diff --git a/src/mono/mono/mini/mini-llvm.c b/src/mono/mono/mini/mini-llvm.c
index 890e6cad878c6..6403c739a03a8 100644
--- a/src/mono/mono/mini/mini-llvm.c
+++ b/src/mono/mono/mini/mini-llvm.c
@@ -9289,7 +9289,7 @@ MONO_RESTORE_WARNING
 			break;
 		}
 
-		case OP_SSSE3_ABS: {
+		case OP_VECTOR_IABS: {
 			// %sub = sub <16 x i8> zeroinitializer, %arg
 			// %cmp = icmp sgt <16 x i8> %arg, zeroinitializer
 			// %abs = select <16 x i1> %cmp, <16 x i8> %arg, <16 x i8> %sub
diff --git a/src/mono/mono/mini/mini-ops.h b/src/mono/mono/mini/mini-ops.h
index 1123be8b4d689..b98c00b0b1709 100644
--- a/src/mono/mono/mini/mini-ops.h
+++ b/src/mono/mono/mini/mini-ops.h
@@ -1026,6 +1026,8 @@ MINI_OP(OP_CVTPS2PD, "cvtps2pd", XREG, XREG, NONE)
 MINI_OP(OP_CVTTPD2DQ, "cvttpd2dq", XREG, XREG, NONE)
 MINI_OP(OP_CVTTPS2DQ, "cvttps2dq", XREG, XREG, NONE)
 
+MINI_OP(OP_VECTOR_IABS, "vector_integer_abs", XREG, XREG, NONE)
+
 /* sse 1 */
 /* inst_c1 is target type */
 MINI_OP(OP_SSE_LOADU, "sse_loadu", XREG, XREG, NONE)
@@ -1112,7 +1114,6 @@ MINI_OP(OP_SSE3_MOVSLDUP, "sse3_movsldup", XREG, XREG, NONE)
 MINI_OP(OP_SSE3_MOVDDUP_MEM, "sse3_movddup_mem", XREG, IREG, NONE)
 
 /* ssse 3 */
-MINI_OP(OP_SSSE3_ABS, "ssse3_abs", XREG, XREG, NONE)
 MINI_OP(OP_SSSE3_SHUFFLE, "ssse3_shuffle", XREG, XREG, XREG)
 MINI_OP3(OP_SSSE3_ALIGNR, "ssse3_alignr", XREG, XREG, XREG, IREG)
 
diff --git a/src/mono/mono/mini/simd-intrinsics.c b/src/mono/mono/mini/simd-intrinsics.c
index 80b966732904b..78c6a17fca101 100644
--- a/src/mono/mono/mini/simd-intrinsics.c
+++ b/src/mono/mono/mini/simd-intrinsics.c
@@ -1130,12 +1130,27 @@ emit_sri_vector (MonoCompile *cfg, MonoMethod *cmethod, MonoMethodSignature *fsi
 	case SN_Abs: {
 		if (!is_element_type_primitive (fsig->params [0]))
 			return NULL;
-#ifdef TARGET_ARM64
 		if (type_enum_is_unsigned (arg0_type))
 			return NULL;
-
+#ifdef TARGET_ARM64
 		int iid = type_enum_is_float (arg0_type) ? INTRINS_AARCH64_ADV_SIMD_FABS : INTRINS_AARCH64_ADV_SIMD_ABS;
 		return emit_simd_ins_for_sig (cfg, klass, OP_XOP_OVR_X_X, iid, arg0_type, fsig, args);
+#elif defined(TARGET_AMD64)
+		MonoClass *arg_class = mono_class_from_mono_type_internal (fsig->params [0]);
+		int size = mono_class_value_size (arg_class, NULL);
+		if (size != 16) 		// Works only with Vector128
+			return NULL;
+
+		if (type_enum_is_float(arg0_type)) {
+			// args [0] & ~vector(-0.0)
+			MonoInst *zero = emit_xzero(cfg, arg_class);	// 0.0
+			zero = emit_simd_ins (cfg, klass, OP_NEGATION, zero->dreg, -1); // -0.0
+			MonoInst *ins = emit_simd_ins (cfg, klass, OP_SSE_ANDN, zero->dreg, args [0]->dreg);
+			ins->inst_c1 = arg0_type;
+			return ins;
+		} else {
+			return emit_simd_ins_for_sig (cfg, klass, OP_VECTOR_IABS, -1, arg0_type, fsig, args);
+		}
 #else
 		return NULL;
 #endif
@@ -3403,7 +3418,7 @@ static SimdIntrinsic sse3_methods [] = {
 };
 
 static SimdIntrinsic ssse3_methods [] = {
-	{SN_Abs, OP_SSSE3_ABS},
+	{SN_Abs, OP_VECTOR_IABS},
 	{SN_AlignRight},
 	{SN_HorizontalAdd},
 	{SN_HorizontalAddSaturate, OP_XOP_X_X_X, INTRINS_SSE_PHADDSW},