new file mode 100644
@@ -0,0 +1,189 @@
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results. */
+/* Chunk 0. */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff0,
+ 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0xfffffffffffffff0,
+ 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0,
+ 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0,
+ 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1800000,
+ 0xc1800000, 0xc1800000 };
+
+/* Chunk 1. */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0xfffffff1, 0xfffffff1,
+ 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0xfffffffffffffff1,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0xfffffff1, 0xfffffff1,
+ 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0xfffffffffffffff1,
+ 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1,
+ 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1,
+ 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0xc1700000, 0xc1700000,
+ 0xc1700000, 0xc1700000 };
+
+/* Chunk 2. */
+VECT_VAR_DECL(expected2,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected2,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,int,32,4) [] = { 0xfffffff2, 0xfffffff2,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,int,64,2) [] = { 0xfffffffffffffff2,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,uint,32,4) [] = { 0xfffffff2, 0xfffffff2,
+ 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected2,uint,64,2) [] = { 0xfffffffffffffff2,
+ 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected2,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2,
+ 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected2,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2,
+ 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected2,hfloat,32,4) [] = { 0xc1600000, 0xc1600000,
+ 0xc1600000, 0xc1600000 };
+
+#define TEST_MSG "VLD1_DUP/VLD1_DUPQ"
+void exec_vld1_dup (void)
+{
+ int i;
+
+ /* Fill vector with buffer item #i. */
+#define TEST_VLD1_DUP(VAR, BUF, Q, T1, T2, W, N) \
+ VECT_VAR(VAR, T1, W, N) = \
+ vld1##Q##_dup_##T2##W(&VECT_VAR(BUF, T1, W, N)[i]); \
+ vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(VAR, T1, W, N))
+
+ DECL_VARIABLE_ALL_VARIANTS(vector);
+#if __ARM_NEON_FP16_INTRINSICS
+ DECL_VARIABLE(vector, float, 16, 4);
+ DECL_VARIABLE(vector, float, 16, 8);
+#endif
+
+ /* Try to read different places from the input buffer. */
+ for (i=0; i<3; i++) {
+ clean_results ();
+
+ TEST_MACRO_ALL_VARIANTS_2_5(TEST_VLD1_DUP, vector, buffer_dup);
+
+ TEST_VLD1_DUP(vector, buffer_dup, , float, f, 32, 2);
+ TEST_VLD1_DUP(vector, buffer_dup, q, float, f, 32, 4);
+
+#if __ARM_NEON_FP16_INTRINSICS
+ TEST_VLD1_DUP(vector, buffer_dup, , float, f, 16, 4);
+ TEST_VLD1_DUP(vector, buffer_dup, q, float, f, 16, 8);
+#endif
+
+ switch (i) {
+ case 0:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected0, "");
+ break;
+ case 1:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected1, "");
+ break;
+ case 2:
+ CHECK_RESULTS_NAMED (TEST_MSG, expected2, "");
+ break;
+ default:
+ abort();
+ }
+ }
+}
+
+int main (void)
+{
+ exec_vld1_dup ();
+ return 0;
+}