Merge branch 'cpu_vector_better' into 'main'

Cargo.lock

Cargo.toml

hercules_cg/src/gpu.rs

hercules_cg/src/rt.rs

hercules_ir/src/einsum.rs

hercules_ir/src/ir.rs

hercules_opt/src/fork_transforms.rs

hercules_opt/src/forkify.rs

hercules_opt/src/gcm.rs

hercules_opt/src/schedule.rs

hercules_opt/src/simplify_cfg.rs

hercules_opt/src/unforkify.rs

hercules_opt/src/utils.rs

juno_samples/dot/Cargo.toml

juno_samples/dot/build.rs

juno_samples/dot/src/cpu.sch

juno_samples/dot/src/dot.jn

juno_samples/dot/src/gpu.sch

juno_samples/dot/src/main.rs

juno_scheduler/src/compile.rs