[PATCH v6 18/82] target/arm: Implement SVE2 complex integer add

From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org
Subject: [PATCH v6 18/82] target/arm: Implement SVE2 complex integer add
Date: Fri, 30 Apr 2021 13:25:06 -0700	[thread overview]
Message-ID: <20210430202610.1136687-19-richard.henderson@linaro.org> (raw)
In-Reply-To: <20210430202610.1136687-1-richard.henderson@linaro.org>

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Fix subtraction ordering (laurent desnogues).
---
 target/arm/helper-sve.h    | 10 +++++++++
 target/arm/sve.decode      |  9 ++++++++
 target/arm/sve_helper.c    | 42 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 31 ++++++++++++++++++++++++++++
 4 files changed, 92 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 4861481fe0..c2155cc544 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2392,3 +2392,13 @@ DEF_HELPER_FLAGS_4(sve2_bgrp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_bgrp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_bgrp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_bgrp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_cadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_cadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_cadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_cadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqcadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqcadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqcadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqcadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 7cb89a0d47..7508b901d0 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1226,3 +1226,12 @@ EORTB           01000101 .. 0 ..... 10010 1 ..... .....  @rd_rn_rm
 BEXT            01000101 .. 0 ..... 1011 00 ..... .....  @rd_rn_rm
 BDEP            01000101 .. 0 ..... 1011 01 ..... .....  @rd_rn_rm
 BGRP            01000101 .. 0 ..... 1011 10 ..... .....  @rd_rn_rm
+
+#### SVE2 Accumulate
+
+## SVE2 complex integer add
+
+CADD_rot90      01000101 .. 00000 0 11011 0 ..... .....  @rdn_rm
+CADD_rot270     01000101 .. 00000 0 11011 1 ..... .....  @rdn_rm
+SQCADD_rot90    01000101 .. 00000 1 11011 0 ..... .....  @rdn_rm
+SQCADD_rot270   01000101 .. 00000 1 11011 1 ..... .....  @rdn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index d692d2fe3d..2e09c3e55b 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1314,6 +1314,48 @@ DO_BITPERM(sve2_bgrp_d, uint64_t, bitgroup)
 
 #undef DO_BITPERM
 
+#define DO_CADD(NAME, TYPE, H, ADD_OP, SUB_OP)                  \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc)  \
+{                                                               \
+    intptr_t i, opr_sz = simd_oprsz(desc);                      \
+    int sub_r = simd_data(desc);                                \
+    if (sub_r) {                                                \
+        for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) {        \
+            TYPE acc_r = *(TYPE *)(vn + H(i));                  \
+            TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE)));   \
+            TYPE el2_r = *(TYPE *)(vm + H(i));                  \
+            TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE)));   \
+            acc_r = ADD_OP(acc_r, el2_i);                       \
+            acc_i = SUB_OP(acc_i, el2_r);                       \
+            *(TYPE *)(vd + H(i)) = acc_r;                       \
+            *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i;        \
+        }                                                       \
+    } else {                                                    \
+        for (i = 0; i < opr_sz; i += 2 * sizeof(TYPE)) {        \
+            TYPE acc_r = *(TYPE *)(vn + H(i));                  \
+            TYPE acc_i = *(TYPE *)(vn + H(i + sizeof(TYPE)));   \
+            TYPE el2_r = *(TYPE *)(vm + H(i));                  \
+            TYPE el2_i = *(TYPE *)(vm + H(i + sizeof(TYPE)));   \
+            acc_r = SUB_OP(acc_r, el2_i);                       \
+            acc_i = ADD_OP(acc_i, el2_r);                       \
+            *(TYPE *)(vd + H(i)) = acc_r;                       \
+            *(TYPE *)(vd + H(i + sizeof(TYPE))) = acc_i;        \
+        }                                                       \
+    }                                                           \
+}
+
+DO_CADD(sve2_cadd_b, int8_t, H1, DO_ADD, DO_SUB)
+DO_CADD(sve2_cadd_h, int16_t, H1_2, DO_ADD, DO_SUB)
+DO_CADD(sve2_cadd_s, int32_t, H1_4, DO_ADD, DO_SUB)
+DO_CADD(sve2_cadd_d, int64_t,     , DO_ADD, DO_SUB)
+
+DO_CADD(sve2_sqcadd_b, int8_t, H1, DO_SQADD_B, DO_SQSUB_B)
+DO_CADD(sve2_sqcadd_h, int16_t, H1_2, DO_SQADD_H, DO_SQSUB_H)
+DO_CADD(sve2_sqcadd_s, int32_t, H1_4, DO_SQADD_S, DO_SQSUB_S)
+DO_CADD(sve2_sqcadd_d, int64_t,     , do_sqadd_d, do_sqsub_d)
+
+#undef DO_CADD
+
 #define DO_ZZI_SHLL(NAME, TYPEW, TYPEN, HW, HN) \
 void HELPER(NAME)(void *vd, void *vn, uint32_t desc)           \
 {                                                              \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index da2f67fb67..c594c59954 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6285,3 +6285,34 @@ static bool trans_BGRP(DisasContext *s, arg_rrr_esz *a)
     }
     return do_sve2_zzw_ool(s, a, fns[a->esz], 0);
 }
+
+static bool do_cadd(DisasContext *s, arg_rrr_esz *a, bool sq, bool rot)
+{
+    static gen_helper_gvec_3 * const fns[2][4] = {
+        { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h,
+          gen_helper_sve2_cadd_s, gen_helper_sve2_cadd_d },
+        { gen_helper_sve2_sqcadd_b, gen_helper_sve2_sqcadd_h,
+          gen_helper_sve2_sqcadd_s, gen_helper_sve2_sqcadd_d },
+    };
+    return do_sve2_zzw_ool(s, a, fns[sq][a->esz], rot);
+}
+
+static bool trans_CADD_rot90(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_cadd(s, a, false, false);
+}
+
+static bool trans_CADD_rot270(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_cadd(s, a, false, true);
+}
+
+static bool trans_SQCADD_rot90(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_cadd(s, a, true, false);
+}
+
+static bool trans_SQCADD_rot270(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_cadd(s, a, true, true);
+}
-- 
2.25.1


