[PULL 105/114] target/arm: Implement aarch64 SUDOT, USDOT

[Peter Maydell <peter.maydell@linaro.org>]

From: Richard Henderson <richard.henderson@linaro.org>

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-84-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/cpu.h           |  5 +++++
 target/arm/translate-a64.c | 25 +++++++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 55383cb0661..8ecb2a1c89e 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -4216,6 +4216,11 @@ static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2;
 }
 
+static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0;
+}
+
 static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0;
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index a8edd2d2815..c8754817842 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -12175,6 +12175,13 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
         }
         feature = dc_isar_feature(aa64_dp, s);
         break;
+    case 0x03: /* USDOT */
+        if (size != MO_32) {
+            unallocated_encoding(s);
+            return;
+        }
+        feature = dc_isar_feature(aa64_i8mm, s);
+        break;
     case 0x18: /* FCMLA, #0 */
     case 0x19: /* FCMLA, #90 */
     case 0x1a: /* FCMLA, #180 */
@@ -12215,6 +12222,10 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
                          u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b);
         return;
 
+    case 0x3: /* USDOT */
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_usdot_b);
+        return;
+
     case 0x8: /* FCMLA, #0 */
     case 0x9: /* FCMLA, #90 */
     case 0xa: /* FCMLA, #180 */
@@ -13360,6 +13371,13 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
             return;
         }
         break;
+    case 0x0f: /* SUDOT, USDOT */
+        if (is_scalar || (size & 1) || !dc_isar_feature(aa64_i8mm, s)) {
+            unallocated_encoding(s);
+            return;
+        }
+        size = MO_32;
+        break;
     case 0x11: /* FCMLA #0 */
     case 0x13: /* FCMLA #90 */
     case 0x15: /* FCMLA #180 */
@@ -13474,6 +13492,13 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
                          u ? gen_helper_gvec_udot_idx_b
                          : gen_helper_gvec_sdot_idx_b);
         return;
+    case 0x0f: /* SUDOT, USDOT */
+        gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index,
+                         extract32(insn, 23, 1)
+                         ? gen_helper_gvec_usdot_idx_b
+                         : gen_helper_gvec_sudot_idx_b);
+        return;
+
     case 0x11: /* FCMLA #0 */
     case 0x13: /* FCMLA #90 */
     case 0x15: /* FCMLA #180 */
-- 
2.20.1