diff mbox

[ARM-AArch64/testsuite,v2,21/21] Add vuzp and vzip tests.

Message ID 1404209174-25364-22-git-send-email-christophe.lyon@linaro.org
State New
Headers show

Commit Message

Christophe Lyon July 1, 2014, 10:06 a.m. UTC

diff mbox

Patch

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 775257e..14f80a0 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,10 @@ 
 2014-06-30  Christophe Lyon  <christophe.lyon@linaro.org>
 
+	* gcc.target/aarch64/neon-intrinsics/vuzp.c: New file.
+	* gcc.target/aarch64/neon-intrinsics/vzip.c: Likewise.
+
+2014-06-30  Christophe Lyon  <christophe.lyon@linaro.org>
+
 	* gcc.target/aarch64/neon-intrinsics/vmul.c: New file.
 
 2014-06-30  Christophe Lyon  <christophe.lyon@linaro.org>
diff --git a/gcc/testsuite/gcc.target/aarch64/neon-intrinsics/vuzp.c b/gcc/testsuite/gcc.target/aarch64/neon-intrinsics/vuzp.c
new file mode 100644
index 0000000..53f875e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/neon-intrinsics/vuzp.c
@@ -0,0 +1,245 @@ 
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results splitted in several chunks.  */
+/* Chunk 0.  */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+					0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff1,
+					 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+					 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff1,
+					  0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0,
+					  0xfffffff1 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+					 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff1,
+					  0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+					 0xf4, 0xf5, 0xf6, 0xf7,
+					 0xf8, 0xf9, 0xfa, 0xfb,
+					 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff1,
+					 0xfff2, 0xfff3,
+					 0xfff4, 0xfff5,
+					 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff1,
+					 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0x3333333333333333,
+					 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+					  0xf4, 0xf5, 0xf6, 0xf7,
+					  0xf8, 0xf9, 0xfa, 0xfb,
+					  0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff1,
+					  0xfff2, 0xfff3,
+					  0xfff4, 0xfff5,
+					  0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff1,
+					  0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0x3333333333333333,
+					  0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3,
+					  0xf4, 0xf5, 0xf6, 0xf7,
+					  0xf8, 0xf9, 0xfa, 0xfb,
+					  0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff1,
+					  0xfff2, 0xfff3,
+					  0xfff4, 0xfff5,
+					  0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1700000,
+					    0xc1600000, 0xc1500000 };
+
+/* Chunk 1.  */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0x11, 0x11, 0x11, 0x11,
+					0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0x55, 0x55, 0x55, 0x55,
+					 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0x55, 0x55, 0x55, 0x55,
+					 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0x11, 0x11, 0x11, 0x11,
+					 0x11, 0x11, 0x11, 0x11,
+					 0x11, 0x11, 0x11, 0x11,
+					 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0x22, 0x22, 0x22, 0x22,
+					 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0x3333333333333333,
+					 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0x55, 0x55, 0x55, 0x55,
+					  0x55, 0x55, 0x55, 0x55,
+					  0x55, 0x55, 0x55, 0x55,
+					  0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0x66, 0x66, 0x66, 0x66,
+					  0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0x77, 0x77, 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0x3333333333333333,
+					  0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0x55, 0x55, 0x55, 0x55,
+					  0x55, 0x55, 0x55, 0x55,
+					  0x55, 0x55, 0x55, 0x55,
+					  0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0x66, 0x66, 0x66, 0x66,
+					  0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0x42073333, 0x42073333,
+					    0x42073333, 0x42073333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vuzp
+#define TEST_MSG "VUZP/VUZPQ"
+#endif
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+void FNNAME (INSN_NAME) (void)
+{
+  /* In this case, output variables are arrays of vectors.  */
+#define DECL_VUZP(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_VUZP(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_VUZP()				\
+  DECL_VUZP(int, 8, 8);				\
+  DECL_VUZP(int, 16, 4);			\
+  DECL_VUZP(int, 32, 2);			\
+  DECL_VUZP(uint, 8, 8);			\
+  DECL_VUZP(uint, 16, 4);			\
+  DECL_VUZP(uint, 32, 2);			\
+  DECL_VUZP(poly, 8, 8);			\
+  DECL_VUZP(poly, 16, 4);			\
+  DECL_VUZP(float, 32, 2);			\
+  DECL_VUZP(int, 8, 16);			\
+  DECL_VUZP(int, 16, 8);			\
+  DECL_VUZP(int, 32, 4);			\
+  DECL_VUZP(uint, 8, 16);			\
+  DECL_VUZP(uint, 16, 8);			\
+  DECL_VUZP(uint, 32, 4);			\
+  DECL_VUZP(poly, 8, 16);			\
+  DECL_VUZP(poly, 16, 8);			\
+  DECL_VUZP(float, 32, 4)
+
+  DECL_ALL_VUZP();
+
+  /* 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_VUZP(INSN)			\
+  TEST_VUZP(INSN, , int, s, 8, 8);		\
+  TEST_VUZP(INSN, , int, s, 16, 4);		\
+  TEST_VUZP(INSN, , int, s, 32, 2);		\
+  TEST_VUZP(INSN, , uint, u, 8, 8);		\
+  TEST_VUZP(INSN, , uint, u, 16, 4);		\
+  TEST_VUZP(INSN, , uint, u, 32, 2);		\
+  TEST_VUZP(INSN, , poly, p, 8, 8);		\
+  TEST_VUZP(INSN, , poly, p, 16, 4);		\
+  TEST_VUZP(INSN, , float, f, 32, 2);		\
+  TEST_VUZP(INSN, q, int, s, 8, 16);		\
+  TEST_VUZP(INSN, q, int, s, 16, 8);		\
+  TEST_VUZP(INSN, q, int, s, 32, 4);		\
+  TEST_VUZP(INSN, q, uint, u, 8, 16);		\
+  TEST_VUZP(INSN, q, uint, u, 16, 8);		\
+  TEST_VUZP(INSN, q, uint, u, 32, 4);		\
+  TEST_VUZP(INSN, q, poly, p, 8, 16);		\
+  TEST_VUZP(INSN, q, poly, p, 16, 8);		\
+  TEST_VUZP(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_VUZP(INSN_NAME);
+
+  CHECK_RESULTS_NAMED (TEST_MSG, expected0, "(chunk 0)");
+
+  TEST_ALL_EXTRA_CHUNKS();
+  CHECK_RESULTS_NAMED (TEST_MSG, expected1, "(chunk 1)");
+}
+
+int main (void)
+{
+  FNNAME (INSN_NAME) ();
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/neon-intrinsics/vzip.c b/gcc/testsuite/gcc.target/aarch64/neon-intrinsics/vzip.c
new file mode 100644
index 0000000..a1f1eee
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/neon-intrinsics/vzip.c
@@ -0,0 +1,243 @@ 
+#include <arm_neon.h>
+#include "arm-neon-ref.h"
+#include "compute-ref-data.h"
+
+/* Expected results splitted in several chunks.  */
+/* Chunk 0.  */
+VECT_VAR_DECL(expected0,int,8,8) [] = { 0xf0, 0xf4, 0x11, 0x11,
+					0xf1, 0xf5, 0x11, 0x11 };
+VECT_VAR_DECL(expected0,int,16,4) [] = { 0xfff0, 0xfff2,
+					 0x22, 0x22 };
+VECT_VAR_DECL(expected0,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected0,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55,
+					 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,uint,16,4) [] = { 0xfff0, 0xfff2,
+					  0x66, 0x66 };
+VECT_VAR_DECL(expected0,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected0,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55,
+					 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,poly,16,4) [] = { 0xfff0, 0xfff2,
+					  0x66, 0x66 };
+VECT_VAR_DECL(expected0,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected0,int,8,16) [] = { 0xf0, 0xf8, 0x11, 0x11,
+					 0xf1, 0xf9, 0x11, 0x11,
+					 0xf2, 0xfa, 0x11, 0x11,
+					 0xf3, 0xfb, 0x11, 0x11 };
+VECT_VAR_DECL(expected0,int,16,8) [] = { 0xfff0, 0xfff4, 0x22, 0x22,
+					 0xfff1, 0xfff5, 0x22, 0x22 };
+VECT_VAR_DECL(expected0,int,32,4) [] = { 0xfffffff0, 0xfffffff2,
+					 0x33, 0x33 };
+VECT_VAR_DECL(expected0,int,64,2) [] = { 0x3333333333333333,
+					 0x3333333333333333 };
+VECT_VAR_DECL(expected0,uint,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55,
+					  0xf1, 0xf9, 0x55, 0x55,
+					  0xf2, 0xfa, 0x55, 0x55,
+					  0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,uint,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66,
+					  0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected0,uint,32,4) [] = { 0xfffffff0, 0xfffffff2,
+					  0x77, 0x77 };
+VECT_VAR_DECL(expected0,uint,64,2) [] = { 0x3333333333333333,
+					  0x3333333333333333 };
+VECT_VAR_DECL(expected0,poly,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55,
+					  0xf1, 0xf9, 0x55, 0x55,
+					  0xf2, 0xfa, 0x55, 0x55,
+					  0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected0,poly,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66,
+					  0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected0,hfloat,32,4) [] = { 0xc1800000, 0xc1600000,
+					    0x42073333, 0x42073333 };
+
+/* Chunk 1.  */
+VECT_VAR_DECL(expected1,int,8,8) [] = { 0xf2, 0xf6, 0x11, 0x11,
+					0xf3, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,4) [] = { 0xfff1, 0xfff3,
+					 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55,
+					 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,4) [] = { 0xfff1, 0xfff3,
+					  0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55,
+					 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,4) [] = { 0xfff1, 0xfff3,
+					  0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected1,int,8,16) [] = { 0xf4, 0xfc, 0x11, 0x11,
+					 0xf5, 0xfd, 0x11, 0x11,
+					 0xf6, 0xfe, 0x11, 0x11,
+					 0xf7, 0xff, 0x11, 0x11 };
+VECT_VAR_DECL(expected1,int,16,8) [] = { 0xfff2, 0xfff6, 0x22, 0x22,
+					 0xfff3, 0xfff7, 0x22, 0x22 };
+VECT_VAR_DECL(expected1,int,32,4) [] = { 0xfffffff1, 0xfffffff3,
+					 0x33, 0x33 };
+VECT_VAR_DECL(expected1,int,64,2) [] = { 0x3333333333333333,
+					 0x3333333333333333 };
+VECT_VAR_DECL(expected1,uint,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55,
+					  0xf5, 0xfd, 0x55, 0x55,
+					  0xf6, 0xfe, 0x55, 0x55,
+					  0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,uint,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66,
+					  0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,uint,32,4) [] = { 0xfffffff1, 0xfffffff3,
+					  0x77, 0x77 };
+VECT_VAR_DECL(expected1,uint,64,2) [] = { 0x3333333333333333,
+					  0x3333333333333333 };
+VECT_VAR_DECL(expected1,poly,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55,
+					  0xf5, 0xfd, 0x55, 0x55,
+					  0xf6, 0xfe, 0x55, 0x55,
+					  0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected1,poly,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66,
+					  0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected1,hfloat,32,4) [] = { 0xc1700000, 0xc1500000,
+					    0x42073333, 0x42073333 };
+
+#ifndef INSN_NAME
+#define INSN_NAME vzip
+#define TEST_MSG "VZIP/VZIPQ"
+#endif
+
+#define FNNAME1(NAME) exec_ ## NAME
+#define FNNAME(NAME) FNNAME1(NAME)
+
+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)");
+}
+
+int main (void)
+{
+  FNNAME (INSN_NAME) ();
+
+  return 0;
+}