Implemented `SqmulRoundSat` for the Cranelift interpreter, performing QN-format fixed point multiplication for 16 and 32-bit integers in SIMD vectors. Copyright (c) 2021, Arm Limited
13 lines
447 B
Plaintext
13 lines
447 B
Plaintext
test interpret
|
|
test run
|
|
target aarch64
|
|
;; x86_64 hasn't implemented this for `i32x4`
|
|
|
|
function %sqmulrs_i32x4(i32x4, i32x4) -> i32x4 {
|
|
block0(v0: i32x4, v1: i32x4):
|
|
v2 = sqmul_round_sat v0, v1
|
|
return v2
|
|
}
|
|
; run: %sqmulrs_i32x4([1000 2000 3000 4000], [10000 100000 1000000 10000000]) == [0 0 1 19]
|
|
; run: %sqmulrs_i32x4([2147483647 -2147483648 -2147483648 0], [2147483647 -2147483648 2147483647 0]) == [2147483646 2147483647 -2147483647 0]
|