diff options
| author | Peter Maydell <peter.maydell@linaro.org> | 2021-09-01 09:02:34 +0100 |
|---|---|---|
| committer | Peter Maydell <peter.maydell@linaro.org> | 2021-09-01 11:08:16 +0100 |
| commit | 1e35cd916695389074b12614d254087a9f51b852 (patch) | |
| tree | 7a7df092b27d80b64cf1ba986123c13a1913f583 /target/arm/mve_helper.c | |
| parent | 52e64f5b1f2c81472b57dbad255ab9b00302f10d (diff) | |
| download | qemu-1e35cd916695389074b12614d254087a9f51b852.zip qemu-1e35cd916695389074b12614d254087a9f51b852.tar.gz qemu-1e35cd916695389074b12614d254087a9f51b852.tar.bz2 | |
target/arm: Implement MVE VADD (floating-point)
Implement the MVE VADD (floating-point) insn. Handling of this is
similar to the 2-operand integer insns, except that we must take care
to only update the floating point exception status if the least
significant bit of the predicate mask for each element is active.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'target/arm/mve_helper.c')
| -rw-r--r-- | target/arm/mve_helper.c | 40 |
1 files changed, 40 insertions, 0 deletions
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index c2826eb..abca7c0 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -25,6 +25,7 @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "tcg/tcg.h" +#include "fpu/softfloat.h" static uint16_t mve_eci_mask(CPUARMState *env) { @@ -2798,3 +2799,42 @@ DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) + +/* + * 2-operand floating point. Note that if an element is partially + * predicated we must do the FP operation to update the non-predicated + * bytes, but we must be careful to avoid updating the FP exception + * state unless byte 0 of the element was unpredicated. + */ +#define DO_2OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_ALL(OP, FN) \ + DO_2OP_FP(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_ALL(vfadd, add) |