On 7/13/21 6:37 AM, Peter Maydell wrote:
+#define DO_VIDUP(OP, ESIZE, TYPE, FN) \
+ uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \
+ uint32_t offset, uint32_t imm) \
+ { \
+ TYPE *d = vd; \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned e; \
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
+ mergemask(&d[H##ESIZE(e)], offset, mask); \
+ offset = FN(offset, imm); \
+ } \
+ mve_advance_vpt(env); \
+ return offset; \
+ }
+
+#define DO_VIWDUP(OP, ESIZE, TYPE, FN) \
+ uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \
+ uint32_t offset, uint32_t wrap, \
+ uint32_t imm) \
+ { \
+ TYPE *d = vd; \
+ uint16_t mask = mve_element_mask(env); \
+ unsigned e; \
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
+ mergemask(&d[H##ESIZE(e)], offset, mask); \
+ offset = FN(offset, wrap, imm); \
+ } \
+ mve_advance_vpt(env); \
+ return offset; \
+ }
+
+#define DO_VIDUP_ALL(OP, FN) \
+ DO_VIDUP(OP##b, 1, int8_t, FN) \
+ DO_VIDUP(OP##h, 2, int16_t, FN) \
+ DO_VIDUP(OP##w, 4, int32_t, FN)
+
+#define DO_VIWDUP_ALL(OP, FN) \
+ DO_VIWDUP(OP##b, 1, int8_t, FN) \
+ DO_VIWDUP(OP##h, 2, int16_t, FN) \
+ DO_VIWDUP(OP##w, 4, int32_t, FN)
Would it be useful to merge VIDUP and VIWDUP by passing wrap == 0?
Or merging VIDUP and VDDUP by negating imm?
Anyway,
Reviewed-by: Richard Henderson <richard.hender...@linaro.org>
r~
