64, GPU-Z or lm-sensors. SystemCheck contributes the other half: whether the condition is costing you throughput, measured as decay and consistency.
A physical core has its own execution units, registers, and L1/L2 cache. A hardware thread, what Windows calls a logical processor, is a scheduling target. On a chip with SMT enabled, each core presents two logical processors that share the core's execution resources, so an 8-core CPU reports 16 threads.
Two threads on one core do not double that core's throughput. They fill scheduling gaps: when one thread stalls waiting on memory, the other issues instructions into the idle execution units. Typical real-world gain from SMT is 15-30% on well-parallelised work, and occasionally negative on workloads that thrash the shared cache.
This distinction matters when reading any multi-core benchmark. A browser can see `navigator.hardwareConcurrency`, which reports logical processors, not physical cores. It cannot tell you how many are physical, whether some are efficiency cores, or whether SMT is enabled. SystemCheck spawns its worker pool from that count, so a 16-thread 8-core machine and a hypothetical 16-core machine start from the same worker count but scale very differently, and that difference shows up in the multi-core result.
Related terms