diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2020-08-28 19:33:44 +0100 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2020-09-01 11:38:20 +0100 |
| commit | 1dc587ee9bfe804406eb3e0bacf47a80644d8abc (patch) | |
| tree | 06f813621ec9493c706d497f23ab74bd126045f1 /target/arm/vec_helper.c | |
| parent | 40fde72dda2da8d55b820fa6c5efd85814be2023 (diff) | |
target/arm: Implement fp16 for Neon pairwise fp ops
Convert the Neon pairwise fp ops to use a single gvic-style
helper to do the full operation instead of one helper call
for each 32-bit part. This allows us to use the same
framework to implement the fp16.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-36-peter.maydell@linaro.org
Diffstat (limited to 'target/arm/vec_helper.c')
| -rw-r--r-- | target/arm/vec_helper.c | 45 |
1 files changed, 45 insertions, 0 deletions
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index e5bb5e395c..46623d401e 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -1771,3 +1771,48 @@ DO_ABA(gvec_uaba_s, uint32_t) DO_ABA(gvec_uaba_d, uint64_t) #undef DO_ABA + +#define DO_NEON_PAIRWISE(NAME, OP) \ + void HELPER(NAME##s)(void *vd, void *vn, void *vm, \ + void *stat, uint32_t oprsz) \ + { \ + float_status *fpst = stat; \ + float32 *d = vd; \ + float32 *n = vn; \ + float32 *m = vm; \ + float32 r0, r1; \ + \ + /* Read all inputs before writing outputs in case vm == vd */ \ + r0 = float32_##OP(n[H4(0)], n[H4(1)], fpst); \ + r1 = float32_##OP(m[H4(0)], m[H4(1)], fpst); \ + \ + d[H4(0)] = r0; \ + d[H4(1)] = r1; \ + } \ + \ + void HELPER(NAME##h)(void *vd, void *vn, void *vm, \ + void *stat, uint32_t oprsz) \ + { \ + float_status *fpst = stat; \ + float16 *d = vd; \ + float16 *n = vn; \ + float16 *m = vm; \ + float16 r0, r1, r2, r3; \ + \ + /* Read all inputs before writing outputs in case vm == vd */ \ + r0 = float16_##OP(n[H2(0)], n[H2(1)], fpst); \ + r1 = float16_##OP(n[H2(2)], n[H2(3)], fpst); \ + r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ + r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ + \ + d[H4(0)] = r0; \ + d[H4(1)] = r1; \ + d[H4(2)] = r2; \ + d[H4(3)] = r3; \ + } + +DO_NEON_PAIRWISE(neon_padd, add) +DO_NEON_PAIRWISE(neon_pmax, max) +DO_NEON_PAIRWISE(neon_pmin, min) + +#undef DO_NEON_PAIRWISE |