target/arm: Fix mask handling for MVE narrowing operations

In the MVE helpers for the narrowing operations (DO_VSHRN and
DO_VSHRN_SAT) we were using the wrong bits of the predicate mask for
the 'top' versions of the insn.  This is because the loop works over
the double-sized input elements and shifts the predicate mask by that
many bits each time, but when we write out the half-sized output we
must look at the mask bits for whichever half of the element we are
writing to.

Correct this by shifting the whole mask right by ESIZE bits for the
'top' insns.  This allows us also to simplify the saturation bit
checking (where we had noticed that we needed to look at a different
mask bit for the 'top' insn.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Peter Maydell 2021-08-13 17:11:47 +01:00
parent ed5a59d61f
commit a5e59e8dcb

View File

@ -1358,6 +1358,7 @@ DO_VSHLL_ALL(vshllt, true)
TYPE *d = vd; \
uint16_t mask = mve_element_mask(env); \
unsigned le; \
mask >>= ESIZE * TOP; \
for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
TYPE r = FN(m[H##LESIZE(le)], shift); \
mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
@ -1419,11 +1420,12 @@ static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max,
uint16_t mask = mve_element_mask(env); \
bool qc = false; \
unsigned le; \
mask >>= ESIZE * TOP; \
for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
bool sat = false; \
TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \
mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
qc |= sat && (mask & 1 << (TOP * ESIZE)); \
qc |= sat & mask & 1; \
} \
if (qc) { \
env->vfp.qc[0] = qc; \