diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2021-08-13 17:11:52 +0100 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2021-08-25 10:48:49 +0100 |
| commit | 6b895bf8fb088a04a91714a555d2b6234cf1e98d (patch) | |
| tree | 728639ab58524cfe71d7d07a621a471e4eb4a827 /target/arm/mve_helper.c | |
| parent | c386443b163965e44ae7a7f7858ec7985e97926b (diff) | |
| download | qemu-6b895bf8fb088a04a91714a555d2b6234cf1e98d.zip qemu-6b895bf8fb088a04a91714a555d2b6234cf1e98d.tar.gz qemu-6b895bf8fb088a04a91714a555d2b6234cf1e98d.tar.bz2 | |
target/arm: Implement MVE VMLAS
Implement the MVE VMLAS insn, which multiplies a vector by a vector
and adds a scalar.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'target/arm/mve_helper.c')
| -rw-r--r-- | target/arm/mve_helper.c | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index 0317176..ab02a1e 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -948,6 +948,22 @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +/* "accumulating" version where FN takes d as well as n and m */ +#define DO_2OP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m), mask); \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -958,6 +974,11 @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) DO_2OP_SCALAR(OP##h, 2, int16_t, FN) \ DO_2OP_SCALAR(OP##w, 4, int32_t, FN) +#define DO_2OP_ACC_SCALAR_U(OP, FN) \ + DO_2OP_ACC_SCALAR(OP##b, 1, uint8_t, FN) \ + DO_2OP_ACC_SCALAR(OP##h, 2, uint16_t, FN) \ + DO_2OP_ACC_SCALAR(OP##w, 4, uint32_t, FN) + DO_2OP_SCALAR_U(vadd_scalar, DO_ADD) DO_2OP_SCALAR_U(vsub_scalar, DO_SUB) DO_2OP_SCALAR_U(vmul_scalar, DO_MUL) @@ -987,6 +1008,11 @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by vector plus scalar */ +#define DO_VMLAS(D, N, M) ((N) * (D) + (M)) + +DO_2OP_ACC_SCALAR_U(vmlas, DO_VMLAS) + /* * Long saturating scalar ops. As with DO_2OP_L, TYPE and H are for the * input (smaller) type and LESIZE, LTYPE, LH for the output (long) type. |