Byte scan and classification¶

Generated workload catalogue · Execution contract

Purpose¶

Provide a compact byte-load/comparison workload with a simple independent expected result.

Setup¶

Property	Value
Workload ID	`scan`
Selection	`--workload scan`
Generator	`buildRV32IBenchmark() in RV32IBenchmarks.cpp`
End condition	EBREAK after the loop and result store

The low byte of each of n seeded words forms a byte array at 0x1000.

Use the shared address map and parameter bounds. N includes any training iterations; n means size.

Implementation¶

Load each byte unsigned and use SLTIU with 128 to count values below 128; repeat the array N times.

for (uint8_t b : bytes) sum += (b < 128);

This is a behavioral summary of the generated assembly, not the host program being timed.

Expected result¶

Result=N*count(input bytes <128). The byte classification is unsigned, so bytes 0x80..0xff contribute zero.

The runner checks the generator's expected result in addition to retirement-by-retirement oracle validation. Output-array assertions, where described, check more than a checksum.

Measurement and running¶

Useful as a small generated smoke case, and later as a sequential byte-access case. It does not require a branch for every classification.

build/rv32i_experiment --core advanced --workload scan \
  --iterations 2 --size 16 --seed 1  \
  --fidelity behavioral --period 4000 \
  --allocation-limit-mib 512 --max-cycles 4096

The explicit period is for a bounded functional check, not a hardware-speed result. For comparisons, use the serial campaign driver, identical case inputs, and a certified per-target clock.

Source and tests¶

src/analysis/RV32IBenchmarks.cpp: emitted instructions and independent expected results.
tests/cpp/RV32IBenchmarkTest.cpp: generator results, parameter bounds, and edge cases.
tests/checks/RV32IBenchmarkCLITest.py and tests/checks/BenchmarkCampaignCLITest.py: shared execution/campaign checks.