target/arm: Implement MVE VCMUL and VCMLA

Implement the MVE VCMUL and VCMLA insns.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 139 insertions, 8 deletions

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index c230610d25..73950403bc 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -440,6 +440,24 @@ DEF_HELPER_FLAGS_4(mve_vfmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfmsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vfmss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vcmul0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmul270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vcmla0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vcmla270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
 DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 3a2056f6b3..403381eef6 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -286,15 +286,29 @@ VQSHL_U          111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev
 VQRSHL_S         111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev
 VQRSHL_U         111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev
 
-VQDMLADH         1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
-VQDMLADHX        1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
-VQRDMLADH        1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
-VQRDMLADHX       1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
+{
+  VCMUL0         111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 0 @2op_sz28
+  VQDMLADH       1110  1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
+  VQDMLSDH       1111  1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
+}
 
-VQDMLSDH         1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op
-VQDMLSDHX        1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
-VQRDMLSDH        1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
-VQRDMLSDHX       1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
+{
+  VCMUL180       111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 0 @2op_sz28
+  VQDMLADHX      111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
+  VQDMLSDHX      111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op
+}
+
+{
+  VCMUL90        111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 1 @2op_sz28
+  VQRDMLADH      111 0 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
+  VQRDMLSDH      111 1 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op
+}
+
+{
+  VCMUL270       111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 1 @2op_sz28
+  VQRDMLADHX     111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
+  VQRDMLSDHX     111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
+}
 
 VQDMULLB         111 . 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 1 @2op_sz28
 VQDMULLT         111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28
@@ -642,3 +656,8 @@ VCADD270_fp       1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_
 
 VFMA              1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp
 VFMS              1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp
+
+VCMLA0            1111 110 00 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
+VCMLA90           1111 110 01 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
+VCMLA180          1111 110 10 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
+VCMLA270          1111 110 11 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index d7f250a445..e478408fdd 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2931,3 +2931,89 @@ DO_VFMA(vfmah, 2, float16, false)
 DO_VFMA(vfmas, 4, float32, false)
 DO_VFMA(vfmsh, 2, float16, true)
 DO_VFMA(vfmss, 4, float32, true)
+
+#define DO_VCMLA(OP, ESIZE, TYPE, ROT, FN)                              \
+    void HELPER(glue(mve_, OP))(CPUARMState *env,                       \
+                                void *vd, void *vn, void *vm)           \
+    {                                                                   \
+        TYPE *d = vd, *n = vn, *m = vm;                                 \
+        TYPE r0, r1, e1, e2, e3, e4;                                    \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        float_status *fpst0, *fpst1;                                    \
+        float_status scratch_fpst;                                      \
+        /* We loop through pairs of elements at a time */               \
+        for (e = 0; e < 16 / ESIZE; e += 2, mask >>= ESIZE * 2) {       \
+            if ((mask & MAKE_64BIT_MASK(0, ESIZE * 2)) == 0) {          \
+                continue;                                               \
+            }                                                           \
+            fpst0 = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 :   \
+                &env->vfp.standard_fp_status;                           \
+            fpst1 = fpst0;                                              \
+            if (!(mask & 1)) {                                          \
+                scratch_fpst = *fpst0;                                  \
+                fpst0 = &scratch_fpst;                                  \
+            }                                                           \
+            if (!(mask & (1 << ESIZE))) {                               \
+                scratch_fpst = *fpst1;                                  \
+                fpst1 = &scratch_fpst;                                  \
+            }                                                           \
+            switch (ROT) {                                              \
+            case 0:                                                     \
+                e1 = m[H##ESIZE(e)];                                    \
+                e2 = n[H##ESIZE(e)];                                    \
+                e3 = m[H##ESIZE(e + 1)];                                \
+                e4 = n[H##ESIZE(e)];                                    \
+                break;                                                  \
+            case 1:                                                     \
+                e1 = TYPE##_chs(m[H##ESIZE(e + 1)]);                    \
+                e2 = n[H##ESIZE(e + 1)];                                \
+                e3 = m[H##ESIZE(e)];                                    \
+                e4 = n[H##ESIZE(e + 1)];                                \
+                break;                                                  \
+            case 2:                                                     \
+                e1 = TYPE##_chs(m[H##ESIZE(e)]);                        \
+                e2 = n[H##ESIZE(e)];                                    \
+                e3 = TYPE##_chs(m[H##ESIZE(e + 1)]);                    \
+                e4 = n[H##ESIZE(e)];                                    \
+                break;                                                  \
+            case 3:                                                     \
+                e1 = m[H##ESIZE(e + 1)];                                \
+                e2 = n[H##ESIZE(e + 1)];                                \
+                e3 = TYPE##_chs(m[H##ESIZE(e)]);                        \
+                e4 = n[H##ESIZE(e + 1)];                                \
+                break;                                                  \
+            default:                                                    \
+                g_assert_not_reached();                                 \
+            }                                                           \
+            r0 = FN(e2, e1, d[H##ESIZE(e)], fpst0);                     \
+            r1 = FN(e4, e3, d[H##ESIZE(e + 1)], fpst1);                 \
+            mergemask(&d[H##ESIZE(e)], r0, mask);                       \
+            mergemask(&d[H##ESIZE(e + 1)], r1, mask >> ESIZE);          \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
+#define DO_VCMULH(N, M, D, S) float16_mul(N, M, S)
+#define DO_VCMULS(N, M, D, S) float32_mul(N, M, S)
+
+#define DO_VCMLAH(N, M, D, S) float16_muladd(N, M, D, 0, S)
+#define DO_VCMLAS(N, M, D, S) float32_muladd(N, M, D, 0, S)
+
+DO_VCMLA(vcmul0h, 2, float16, 0, DO_VCMULH)
+DO_VCMLA(vcmul0s, 4, float32, 0, DO_VCMULS)
+DO_VCMLA(vcmul90h, 2, float16, 1, DO_VCMULH)
+DO_VCMLA(vcmul90s, 4, float32, 1, DO_VCMULS)
+DO_VCMLA(vcmul180h, 2, float16, 2, DO_VCMULH)
+DO_VCMLA(vcmul180s, 4, float32, 2, DO_VCMULS)
+DO_VCMLA(vcmul270h, 2, float16, 3, DO_VCMULH)
+DO_VCMLA(vcmul270s, 4, float32, 3, DO_VCMULS)
+
+DO_VCMLA(vcmla0h, 2, float16, 0, DO_VCMLAH)
+DO_VCMLA(vcmla0s, 4, float32, 0, DO_VCMLAS)
+DO_VCMLA(vcmla90h, 2, float16, 1, DO_VCMLAH)
+DO_VCMLA(vcmla90s, 4, float32, 1, DO_VCMLAS)
+DO_VCMLA(vcmla180h, 2, float16, 2, DO_VCMLAH)
+DO_VCMLA(vcmla180s, 4, float32, 2, DO_VCMLAS)
+DO_VCMLA(vcmla270h, 2, float16, 3, DO_VCMLAH)
+DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index d61abc6d46..d62ed1fc29 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -856,6 +856,14 @@ DO_2OP_FP(VCADD90_fp, vfcadd90)
 DO_2OP_FP(VCADD270_fp, vfcadd270)
 DO_2OP_FP(VFMA, vfma)
 DO_2OP_FP(VFMS, vfms)
+DO_2OP_FP(VCMUL0, vcmul0)
+DO_2OP_FP(VCMUL90, vcmul90)
+DO_2OP_FP(VCMUL180, vcmul180)
+DO_2OP_FP(VCMUL270, vcmul270)
+DO_2OP_FP(VCMLA0, vcmla0)
+DO_2OP_FP(VCMLA90, vcmla90)
+DO_2OP_FP(VCMLA180, vcmla180)
+DO_2OP_FP(VCMLA270, vcmla270)
 
 static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
                           MVEGenTwoOpScalarFn fn)