code wiki / (root) / nx_simd_i16x16_test.nx

nx_simd_i16x16_test.nx

buildroot/runtime/nx_simd_i16x16_test.nx

4755 B118 linesdepth 6pulls 8 transitivereach 0 importersview sourcekind gate/prooftopic simd

docs dependencies structs consts functions

about

nx_simd_i16x16_test.nx -- exercise the i16x16 SIMD intrinsics. 16 lanes of 16-bit ints in 256-bit vectors. Same bit-exact-vs- scalar gate as the i64x4 and i32x8 smokes. Useful for image processing / audio / quantized ML weights at int16.

dependencies 2 imports · 0 importers

imports: nx_kernel_v2.nxnx_log.nx

imported by: nobody (leaf or entry point)

call flow from main pre-order; caps 40 nodes / depth 6 declared; ↻ = already shown

structs

none

consts

none

functions

11	func pack4(a: i64, b: i64, c: i64, d: i64) -> i64 called by 5: t1_load_store t2_vadd t3_vmul t4_vbroadcast t5_vreduce_sum
15	func t1_load_store() -> i64 called by 1: main calls 1: pack4
33	func t2_vadd() -> i64 called by 1: main calls 1: pack4
56	func t3_vmul() -> i64 called by 1: main calls 1: pack4
79	func t4_vbroadcast() -> i64 called by 1: main calls 1: pack4
91	func t5_vreduce_sum() -> i64 called by 1: main calls 1: pack4
103	func main() -> nx_exit calls 5: t1_load_store t2_vadd t3_vmul t4_vbroadcast t5_vreduce_sum