[PATCH 15/31] target/arm: Implement PMULLB and PMULLT

[Richard Henderson]

Signed-off-by: Richard Henderson <address@hidden>
---
 target/arm/cpu.h           | 10 ++++++++++
 target/arm/helper-sve.h    |  1 +
 target/arm/sve.decode      |  2 ++
 target/arm/translate-sve.c | 22 ++++++++++++++++++++++
 target/arm/vec_helper.c    | 26 ++++++++++++++++++++++++++
 5 files changed, 61 insertions(+)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 2314e3c18c..2e9d9f046d 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -3855,6 +3855,16 @@ static inline bool isar_feature_aa64_sve2(const 
ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0;
 }
 
+static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0;
+}
+
+static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2;
+}
+
 /*
  * Feature tests for "does this exist in either 32-bit or 64-bit?"
  */
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index c4784919d2..943839e2dc 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2371,3 +2371,4 @@ DEF_HELPER_FLAGS_4(sve2_umull_zzz_s, TCG_CALL_NO_RWG, 
void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve2_umull_zzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_4(sve2_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_pmull_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 2410dd85a1..04bf9e5ce8 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1204,6 +1204,8 @@ USUBWT          01000101 .. 0 ..... 010 111 ..... .....  
@rd_rn_rm
 
 SQDMULLB_zzz    01000101 .. 0 ..... 011 000 ..... .....  @rd_rn_rm
 SQDMULLT_zzz    01000101 .. 0 ..... 011 001 ..... .....  @rd_rn_rm
+PMULLB          01000101 .. 0 ..... 011 010 ..... .....  @rd_rn_rm
+PMULLT          01000101 .. 0 ..... 011 011 ..... .....  @rd_rn_rm
 SMULLB_zzz      01000101 .. 0 ..... 011 100 ..... .....  @rd_rn_rm
 SMULLT_zzz      01000101 .. 0 ..... 011 101 ..... .....  @rd_rn_rm
 UMULLB_zzz      01000101 .. 0 ..... 011 110 ..... .....  @rd_rn_rm
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index c66ec9eb83..67416a25ce 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -6064,6 +6064,28 @@ DO_SVE2_ZZZ_TB(SMULLT_zzz, smull_zzz, true, true)
 DO_SVE2_ZZZ_TB(UMULLB_zzz, umull_zzz, false, false)
 DO_SVE2_ZZZ_TB(UMULLT_zzz, umull_zzz, true, true)
 
+static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_gvec_pmull_q, gen_helper_sve2_pmull_h,
+        NULL,                    gen_helper_sve2_pmull_d,
+    };
+    if (a->esz == 0 && !dc_isar_feature(aa64_sve2_pmull128, s)) {
+        return false;
+    }
+    return do_sve2_zzw_ool(s, a, fns[a->esz], sel);
+}
+
+static bool trans_PMULLB(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_trans_pmull(s, a, false);
+}
+
+static bool trans_PMULLT(DisasContext *s, arg_rrr_esz *a)
+{
+    return do_trans_pmull(s, a, true);
+}
+
 #define DO_SVE2_ZZZ_WTB(NAME, name, SEL2) \
 static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a)       \
 {                                                               \
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 00dc38c9db..154d32518a 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -1256,6 +1256,32 @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, 
uint32_t desc)
         d[i] = pmull_h(nn, mm);
     }
 }
+
+static uint64_t pmull_d(uint64_t op1, uint64_t op2)
+{
+    uint64_t result = 0;
+    int i;
+
+    for (i = 0; i < 32; ++i) {
+        uint64_t mask = -((op1 >> i) & 1);
+        result ^= (op2 << i) & mask;
+    }
+    return result;
+}
+
+void HELPER(sve2_pmull_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+    int shift = simd_data(desc) * 32;
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    uint64_t *d = vd, *n = vn, *m = vm;
+
+    for (i = 0; i < opr_sz / 8; ++i) {
+        uint64_t nn = (uint32_t)(n[i] >> shift);
+        uint64_t mm = (uint32_t)(m[i] >> shift);
+
+        d[i] = pmull_d(nn, mm);
+    }
+}
 #endif
 
 /*
-- 
2.20.1