[PATCH v2 080/101] target/arm: Implement {ADD, SMIN, SMAX, UMIN, UMAX}QV for SVE2p1

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/helper-sve.h    | 25 ++++++++++++++++++
 target/arm/tcg/sve_helper.c    | 46 ++++++++++++++++++++++++++++++++++
 target/arm/tcg/translate-sve.c | 35 ++++++++++++++++++++++++++
 target/arm/tcg/sve.decode      |  7 ++++++
 4 files changed, 113 insertions(+)

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 74029c641b..5f5ecc2e0d 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -2928,3 +2928,28 @@ DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_addqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_addqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_addqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_addqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_smaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_sminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_umaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index dfc3e5cabe..382c471aaa 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -1814,6 +1814,52 @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN)
 #undef DO_VPZ
 #undef DO_VPZ_D
 
+#define DO_VPQ(NAME, TYPE, H, INIT, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc)          \
+{                                                                       \
+    TYPE tmp[16 / sizeof(TYPE)] = { [0 ... 16 / sizeof(TYPE) - 1] = INIT }; \
+    TYPE *n = vn; uint16_t *g = vg;                                     \
+    uintptr_t oprsz = simd_oprsz(desc);                                 \
+    uintptr_t nseg = oprsz / 16, nsegelt = 16 / sizeof(TYPE);           \
+    for (uintptr_t s = 0; s < nseg; s++) {                              \
+        uint16_t pg = g[H2(s)];                                         \
+        for (uintptr_t e = 0; e < nsegelt; e++, pg >>= sizeof(TYPE)) {  \
+            if (pg & 1) {                                               \
+                tmp[e] = OP(tmp[H(e)], n[s * nsegelt + H(e)]);          \
+            }                                                           \
+        }                                                               \
+    }                                                                   \
+    memcpy(vd, tmp, 16);                                                \
+    clear_tail(vd, 16, simd_maxsz(desc));                               \
+}
+
+DO_VPQ(sve2p1_addqv_b, uint8_t, H1, 0, DO_ADD)
+DO_VPQ(sve2p1_addqv_h, uint16_t, H2, 0, DO_ADD)
+DO_VPQ(sve2p1_addqv_s, uint32_t, H4, 0, DO_ADD)
+DO_VPQ(sve2p1_addqv_d, uint64_t, H8, 0, DO_ADD)
+
+DO_VPQ(sve2p1_smaxqv_b, int8_t, H1, INT8_MIN, DO_MAX)
+DO_VPQ(sve2p1_smaxqv_h, int16_t, H2, INT16_MIN, DO_MAX)
+DO_VPQ(sve2p1_smaxqv_s, int32_t, H4, INT32_MIN, DO_MAX)
+DO_VPQ(sve2p1_smaxqv_d, int64_t, H8, INT64_MIN, DO_MAX)
+
+DO_VPQ(sve2p1_sminqv_b, int8_t, H1, INT8_MAX, DO_MIN)
+DO_VPQ(sve2p1_sminqv_h, int16_t, H2, INT16_MAX, DO_MIN)
+DO_VPQ(sve2p1_sminqv_s, int32_t, H4, INT32_MAX, DO_MIN)
+DO_VPQ(sve2p1_sminqv_d, int64_t, H8, INT64_MAX, DO_MIN)
+
+DO_VPQ(sve2p1_umaxqv_b, uint8_t, H1, 0, DO_MAX)
+DO_VPQ(sve2p1_umaxqv_h, uint16_t, H2, 0, DO_MAX)
+DO_VPQ(sve2p1_umaxqv_s, uint32_t, H4, 0, DO_MAX)
+DO_VPQ(sve2p1_umaxqv_d, uint64_t, H8, 0, DO_MAX)
+
+DO_VPQ(sve2p1_uminqv_b, uint8_t, H1, -1, DO_MIN)
+DO_VPQ(sve2p1_uminqv_h, uint16_t, H2, -1, DO_MIN)
+DO_VPQ(sve2p1_uminqv_s, uint32_t, H4, -1, DO_MIN)
+DO_VPQ(sve2p1_uminqv_d, uint64_t, H8, -1, DO_MIN)
+
+#undef DO_VPQ
+
 /* Two vector operand, one scalar operand, unpredicated.  */
 #define DO_ZZI(NAME, TYPE, OP)                                       \
 void HELPER(NAME)(void *vd, void *vn, uint64_t s64, uint32_t desc)   \
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index e6e2f342ab..ade4914aba 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -828,6 +828,41 @@ TRANS_FEAT(SXTW, aa64_sve, gen_gvec_ool_arg_zpz,
 TRANS_FEAT(UXTW, aa64_sve, gen_gvec_ool_arg_zpz,
            a->esz == 3 ? gen_helper_sve_uxtw_d : NULL, a, 0)
 
+static gen_helper_gvec_3 * const addqv_fns[4] = {
+    gen_helper_sve2p1_addqv_b, gen_helper_sve2p1_addqv_h,
+    gen_helper_sve2p1_addqv_s, gen_helper_sve2p1_addqv_d,
+};
+TRANS_FEAT(ADDQV, aa64_sme2p1_or_sve2p1,
+           gen_gvec_ool_arg_zpz, addqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const smaxqv_fns[4] = {
+    gen_helper_sve2p1_smaxqv_b, gen_helper_sve2p1_smaxqv_h,
+    gen_helper_sve2p1_smaxqv_s, gen_helper_sve2p1_smaxqv_d,
+};
+TRANS_FEAT(SMAXQV, aa64_sme2p1_or_sve2p1,
+           gen_gvec_ool_arg_zpz, smaxqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const sminqv_fns[4] = {
+    gen_helper_sve2p1_sminqv_b, gen_helper_sve2p1_sminqv_h,
+    gen_helper_sve2p1_sminqv_s, gen_helper_sve2p1_sminqv_d,
+};
+TRANS_FEAT(SMINQV, aa64_sme2p1_or_sve2p1,
+           gen_gvec_ool_arg_zpz, sminqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const umaxqv_fns[4] = {
+    gen_helper_sve2p1_umaxqv_b, gen_helper_sve2p1_umaxqv_h,
+    gen_helper_sve2p1_umaxqv_s, gen_helper_sve2p1_umaxqv_d,
+};
+TRANS_FEAT(UMAXQV, aa64_sme2p1_or_sve2p1,
+           gen_gvec_ool_arg_zpz, umaxqv_fns[a->esz], a, 0)
+
+static gen_helper_gvec_3 * const uminqv_fns[4] = {
+    gen_helper_sve2p1_uminqv_b, gen_helper_sve2p1_uminqv_h,
+    gen_helper_sve2p1_uminqv_s, gen_helper_sve2p1_uminqv_d,
+};
+TRANS_FEAT(UMINQV, aa64_sme2p1_or_sve2p1,
+           gen_gvec_ool_arg_zpz, uminqv_fns[a->esz], a, 0)
+
 /*
  *** SVE Integer Reduction Group
  */
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 13a76f773d..f16764a947 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -340,6 +340,13 @@ UMAXV           00000100 .. 001 001 001 ... ..... .....         @rd_pg_rn
 SMINV           00000100 .. 001 010 001 ... ..... .....         @rd_pg_rn
 UMINV           00000100 .. 001 011 001 ... ..... .....         @rd_pg_rn
 
+# SVE2.1 segment reduction
+ADDQV           00000100 .. 000 101 001 ... ..... .....         @rd_pg_rn
+SMAXQV          00000100 .. 001 100 001 ... ..... .....         @rd_pg_rn
+SMINQV          00000100 .. 001 110 001 ... ..... .....         @rd_pg_rn
+UMAXQV          00000100 .. 001 101 001 ... ..... .....         @rd_pg_rn
+UMINQV          00000100 .. 001 111 001 ... ..... .....         @rd_pg_rn
+
 ### SVE Shift by Immediate - Predicated Group
 
 # SVE bitwise shift by immediate (predicated)
-- 
2.43.0