@@ -326,6 +326,51 @@ DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_addp_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_addp_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_addp_zpzz_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_addp_zpzz_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_smaxp_zpzz_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_umaxp_zpzz_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sminp_zpzz_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_b, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_uminp_zpzz_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve_asr_zpzw_b, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_asr_zpzw_h, TCG_CALL_NO_RWG,
@@ -1143,3 +1143,11 @@ SRHADD 01000100 .. 010 100 100 ... ..... ..... @rdn_pg_rm
URHADD 01000100 .. 010 101 100 ... ..... ..... @rdn_pg_rm
SHSUB 01000100 .. 010 110 100 ... ..... ..... @rdm_pg_rn # SHSUBR
UHSUB 01000100 .. 010 111 100 ... ..... ..... @rdm_pg_rn # UHSUBR
+
+### SVE2 integer pairwise arithmetic
+
+ADDP 01000100 .. 010 001 101 ... ..... ..... @rdn_pg_rm
+SMAXP 01000100 .. 010 100 101 ... ..... ..... @rdn_pg_rm
+UMAXP 01000100 .. 010 101 101 ... ..... ..... @rdn_pg_rm
+SMINP 01000100 .. 010 110 101 ... ..... ..... @rdn_pg_rm
+UMINP 01000100 .. 010 111 101 ... ..... ..... @rdn_pg_rm
@@ -681,6 +681,82 @@ DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D)
#undef DO_ZPZZ
#undef DO_ZPZZ_D
+/*
+ * Three operand expander, operating on element pairs.
+ * If the slot I is even, the elements from from VN {I, I+1}.
+ * If the slot I is odd, the elements from from VM {I-1, I}.
+ * Load all of the input elements in each pair before overwriting output.
+ */
+#define DO_ZPZZ_PAIR(NAME, TYPE, H, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ for (i = 0; i < opr_sz; ) { \
+ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \
+ do { \
+ TYPE n0 = *(TYPE *)(vn + H(i)); \
+ TYPE m0 = *(TYPE *)(vm + H(i)); \
+ TYPE n1 = *(TYPE *)(vn + H(i + sizeof(TYPE))); \
+ TYPE m1 = *(TYPE *)(vm + H(i + sizeof(TYPE))); \
+ if (pg & 1) { \
+ *(TYPE *)(vd + H(i)) = OP(n0, n1); \
+ } \
+ i += sizeof(TYPE), pg >>= sizeof(TYPE); \
+ if (pg & 1) { \
+ *(TYPE *)(vd + H(i)) = OP(m0, m1); \
+ } \
+ i += sizeof(TYPE), pg >>= sizeof(TYPE); \
+ } while (i & 15); \
+ } \
+}
+
+/* Similarly, specialized for 64-bit operands. */
+#define DO_ZPZZ_PAIR_D(NAME, TYPE, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc) / 8; \
+ TYPE *d = vd, *n = vn, *m = vm; \
+ uint8_t *pg = vg; \
+ for (i = 0; i < opr_sz; i += 2) { \
+ TYPE n0 = n[i], n1 = n[i + 1]; \
+ TYPE m0 = m[i], m1 = m[i + 1]; \
+ if (pg[H1(i)] & 1) { \
+ d[i] = OP(n0, n1); \
+ } \
+ if (pg[H1(i + 1)] & 1) { \
+ d[i + 1] = OP(m0, m1); \
+ } \
+ } \
+}
+
+DO_ZPZZ_PAIR(sve2_addp_zpzz_b, uint8_t, H1_2, DO_ADD)
+DO_ZPZZ_PAIR(sve2_addp_zpzz_h, uint16_t, H1_2, DO_ADD)
+DO_ZPZZ_PAIR(sve2_addp_zpzz_s, uint32_t, H1_4, DO_ADD)
+DO_ZPZZ_PAIR_D(sve2_addp_zpzz_d, uint64_t, DO_ADD)
+
+DO_ZPZZ_PAIR(sve2_umaxp_zpzz_b, uint8_t, H1_2, DO_MAX)
+DO_ZPZZ_PAIR(sve2_umaxp_zpzz_h, uint16_t, H1_2, DO_MAX)
+DO_ZPZZ_PAIR(sve2_umaxp_zpzz_s, uint32_t, H1_4, DO_MAX)
+DO_ZPZZ_PAIR_D(sve2_umaxp_zpzz_d, uint64_t, DO_MAX)
+
+DO_ZPZZ_PAIR(sve2_uminp_zpzz_b, uint8_t, H1_2, DO_MIN)
+DO_ZPZZ_PAIR(sve2_uminp_zpzz_h, uint16_t, H1_2, DO_MIN)
+DO_ZPZZ_PAIR(sve2_uminp_zpzz_s, uint32_t, H1_4, DO_MIN)
+DO_ZPZZ_PAIR_D(sve2_uminp_zpzz_d, uint64_t, DO_MIN)
+
+DO_ZPZZ_PAIR(sve2_smaxp_zpzz_b, int8_t, H1_2, DO_MAX)
+DO_ZPZZ_PAIR(sve2_smaxp_zpzz_h, int16_t, H1_2, DO_MAX)
+DO_ZPZZ_PAIR(sve2_smaxp_zpzz_s, int32_t, H1_4, DO_MAX)
+DO_ZPZZ_PAIR_D(sve2_smaxp_zpzz_d, int64_t, DO_MAX)
+
+DO_ZPZZ_PAIR(sve2_sminp_zpzz_b, int8_t, H1_2, DO_MIN)
+DO_ZPZZ_PAIR(sve2_sminp_zpzz_h, int16_t, H1_2, DO_MIN)
+DO_ZPZZ_PAIR(sve2_sminp_zpzz_s, int32_t, H1_4, DO_MIN)
+DO_ZPZZ_PAIR_D(sve2_sminp_zpzz_d, int64_t, DO_MIN)
+
+#undef DO_ZPZZ_PAIR
+#undef DO_ZPZZ_PAIR_D
+
/* Three-operand expander, controlled by a predicate, in which the
* third operand is "wide". That is, for D = N op M, the same 64-bit
* value of M is used with all of the narrower values of N.
@@ -5523,3 +5523,9 @@ DO_SVE2_ZPZZ(SHSUB, shsub)
DO_SVE2_ZPZZ(UHADD, uhadd)
DO_SVE2_ZPZZ(URHADD, urhadd)
DO_SVE2_ZPZZ(UHSUB, uhsub)
+
+DO_SVE2_ZPZZ(ADDP, addp)
+DO_SVE2_ZPZZ(SMAXP, smaxp)
+DO_SVE2_ZPZZ(UMAXP, umaxp)
+DO_SVE2_ZPZZ(SMINP, sminp)
+DO_SVE2_ZPZZ(UMINP, uminp)
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- v2: Load all inputs before writing any output (laurent desnogues) --- target/arm/helper-sve.h | 45 ++++++++++++++++++++++ target/arm/sve.decode | 8 ++++ target/arm/sve_helper.c | 76 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 6 +++ 4 files changed, 135 insertions(+) -- 2.25.1