target-arm: Implement VMULL.P8

Implement VMULL.P8 (the 32x32->64 version of the polynomial multiply
instruction).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

diff --git a/target-arm/helpers.h b/target-arm/helpers.h
index 77f1635..18b488b 100644 (file)
--- a/target-arm/helpers.h
+++ b/target-arm/helpers.h
@@ -277,6 +277,7 @@ DEF_HELPER_2(neon_sub_u16, i32, i32, i32)
 DEF_HELPER_2(neon_mul_u8, i32, i32, i32)
 DEF_HELPER_2(neon_mul_u16, i32, i32, i32)
 DEF_HELPER_2(neon_mul_p8, i32, i32, i32)
+DEF_HELPER_2(neon_mull_p8, i64, i32, i32)
 
 DEF_HELPER_2(neon_tst_u8, i32, i32, i32)
 DEF_HELPER_2(neon_tst_u16, i32, i32, i32)

diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index dc09968..ee253bb 100644 (file)
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -895,6 +895,36 @@ uint32_t HELPER(neon_mul_p8)(uint32_t op1, uint32_t op2)
     return result;
 }
 
+uint64_t HELPER(neon_mull_p8)(uint32_t op1, uint32_t op2)
+{
+    uint64_t result = 0;
+    uint64_t mask;
+    uint64_t op2ex = op2;
+    op2ex = (op2ex & 0xff) |
+        ((op2ex & 0xff00) << 8) |
+        ((op2ex & 0xff0000) << 16) |
+        ((op2ex & 0xff000000) << 24);
+    while (op1) {
+        mask = 0;
+        if (op1 & 1) {
+            mask |= 0xffff;
+        }
+        if (op1 & (1 << 8)) {
+            mask |= (0xffffU << 16);
+        }
+        if (op1 & (1 << 16)) {
+            mask |= (0xffffULL << 32);
+        }
+        if (op1 & (1 << 24)) {
+            mask |= (0xffffULL << 48);
+        }
+        result ^= op2ex & mask;
+        op1 = (op1 >> 1) & 0x7f7f7f7f;
+        op2ex <<= 1;
+    }
+    return result;
+}
+
 #define NEON_FN(dest, src1, src2) dest = (src1 & src2) ? -1 : 0
 NEON_VOP(tst_u8, neon_u8, 4)
 NEON_VOP(tst_u16, neon_u16, 2)

diff --git a/target-arm/translate.c b/target-arm/translate.c
index 362d1d0..0c93896 100644 (file)
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -5124,8 +5124,10 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                         gen_neon_mull(cpu_V0, tmp, tmp2, size, u);
                         break;
                     case 14: /* Polynomial VMULL */
-                        cpu_abort(env, "Polynomial VMULL not implemented");
-
+                        gen_helper_neon_mull_p8(cpu_V0, tmp, tmp2);
+                        dead_tmp(tmp2);
+                        dead_tmp(tmp);
+                        break;
                     default: /* 15 is RESERVED.  */
                         return 1;
                     }