示例#1
0
void vsli_extra(void)
{
  /* Test cases with maximum shift amount (this amount is different
     from vsri).  */

  DECL_VARIABLE_ALL_VARIANTS(vector);
  DECL_VARIABLE_ALL_VARIANTS(vector2);
  DECL_VARIABLE_ALL_VARIANTS(vector_res);

  clean_results ();

  /* Initialize input "vector" from "buffer".  */
  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);

  /* Fill input vector2 with arbitrary values.  */
  VDUP(vector2, , int, s, 8, 8, 2);
  VDUP(vector2, , int, s, 16, 4, -4);
  VDUP(vector2, , int, s, 32, 2, 3);
  VDUP(vector2, , int, s, 64, 1, 100);
  VDUP(vector2, , uint, u, 8, 8, 20);
  VDUP(vector2, , uint, u, 16, 4, 30);
  VDUP(vector2, , uint, u, 32, 2, 40);
  VDUP(vector2, , uint, u, 64, 1, 2);
  VDUP(vector2, , poly, p, 8, 8, 20);
  VDUP(vector2, , poly, p, 16, 4, 30);
  VDUP(vector2, q, int, s, 8, 16, -10);
  VDUP(vector2, q, int, s, 16, 8, -20);
  VDUP(vector2, q, int, s, 32, 4, -30);
  VDUP(vector2, q, int, s, 64, 2, 24);
  VDUP(vector2, q, uint, u, 8, 16, 12);
  VDUP(vector2, q, uint, u, 16, 8, 3);
  VDUP(vector2, q, uint, u, 32, 4, 55);
  VDUP(vector2, q, uint, u, 64, 2, 3);
  VDUP(vector2, q, poly, p, 8, 16, 12);
  VDUP(vector2, q, poly, p, 16, 8, 3);

  /* Use maximum allowed shift amount.  */
  TEST_VSXI_N(INSN_NAME, , int, s, 8, 8, 7);
  TEST_VSXI_N(INSN_NAME, , int, s, 16, 4, 15);
  TEST_VSXI_N(INSN_NAME, , int, s, 32, 2, 31);
  TEST_VSXI_N(INSN_NAME, , int, s, 64, 1, 63);
  TEST_VSXI_N(INSN_NAME, , uint, u, 8, 8, 7);
  TEST_VSXI_N(INSN_NAME, , uint, u, 16, 4, 15);
  TEST_VSXI_N(INSN_NAME, , uint, u, 32, 2, 31);
  TEST_VSXI_N(INSN_NAME, , uint, u, 64, 1, 63);
  TEST_VSXI_N(INSN_NAME, , poly, p, 8, 8, 7);
  TEST_VSXI_N(INSN_NAME, , poly, p, 16, 4, 15);
  TEST_VSXI_N(INSN_NAME, q, int, s, 8, 16, 7);
  TEST_VSXI_N(INSN_NAME, q, int, s, 16, 8, 15);
  TEST_VSXI_N(INSN_NAME, q, int, s, 32, 4, 31);
  TEST_VSXI_N(INSN_NAME, q, int, s, 64, 2, 63);
  TEST_VSXI_N(INSN_NAME, q, uint, u, 8, 16, 7);
  TEST_VSXI_N(INSN_NAME, q, uint, u, 16, 8, 15);
  TEST_VSXI_N(INSN_NAME, q, uint, u, 32, 4, 31);
  TEST_VSXI_N(INSN_NAME, q, uint, u, 64, 2, 63);
  TEST_VSXI_N(INSN_NAME, q, poly, p, 8, 16, 7);
  TEST_VSXI_N(INSN_NAME, q, poly, p, 16, 8, 15);

  CHECK_RESULTS_NAMED (TEST_MSG, expected_max_shift, "(max shift amount)");
}
示例#2
0
文件: vzip.c 项目: AlexMioMio/gcc
void FNNAME (INSN_NAME) (void)
{
  /* In this case, output variables are arrays of vectors.  */
#define DECL_VZIP(T1, W, N)						\
  VECT_ARRAY_TYPE(T1, W, N, 2) VECT_ARRAY_VAR(result_vec, T1, W, N, 2);	\
  VECT_VAR_DECL(result_bis, T1, W, N)[2 * N]

  /* We need to use a temporary result buffer (result_bis), because
     the one used for other tests is not large enough. A subset of the
     result data is moved from result_bis to result, and it is this
     subset which is used to check the actual behaviour. The next
     macro enables to move another chunk of data from result_bis to
     result.  */
#define TEST_VZIP(INSN, Q, T1, T2, W, N)				\
  VECT_ARRAY_VAR(result_vec, T1, W, N, 2) =				\
    INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
		      VECT_VAR(vector2, T1, W, N));			\
  vst2##Q##_##T2##W(VECT_VAR(result_bis, T1, W, N),			\
		    VECT_ARRAY_VAR(result_vec, T1, W, N, 2));		\
  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis, T1, W, N),	\
	 sizeof(VECT_VAR(result, T1, W, N)));

  /* Overwrite "result" with the contents of "result_bis"[X].  */
#define TEST_EXTRA_CHUNK(T1, W, N, X)					\
  memcpy(VECT_VAR(result, T1, W, N), &(VECT_VAR(result_bis, T1, W, N)[X*N]), \
	 sizeof(VECT_VAR(result, T1, W, N)));

  DECL_VARIABLE_ALL_VARIANTS(vector1);
  DECL_VARIABLE_ALL_VARIANTS(vector2);

  /* We don't need 64 bits variants.  */
#define DECL_ALL_VZIP()				\
  DECL_VZIP(int, 8, 8);				\
  DECL_VZIP(int, 16, 4);			\
  DECL_VZIP(int, 32, 2);			\
  DECL_VZIP(uint, 8, 8);			\
  DECL_VZIP(uint, 16, 4);			\
  DECL_VZIP(uint, 32, 2);			\
  DECL_VZIP(poly, 8, 8);			\
  DECL_VZIP(poly, 16, 4);			\
  DECL_VZIP(float, 32, 2);			\
  DECL_VZIP(int, 8, 16);			\
  DECL_VZIP(int, 16, 8);			\
  DECL_VZIP(int, 32, 4);			\
  DECL_VZIP(uint, 8, 16);			\
  DECL_VZIP(uint, 16, 8);			\
  DECL_VZIP(uint, 32, 4);			\
  DECL_VZIP(poly, 8, 16);			\
  DECL_VZIP(poly, 16, 8);			\
  DECL_VZIP(float, 32, 4)

  DECL_ALL_VZIP();

  /* Initialize input "vector" from "buffer".  */
  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
  VLOAD(vector1, buffer, , float, f, 32, 2);
  VLOAD(vector1, buffer, q, float, f, 32, 4);

  /* Choose arbitrary initialization values.  */
  VDUP(vector2, , int, s, 8, 8, 0x11);
  VDUP(vector2, , int, s, 16, 4, 0x22);
  VDUP(vector2, , int, s, 32, 2, 0x33);
  VDUP(vector2, , uint, u, 8, 8, 0x55);
  VDUP(vector2, , uint, u, 16, 4, 0x66);
  VDUP(vector2, , uint, u, 32, 2, 0x77);
  VDUP(vector2, , poly, p, 8, 8, 0x55);
  VDUP(vector2, , poly, p, 16, 4, 0x66);
  VDUP(vector2, , float, f, 32, 2, 33.6f);

  VDUP(vector2, q, int, s, 8, 16, 0x11);
  VDUP(vector2, q, int, s, 16, 8, 0x22);
  VDUP(vector2, q, int, s, 32, 4, 0x33);
  VDUP(vector2, q, uint, u, 8, 16, 0x55);
  VDUP(vector2, q, uint, u, 16, 8, 0x66);
  VDUP(vector2, q, uint, u, 32, 4, 0x77);
  VDUP(vector2, q, poly, p, 8, 16, 0x55);
  VDUP(vector2, q, poly, p, 16, 8, 0x66);
  VDUP(vector2, q, float, f, 32, 4, 33.8f);

#define TEST_ALL_VZIP(INSN)			\
  TEST_VZIP(INSN, , int, s, 8, 8);		\
  TEST_VZIP(INSN, , int, s, 16, 4);		\
  TEST_VZIP(INSN, , int, s, 32, 2);		\
  TEST_VZIP(INSN, , uint, u, 8, 8);		\
  TEST_VZIP(INSN, , uint, u, 16, 4);		\
  TEST_VZIP(INSN, , uint, u, 32, 2);		\
  TEST_VZIP(INSN, , poly, p, 8, 8);		\
  TEST_VZIP(INSN, , poly, p, 16, 4);		\
  TEST_VZIP(INSN, , float, f, 32, 2);		\
  TEST_VZIP(INSN, q, int, s, 8, 16);		\
  TEST_VZIP(INSN, q, int, s, 16, 8);		\
  TEST_VZIP(INSN, q, int, s, 32, 4);		\
  TEST_VZIP(INSN, q, uint, u, 8, 16);		\
  TEST_VZIP(INSN, q, uint, u, 16, 8);		\
  TEST_VZIP(INSN, q, uint, u, 32, 4);		\
  TEST_VZIP(INSN, q, poly, p, 8, 16);		\
  TEST_VZIP(INSN, q, poly, p, 16, 8);		\
  TEST_VZIP(INSN, q, float, f, 32, 4)

#define TEST_ALL_EXTRA_CHUNKS()			\
  TEST_EXTRA_CHUNK(int, 8, 8, 1);		\
  TEST_EXTRA_CHUNK(int, 16, 4, 1);		\
  TEST_EXTRA_CHUNK(int, 32, 2, 1);		\
  TEST_EXTRA_CHUNK(uint, 8, 8, 1);		\
  TEST_EXTRA_CHUNK(uint, 16, 4, 1);		\
  TEST_EXTRA_CHUNK(uint, 32, 2, 1);		\
  TEST_EXTRA_CHUNK(poly, 8, 8, 1);		\
  TEST_EXTRA_CHUNK(poly, 16, 4, 1);		\
  TEST_EXTRA_CHUNK(float, 32, 2, 1);		\
  TEST_EXTRA_CHUNK(int, 8, 16, 1);		\
  TEST_EXTRA_CHUNK(int, 16, 8, 1);		\
  TEST_EXTRA_CHUNK(int, 32, 4, 1);		\
  TEST_EXTRA_CHUNK(uint, 8, 16, 1);		\
  TEST_EXTRA_CHUNK(uint, 16, 8, 1);		\
  TEST_EXTRA_CHUNK(uint, 32, 4, 1);		\
  TEST_EXTRA_CHUNK(poly, 8, 16, 1);		\
  TEST_EXTRA_CHUNK(poly, 16, 8, 1);		\
  TEST_EXTRA_CHUNK(float, 32, 4, 1)

  clean_results ();

  /* Execute the tests.  */
  TEST_ALL_VZIP(INSN_NAME);

  CHECK_RESULTS_NAMED (TEST_MSG, expected0, "(chunk 0)");

  TEST_ALL_EXTRA_CHUNKS();
  CHECK_RESULTS_NAMED (TEST_MSG, expected1, "(chunk 1)");
}
示例#3
0
void exec_vldX_dup (void)
{
  /* In this case, input variables are arrays of vectors.  */
#define DECL_VLDX_DUP(T1, W, N, X)					\
  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X);	\
  VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]

  /* We need to use a temporary result buffer (result_bis), because
     the one used for other tests is not large enough. A subset of the
     result data is moved from result_bis to result, and it is this
     subset which is used to check the actual behaviour. The next
     macro enables to move another chunk of data from result_bis to
     result.  */
#define TEST_VLDX_DUP(Q, T1, T2, W, N, X)				\
  VECT_ARRAY_VAR(vector, T1, W, N, X) =					\
    vld##X##Q##_dup_##T2##W(&VECT_VAR(buffer_dup, T1, W, N)[0]);	\
									\
  vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N),		\
		      VECT_ARRAY_VAR(vector, T1, W, N, X));		\
  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
	 sizeof(VECT_VAR(result, T1, W, N)));


  /* Overwrite "result" with the contents of "result_bis"[Y].  */
#define TEST_EXTRA_CHUNK(T1, W, N, X,Y)			\
  memcpy(VECT_VAR(result, T1, W, N),			\
	 &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]),	\
	 sizeof(VECT_VAR(result, T1, W, N)));

#define DECL_ALL_VLDX_DUP(X)			\
  DECL_VLDX_DUP(int, 8, 8, X);			\
  DECL_VLDX_DUP(int, 16, 4, X);			\
  DECL_VLDX_DUP(int, 32, 2, X);			\
  DECL_VLDX_DUP(int, 64, 1, X);			\
  DECL_VLDX_DUP(uint, 8, 8, X);			\
  DECL_VLDX_DUP(uint, 16, 4, X);		\
  DECL_VLDX_DUP(uint, 32, 2, X);		\
  DECL_VLDX_DUP(uint, 64, 1, X);		\
  DECL_VLDX_DUP(poly, 8, 8, X);			\
  DECL_VLDX_DUP(poly, 16, 4, X);		\
  DECL_VLDX_DUP(float, 32, 2, X)

#define TEST_ALL_VLDX_DUP(X)			\
  TEST_VLDX_DUP(, int, s, 8, 8, X);		\
  TEST_VLDX_DUP(, int, s, 16, 4, X);		\
  TEST_VLDX_DUP(, int, s, 32, 2, X);		\
  TEST_VLDX_DUP(, int, s, 64, 1, X);		\
  TEST_VLDX_DUP(, uint, u, 8, 8, X);		\
  TEST_VLDX_DUP(, uint, u, 16, 4, X);		\
  TEST_VLDX_DUP(, uint, u, 32, 2, X);		\
  TEST_VLDX_DUP(, uint, u, 64, 1, X);		\
  TEST_VLDX_DUP(, poly, p, 8, 8, X);		\
  TEST_VLDX_DUP(, poly, p, 16, 4, X);		\
  TEST_VLDX_DUP(, float, f, 32, 2, X)

#define TEST_ALL_EXTRA_CHUNKS(X, Y)		\
  TEST_EXTRA_CHUNK(int, 8, 8, X, Y);		\
  TEST_EXTRA_CHUNK(int, 16, 4, X, Y);		\
  TEST_EXTRA_CHUNK(int, 32, 2, X, Y);		\
  TEST_EXTRA_CHUNK(int, 64, 1, X, Y);		\
  TEST_EXTRA_CHUNK(uint, 8, 8, X, Y);		\
  TEST_EXTRA_CHUNK(uint, 16, 4, X, Y);		\
  TEST_EXTRA_CHUNK(uint, 32, 2, X, Y);		\
  TEST_EXTRA_CHUNK(uint, 64, 1, X, Y);		\
  TEST_EXTRA_CHUNK(poly, 8, 8, X, Y);		\
  TEST_EXTRA_CHUNK(poly, 16, 4, X, Y);		\
  TEST_EXTRA_CHUNK(float, 32, 2, X, Y)


  DECL_ALL_VLDX_DUP(2);
  DECL_ALL_VLDX_DUP(3);
  DECL_ALL_VLDX_DUP(4);

  /* Special input buffers of suitable size are needed for vld2/vld3/vld4.  */
  /* Input buffers for vld2, 1 of each size */
  VECT_ARRAY_INIT2(buffer_vld2, int, 8, 8);
  PAD(buffer_vld2_pad, int, 8, 8);
  VECT_ARRAY_INIT2(buffer_vld2, int, 16, 4);
  PAD(buffer_vld2_pad, int, 16, 4);
  VECT_ARRAY_INIT2(buffer_vld2, int, 32, 2);
  PAD(buffer_vld2_pad, int, 32, 2);
  VECT_ARRAY_INIT2(buffer_vld2, int, 64, 1);
  PAD(buffer_vld2_pad, int, 64, 1);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 8, 8);
  PAD(buffer_vld2_pad, uint, 8, 8);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 16, 4);
  PAD(buffer_vld2_pad, uint, 16, 4);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 32, 2);
  PAD(buffer_vld2_pad, uint, 32, 2);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 64, 1);
  PAD(buffer_vld2_pad, uint, 64, 1);
  VECT_ARRAY_INIT2(buffer_vld2, poly, 8, 8);
  PAD(buffer_vld2_pad, poly, 8, 8);
  VECT_ARRAY_INIT2(buffer_vld2, poly, 16, 4);
  PAD(buffer_vld2_pad, poly, 16, 4);
  VECT_ARRAY_INIT2(buffer_vld2, float, 32, 2);
  PAD(buffer_vld2_pad, float, 32, 2);

  VECT_ARRAY_INIT2(buffer_vld2, int, 8, 16);
  PAD(buffer_vld2_pad, int, 8, 16);
  VECT_ARRAY_INIT2(buffer_vld2, int, 16, 8);
  PAD(buffer_vld2_pad, int, 16, 8);
  VECT_ARRAY_INIT2(buffer_vld2, int, 32, 4);
  PAD(buffer_vld2_pad, int, 32, 4);
  VECT_ARRAY_INIT2(buffer_vld2, int, 64, 2);
  PAD(buffer_vld2_pad, int, 64, 2);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 8, 16);
  PAD(buffer_vld2_pad, uint, 8, 16);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 16, 8);
  PAD(buffer_vld2_pad, uint, 16, 8);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 32, 4);
  PAD(buffer_vld2_pad, uint, 32, 4);
  VECT_ARRAY_INIT2(buffer_vld2, uint, 64, 2);
  PAD(buffer_vld2_pad, uint, 64, 2);
  VECT_ARRAY_INIT2(buffer_vld2, poly, 8, 16);
  PAD(buffer_vld2_pad, poly, 8, 16);
  VECT_ARRAY_INIT2(buffer_vld2, poly, 16, 8);
  PAD(buffer_vld2_pad, poly, 16, 8);
  VECT_ARRAY_INIT2(buffer_vld2, float, 32, 4);
  PAD(buffer_vld2_pad, float, 32, 4);

  /* Input buffers for vld3, 1 of each size */
  VECT_ARRAY_INIT3(buffer_vld3, int, 8, 8);
  PAD(buffer_vld3_pad, int, 8, 8);
  VECT_ARRAY_INIT3(buffer_vld3, int, 16, 4);
  PAD(buffer_vld3_pad, int, 16, 4);
  VECT_ARRAY_INIT3(buffer_vld3, int, 32, 2);
  PAD(buffer_vld3_pad, int, 32, 2);
  VECT_ARRAY_INIT3(buffer_vld3, int, 64, 1);
  PAD(buffer_vld3_pad, int, 64, 1);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 8, 8);
  PAD(buffer_vld3_pad, uint, 8, 8);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 16, 4);
  PAD(buffer_vld3_pad, uint, 16, 4);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 32, 2);
  PAD(buffer_vld3_pad, uint, 32, 2);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 64, 1);
  PAD(buffer_vld3_pad, uint, 64, 1);
  VECT_ARRAY_INIT3(buffer_vld3, poly, 8, 8);
  PAD(buffer_vld3_pad, poly, 8, 8);
  VECT_ARRAY_INIT3(buffer_vld3, poly, 16, 4);
  PAD(buffer_vld3_pad, poly, 16, 4);
  VECT_ARRAY_INIT3(buffer_vld3, float, 32, 2);
  PAD(buffer_vld3_pad, float, 32, 2);

  VECT_ARRAY_INIT3(buffer_vld3, int, 8, 16);
  PAD(buffer_vld3_pad, int, 8, 16);
  VECT_ARRAY_INIT3(buffer_vld3, int, 16, 8);
  PAD(buffer_vld3_pad, int, 16, 8);
  VECT_ARRAY_INIT3(buffer_vld3, int, 32, 4);
  PAD(buffer_vld3_pad, int, 32, 4);
  VECT_ARRAY_INIT3(buffer_vld3, int, 64, 2);
  PAD(buffer_vld3_pad, int, 64, 2);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 8, 16);
  PAD(buffer_vld3_pad, uint, 8, 16);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 16, 8);
  PAD(buffer_vld3_pad, uint, 16, 8);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 32, 4);
  PAD(buffer_vld3_pad, uint, 32, 4);
  VECT_ARRAY_INIT3(buffer_vld3, uint, 64, 2);
  PAD(buffer_vld3_pad, uint, 64, 2);
  VECT_ARRAY_INIT3(buffer_vld3, poly, 8, 16);
  PAD(buffer_vld3_pad, poly, 8, 16);
  VECT_ARRAY_INIT3(buffer_vld3, poly, 16, 8);
  PAD(buffer_vld3_pad, poly, 16, 8);
  VECT_ARRAY_INIT3(buffer_vld3, float, 32, 4);
  PAD(buffer_vld3_pad, float, 32, 4);

  /* Input buffers for vld4, 1 of each size */
  VECT_ARRAY_INIT4(buffer_vld4, int, 8, 8);
  PAD(buffer_vld4_pad, int, 8, 8);
  VECT_ARRAY_INIT4(buffer_vld4, int, 16, 4);
  PAD(buffer_vld4_pad, int, 16, 4);
  VECT_ARRAY_INIT4(buffer_vld4, int, 32, 2);
  PAD(buffer_vld4_pad, int, 32, 2);
  VECT_ARRAY_INIT4(buffer_vld4, int, 64, 1);
  PAD(buffer_vld4_pad, int, 64, 1);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 8, 8);
  PAD(buffer_vld4_pad, uint, 8, 8);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 16, 4);
  PAD(buffer_vld4_pad, uint, 16, 4);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 32, 2);
  PAD(buffer_vld4_pad, uint, 32, 2);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 64, 1);
  PAD(buffer_vld4_pad, uint, 64, 1);
  VECT_ARRAY_INIT4(buffer_vld4, poly, 8, 8);
  PAD(buffer_vld4_pad, poly, 8, 8);
  VECT_ARRAY_INIT4(buffer_vld4, poly, 16, 4);
  PAD(buffer_vld4_pad, poly, 16, 4);
  VECT_ARRAY_INIT4(buffer_vld4, float, 32, 2);
  PAD(buffer_vld4_pad, float, 32, 2);

  VECT_ARRAY_INIT4(buffer_vld4, int, 8, 16);
  PAD(buffer_vld4_pad, int, 8, 16);
  VECT_ARRAY_INIT4(buffer_vld4, int, 16, 8);
  PAD(buffer_vld4_pad, int, 16, 8);
  VECT_ARRAY_INIT4(buffer_vld4, int, 32, 4);
  PAD(buffer_vld4_pad, int, 32, 4);
  VECT_ARRAY_INIT4(buffer_vld4, int, 64, 2);
  PAD(buffer_vld4_pad, int, 64, 2);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 8, 16);
  PAD(buffer_vld4_pad, uint, 8, 16);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 16, 8);
  PAD(buffer_vld4_pad, uint, 16, 8);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 32, 4);
  PAD(buffer_vld4_pad, uint, 32, 4);
  VECT_ARRAY_INIT4(buffer_vld4, uint, 64, 2);
  PAD(buffer_vld4_pad, uint, 64, 2);
  VECT_ARRAY_INIT4(buffer_vld4, poly, 8, 16);
  PAD(buffer_vld4_pad, poly, 8, 16);
  VECT_ARRAY_INIT4(buffer_vld4, poly, 16, 8);
  PAD(buffer_vld4_pad, poly, 16, 8);
  VECT_ARRAY_INIT4(buffer_vld4, float, 32, 4);
  PAD(buffer_vld4_pad, float, 32, 4);

  /* Check vld2_dup/vld2q_dup.  */
  clean_results ();
#define TEST_MSG "VLD2_DUP/VLD2Q_DUP"
  TEST_ALL_VLDX_DUP(2);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_0, "chunk 0");

  TEST_ALL_EXTRA_CHUNKS(2, 1);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld2_1, "chunk 1");

  /* Check vld3_dup/vld3q_dup.  */
  clean_results ();
#undef TEST_MSG
#define TEST_MSG "VLD3_DUP/VLD3Q_DUP"
  TEST_ALL_VLDX_DUP(3);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_0, "chunk 0");

  TEST_ALL_EXTRA_CHUNKS(3, 1);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_1, "chunk 1");

  TEST_ALL_EXTRA_CHUNKS(3, 2);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld3_2, "chunk 2");

  /* Check vld4_dup/vld4q_dup */
  clean_results ();
#undef TEST_MSG
#define TEST_MSG "VLD4_DUP/VLD4Q_DUP"
  TEST_ALL_VLDX_DUP(4);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_0, "chunk 0");

  TEST_ALL_EXTRA_CHUNKS(4, 1);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_1, "chunk 1");

  TEST_ALL_EXTRA_CHUNKS(4, 2);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_2, "chunk 2");

  TEST_ALL_EXTRA_CHUNKS(4, 3);
  CHECK_RESULTS_NAMED (TEST_MSG, expected_vld4_3, "chunk 3");
}