Implement with a DO_COMPACT macro and general purpose
predicate handling.
Signed-off-by: Richard Henderson <[email protected]>
---
target/arm/tcg/sve_helper.c | 51 +++++++++++++++----------------------
1 file changed, 21 insertions(+), 30 deletions(-)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index a13ccf4b85..40cf567b0d 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -3637,39 +3637,30 @@ DO_TRN(sve2_trn_q, Int128, )
#undef DO_UZP
#undef DO_TRN
-void HELPER(sve_compact_s)(void *vd, void *vn, void *vg, uint32_t desc)
-{
- intptr_t i, j, opr_sz = simd_oprsz(desc) / 4;
- uint32_t *d = vd, *n = vn;
- uint8_t *pg = vg;
-
- for (i = j = 0; i < opr_sz; i++) {
- if (pg[H1(i / 2)] & (i & 1 ? 0x10 : 0x01)) {
- d[H4(j)] = n[H4(i)];
- j++;
- }
- }
- for (; j < opr_sz; j++) {
- d[H4(j)] = 0;
- }
+#define DO_COMPACT(NAME, TYPE, H) \
+void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \
+{ \
+ intptr_t i = 0, j = 0, oprsz = simd_oprsz(desc); \
+ do { \
+ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \
+ do { \
+ if (pg & 1) { \
+ *(TYPE *)(vd + H(j)) = *(TYPE *)(vn + H(i)); \
+ j += sizeof(TYPE); \
+ } \
+ i += sizeof(TYPE); \
+ pg >>= sizeof(TYPE); \
+ } while (i & 15); \
+ } while (i < oprsz); \
+ for (; j < oprsz; j += sizeof(TYPE)) { \
+ *(TYPE *)(vd + H(j)) = 0; \
+ } \
}
-void HELPER(sve_compact_d)(void *vd, void *vn, void *vg, uint32_t desc)
-{
- intptr_t i, j, opr_sz = simd_oprsz(desc) / 8;
- uint64_t *d = vd, *n = vn;
- uint8_t *pg = vg;
+DO_COMPACT(sve_compact_s, uint32_t, H1_4)
+DO_COMPACT(sve_compact_d, uint64_t, H1_8)
- for (i = j = 0; i < opr_sz; i++) {
- if (pg[H1(i)] & 1) {
- d[j] = n[i];
- j++;
- }
- }
- for (; j < opr_sz; j++) {
- d[j] = 0;
- }
-}
+#undef DO_COMPACT
/* Similar to the ARM LastActiveElement pseudocode function, except the
* result is multiplied by the element size. This includes the not found
--
2.43.0
