+2018-01-13 Richard Sandiford <richard.sandiford@linaro.org>
+ Alan Hayward <alan.hayward@arm.com>
+ David Sherwood <david.sherwood@arm.com>
+
+ * gcc.target/aarch64/sve/struct_move_1.c: New test.
+ * gcc.target/aarch64/sve/struct_move_2.c: Likewise.
+ * gcc.target/aarch64/sve/struct_move_3.c: Likewise.
+ * gcc.target/aarch64/sve/struct_move_4.c: Likewise.
+ * gcc.target/aarch64/sve/struct_move_5.c: Likewise.
+ * gcc.target/aarch64/sve/struct_move_6.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_1.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_1_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_2.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_2_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_3.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_3_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_4.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_4_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_5.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_5_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_6.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_6_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_7.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_7_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_8.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_8_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_9.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_9_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_10.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_10_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_11.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_11_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_12.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_12_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_13.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_13_run.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_14.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_15.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_16.c: Likewise.
+ * gcc.target/aarch64/sve/struct_vect_17.c: Likewise.
+
2018-01-13 Richard Sandiford <richard.sandiford@linaro.org>
Alan Hayward <alan.hayward@arm.com>
David Sherwood <david.sherwood@arm.com>
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O -msve-vector-bits=256 -mbig-endian --save-temps" } */
+
+typedef char vnx16qi __attribute__((vector_size(32)));
+typedef struct { vnx16qi a[2]; } vnx32qi;
+
+typedef short vnx8hi __attribute__((vector_size(32)));
+typedef struct { vnx8hi a[2]; } vnx16hi;
+
+typedef int vnx4si __attribute__((vector_size(32)));
+typedef struct { vnx4si a[2]; } vnx8si;
+
+typedef long vnx2di __attribute__((vector_size(32)));
+typedef struct { vnx2di a[2]; } vnx4di;
+
+typedef _Float16 vnx8hf __attribute__((vector_size(32)));
+typedef struct { vnx8hf a[2]; } vnx16hf;
+
+typedef float vnx4sf __attribute__((vector_size(32)));
+typedef struct { vnx4sf a[2]; } vnx8sf;
+
+typedef double vnx2df __attribute__((vector_size(32)));
+typedef struct { vnx2df a[2]; } vnx4df;
+
+#define TEST_TYPE(TYPE, REG1, REG2) \
+ void \
+ f1_##TYPE (TYPE *a) \
+ { \
+ register TYPE x asm (#REG1) = a[0]; \
+ asm volatile ("# test " #TYPE " 1 %S0" :: "w" (x)); \
+ register TYPE y asm (#REG2) = x; \
+ asm volatile ("# test " #TYPE " 2 %S0, %S1, %S2" \
+ : "=&w" (x) : "0" (x), "w" (y)); \
+ a[1] = x; \
+ } \
+ /* This must compile, but we don't care how. */ \
+ void \
+ f2_##TYPE (TYPE *a) \
+ { \
+ TYPE x = a[0]; \
+ x.a[0][3] = 1; \
+ x.a[1][2] = 12; \
+ asm volatile ("# %0" :: "w" (x)); \
+ } \
+ void \
+ f3_##TYPE (TYPE *a, int i) \
+ { \
+ TYPE x = a[0]; \
+ x.a[0][i] = 1; \
+ asm volatile ("# %0" :: "w" (x)); \
+ } \
+ void \
+ f4_##TYPE (TYPE *a, int i, int j) \
+ { \
+ TYPE x = a[0]; \
+ x.a[i][j] = 44; \
+ asm volatile ("# %0" :: "w" (x)); \
+ }
+
+TEST_TYPE (vnx32qi, z0, z2)
+TEST_TYPE (vnx16hi, z5, z7)
+TEST_TYPE (vnx8si, z10, z12)
+TEST_TYPE (vnx4di, z15, z17)
+TEST_TYPE (vnx16hf, z18, z20)
+TEST_TYPE (vnx8sf, z21, z23)
+TEST_TYPE (vnx4df, z28, z30)
+
+/* { dg-final { scan-assembler {\tld1b\tz0.b, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1b\tz1.b, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx32qi 1 z0\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z0.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z1.d\n} } } */
+/* { dg-final { scan-assembler { test vnx32qi 2 z0, z0, z2\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz0.b, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz1.b, p[0-7], \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1h\tz5.h, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz6.h, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16hi 1 z5\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz7.d, z5.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz8.d, z6.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16hi 2 z5, z5, z7\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz5.h, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz6.h, p[0-7], \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1w\tz10.s, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz11.s, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8si 1 z10\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz12.d, z10.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz13.d, z11.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8si 2 z10, z10, z12\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz10.s, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz11.s, p[0-7], \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1d\tz15.d, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz16.d, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx4di 1 z15\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z15.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz18.d, z16.d\n} } } */
+/* { dg-final { scan-assembler { test vnx4di 2 z15, z15, z17\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz15.d, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz16.d, p[0-7], \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1h\tz18.h, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz19.h, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16hf 1 z18\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz20.d, z18.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz21.d, z19.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16hf 2 z18, z18, z20\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz18.h, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz19.h, p[0-7], \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1w\tz21.s, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz22.s, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8sf 1 z21\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz23.d, z21.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz24.d, z22.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8sf 2 z21, z21, z23\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz21.s, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz22.s, p[0-7], \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1d\tz28.d, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz29.d, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx4df 1 z28\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz30.d, z28.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz31.d, z29.d\n} } } */
+/* { dg-final { scan-assembler { test vnx4df 2 z28, z28, z30\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz28.d, p[0-7], \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz29.d, p[0-7], \[x0, #3, mul vl\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O -msve-vector-bits=256 -mbig-endian --save-temps" } */
+
+typedef char vnx16qi __attribute__((vector_size(32)));
+typedef struct { vnx16qi a[3]; } vnx48qi;
+
+typedef short vnx8hi __attribute__((vector_size(32)));
+typedef struct { vnx8hi a[3]; } vnx24hi;
+
+typedef int vnx4si __attribute__((vector_size(32)));
+typedef struct { vnx4si a[3]; } vnx12si;
+
+typedef long vnx2di __attribute__((vector_size(32)));
+typedef struct { vnx2di a[3]; } vnx6di;
+
+typedef _Float16 vnx8hf __attribute__((vector_size(32)));
+typedef struct { vnx8hf a[3]; } vnx24hf;
+
+typedef float vnx4sf __attribute__((vector_size(32)));
+typedef struct { vnx4sf a[3]; } vnx12sf;
+
+typedef double vnx2df __attribute__((vector_size(32)));
+typedef struct { vnx2df a[3]; } vnx6df;
+
+#define TEST_TYPE(TYPE, REG1, REG2) \
+ void \
+ f_##TYPE (TYPE *a) \
+ { \
+ register TYPE x asm (#REG1) = a[0]; \
+ asm volatile ("# test " #TYPE " 1 %S0" :: "w" (x)); \
+ register TYPE y asm (#REG2) = x; \
+ asm volatile ("# test " #TYPE " 2 %S0, %S1, %S2" \
+ : "=&w" (x) : "0" (x), "w" (y)); \
+ a[1] = x; \
+ }
+
+TEST_TYPE (vnx48qi, z0, z3)
+TEST_TYPE (vnx24hi, z6, z2)
+TEST_TYPE (vnx12si, z12, z15)
+TEST_TYPE (vnx6di, z16, z13)
+TEST_TYPE (vnx24hf, z18, z1)
+TEST_TYPE (vnx12sf, z20, z23)
+TEST_TYPE (vnx6df, z26, z29)
+
+/* { dg-final { scan-assembler {\tld1b\tz0.b, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1b\tz1.b, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1b\tz2.b, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx48qi 1 z0\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z0.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z1.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz5.d, z2.d\n} } } */
+/* { dg-final { scan-assembler { test vnx48qi 2 z0, z0, z3\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz0.b, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz1.b, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz2.b, p[0-7], \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1h\tz6.h, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz7.h, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz8.h, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx24hi 1 z6\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z6.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z7.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z8.d\n} } } */
+/* { dg-final { scan-assembler { test vnx24hi 2 z6, z6, z2\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz6.h, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz7.h, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz8.h, p[0-7], \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1w\tz12.s, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz13.s, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz14.s, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx12si 1 z12\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz15.d, z12.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z13.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z14.d\n} } } */
+/* { dg-final { scan-assembler { test vnx12si 2 z12, z12, z15\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz12.s, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz13.s, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz14.s, p[0-7], \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1d\tz16.d, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz17.d, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz18.d, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx6di 1 z16\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz13.d, z16.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz14.d, z17.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz15.d, z18.d\n} } } */
+/* { dg-final { scan-assembler { test vnx6di 2 z16, z16, z13\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz16.d, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz17.d, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz18.d, p[0-7], \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1h\tz18.h, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz19.h, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz20.h, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx24hf 1 z18\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz1.d, z18.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z19.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z20.d\n} } } */
+/* { dg-final { scan-assembler { test vnx24hf 2 z18, z18, z1\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz18.h, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz19.h, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz20.h, p[0-7], \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1w\tz20.s, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz21.s, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz22.s, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx12sf 1 z20\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz23.d, z20.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz24.d, z21.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz25.d, z22.d\n} } } */
+/* { dg-final { scan-assembler { test vnx12sf 2 z20, z20, z23\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz20.s, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz21.s, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz22.s, p[0-7], \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1d\tz26.d, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz27.d, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz28.d, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx6df 1 z26\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz29.d, z26.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz30.d, z27.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz31.d, z28.d\n} } } */
+/* { dg-final { scan-assembler { test vnx6df 2 z26, z26, z29\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz26.d, p[0-7], \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz27.d, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz28.d, p[0-7], \[x0, #5, mul vl\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O -msve-vector-bits=256 -mbig-endian --save-temps" } */
+
+typedef char vnx16qi __attribute__((vector_size(32)));
+typedef struct { vnx16qi a[4]; } vnx64qi;
+
+typedef short vnx8hi __attribute__((vector_size(32)));
+typedef struct { vnx8hi a[4]; } vnx32hi;
+
+typedef int vnx4si __attribute__((vector_size(32)));
+typedef struct { vnx4si a[4]; } vnx16si;
+
+typedef long vnx2di __attribute__((vector_size(32)));
+typedef struct { vnx2di a[4]; } vnx8di;
+
+typedef _Float16 vnx8hf __attribute__((vector_size(32)));
+typedef struct { vnx8hf a[4]; } vnx32hf;
+
+typedef float vnx4sf __attribute__((vector_size(32)));
+typedef struct { vnx4sf a[4]; } vnx16sf;
+
+typedef double vnx2df __attribute__((vector_size(32)));
+typedef struct { vnx2df a[4]; } vnx8df;
+
+#define TEST_TYPE(TYPE, REG1, REG2) \
+ void \
+ f_##TYPE (TYPE *a) \
+ { \
+ register TYPE x asm (#REG1) = a[0]; \
+ asm volatile ("# test " #TYPE " 1 %S0" :: "w" (x)); \
+ register TYPE y asm (#REG2) = x; \
+ asm volatile ("# test " #TYPE " 2 %S0, %S1, %S2" \
+ : "=&w" (x) : "0" (x), "w" (y)); \
+ a[1] = x; \
+ }
+
+TEST_TYPE (vnx64qi, z0, z4)
+TEST_TYPE (vnx32hi, z6, z2)
+TEST_TYPE (vnx16si, z12, z16)
+TEST_TYPE (vnx8di, z17, z13)
+TEST_TYPE (vnx32hf, z18, z1)
+TEST_TYPE (vnx16sf, z20, z16)
+TEST_TYPE (vnx8df, z24, z28)
+
+/* { dg-final { scan-assembler {\tld1b\tz0.b, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1b\tz1.b, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1b\tz2.b, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1b\tz3.b, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx64qi 1 z0\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z0.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz5.d, z1.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz6.d, z2.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz7.d, z3.d\n} } } */
+/* { dg-final { scan-assembler { test vnx64qi 2 z0, z0, z4\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz0.b, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz1.b, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz2.b, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1b\tz3.b, p[0-7], \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1h\tz6.h, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz7.h, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz8.h, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz9.h, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx32hi 1 z6\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z6.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z7.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z8.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz5.d, z9.d\n} } } */
+/* { dg-final { scan-assembler { test vnx32hi 2 z6, z6, z2\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz6.h, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz7.h, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz8.h, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz9.h, p[0-7], \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1w\tz12.s, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz13.s, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz14.s, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz15.s, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16si 1 z12\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z12.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z13.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz18.d, z14.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz19.d, z15.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16si 2 z12, z12, z16\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz12.s, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz13.s, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz14.s, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz15.s, p[0-7], \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1d\tz17.d, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz18.d, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz19.d, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz20.d, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8di 1 z17\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz13.d, z17.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz14.d, z18.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz15.d, z19.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z20.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8di 2 z17, z17, z13\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz17.d, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz18.d, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz19.d, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz20.d, p[0-7], \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1h\tz18.h, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz19.h, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz20.h, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1h\tz21.h, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx32hf 1 z18\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz1.d, z18.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z19.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z20.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z21.d\n} } } */
+/* { dg-final { scan-assembler { test vnx32hf 2 z18, z18, z1\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz18.h, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz19.h, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz20.h, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1h\tz21.h, p[0-7], \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1w\tz20.s, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz21.s, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz22.s, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1w\tz23.s, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16sf 1 z20\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z20.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z21.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz18.d, z22.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz19.d, z23.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16sf 2 z20, z20, z16\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz20.s, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz21.s, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz22.s, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1w\tz23.s, p[0-7], \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tld1d\tz24.d, p[0-7]/z, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz25.d, p[0-7]/z, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz26.d, p[0-7]/z, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tld1d\tz27.d, p[0-7]/z, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8df 1 z24\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz28.d, z24.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz29.d, z25.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz30.d, z26.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz31.d, z27.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8df 2 z24, z24, z28\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz24.d, p[0-7], \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz25.d, p[0-7], \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz26.d, p[0-7], \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tst1d\tz27.d, p[0-7], \[x0, #7, mul vl\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O -msve-vector-bits=256 -mlittle-endian --save-temps" } */
+
+typedef char vnx16qi __attribute__((vector_size(32)));
+typedef struct { vnx16qi a[2]; } vnx32qi;
+
+typedef short vnx8hi __attribute__((vector_size(32)));
+typedef struct { vnx8hi a[2]; } vnx16hi;
+
+typedef int vnx4si __attribute__((vector_size(32)));
+typedef struct { vnx4si a[2]; } vnx8si;
+
+typedef long vnx2di __attribute__((vector_size(32)));
+typedef struct { vnx2di a[2]; } vnx4di;
+
+typedef float vnx4sf __attribute__((vector_size(32)));
+typedef struct { vnx4sf a[2]; } vnx8sf;
+
+typedef double vnx2df __attribute__((vector_size(32)));
+typedef struct { vnx2df a[2]; } vnx4df;
+
+#define TEST_TYPE(TYPE, REG1, REG2) \
+ void \
+ f1_##TYPE (TYPE *a) \
+ { \
+ register TYPE x asm (#REG1) = a[0]; \
+ asm volatile ("# test " #TYPE " 1 %S0" :: "w" (x)); \
+ register TYPE y asm (#REG2) = x; \
+ asm volatile ("# test " #TYPE " 2 %S0, %S1, %S2" \
+ : "=&w" (x) : "0" (x), "w" (y)); \
+ a[1] = x; \
+ } \
+ /* This must compile, but we don't care how. */ \
+ void \
+ f2_##TYPE (TYPE *a) \
+ { \
+ TYPE x = a[0]; \
+ x.a[0][3] = 1; \
+ x.a[1][2] = 12; \
+ asm volatile ("# %0" :: "w" (x)); \
+ } \
+ void \
+ f3_##TYPE (TYPE *a, int i) \
+ { \
+ TYPE x = a[0]; \
+ x.a[0][i] = 1; \
+ asm volatile ("# %0" :: "w" (x)); \
+ } \
+ void \
+ f4_##TYPE (TYPE *a, int i, int j) \
+ { \
+ TYPE x = a[0]; \
+ x.a[i][j] = 44; \
+ asm volatile ("# %0" :: "w" (x)); \
+ }
+
+TEST_TYPE (vnx32qi, z0, z2)
+TEST_TYPE (vnx16hi, z5, z7)
+TEST_TYPE (vnx8si, z10, z12)
+TEST_TYPE (vnx4di, z15, z17)
+TEST_TYPE (vnx8sf, z20, z23)
+TEST_TYPE (vnx4df, z28, z30)
+
+/* { dg-final { scan-assembler {\tldr\tz0, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz1, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx32qi 1 z0\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z0.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z1.d\n} } } */
+/* { dg-final { scan-assembler { test vnx32qi 2 z0, z0, z2\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz0, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz1, \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz5, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz6, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16hi 1 z5\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz7.d, z5.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz8.d, z6.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16hi 2 z5, z5, z7\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz5, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz6, \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz10, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz11, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8si 1 z10\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz12.d, z10.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz13.d, z11.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8si 2 z10, z10, z12\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz10, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz11, \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz15, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz16, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx4di 1 z15\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z15.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz18.d, z16.d\n} } } */
+/* { dg-final { scan-assembler { test vnx4di 2 z15, z15, z17\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz15, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz16, \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz20, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz21, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8sf 1 z20\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz23.d, z20.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz24.d, z21.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8sf 2 z20, z20, z23\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz20, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz21, \[x0, #3, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz28, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz29, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx4df 1 z28\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz30.d, z28.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz31.d, z29.d\n} } } */
+/* { dg-final { scan-assembler { test vnx4df 2 z28, z28, z30\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz28, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz29, \[x0, #3, mul vl\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O -msve-vector-bits=256 -mlittle-endian --save-temps" } */
+
+typedef char vnx16qi __attribute__((vector_size(32)));
+typedef struct { vnx16qi a[3]; } vnx48qi;
+
+typedef short vnx8hi __attribute__((vector_size(32)));
+typedef struct { vnx8hi a[3]; } vnx24hi;
+
+typedef int vnx4si __attribute__((vector_size(32)));
+typedef struct { vnx4si a[3]; } vnx12si;
+
+typedef long vnx2di __attribute__((vector_size(32)));
+typedef struct { vnx2di a[3]; } vnx6di;
+
+typedef float vnx4sf __attribute__((vector_size(32)));
+typedef struct { vnx4sf a[3]; } vnx12sf;
+
+typedef double vnx2df __attribute__((vector_size(32)));
+typedef struct { vnx2df a[3]; } vnx6df;
+
+#define TEST_TYPE(TYPE, REG1, REG2) \
+ void \
+ f_##TYPE (TYPE *a) \
+ { \
+ register TYPE x asm (#REG1) = a[0]; \
+ asm volatile ("# test " #TYPE " 1 %S0" :: "w" (x)); \
+ register TYPE y asm (#REG2) = x; \
+ asm volatile ("# test " #TYPE " 2 %S0, %S1, %S2" \
+ : "=&w" (x) : "0" (x), "w" (y)); \
+ a[1] = x; \
+ }
+
+TEST_TYPE (vnx48qi, z0, z3)
+TEST_TYPE (vnx24hi, z6, z2)
+TEST_TYPE (vnx12si, z12, z15)
+TEST_TYPE (vnx6di, z16, z13)
+TEST_TYPE (vnx12sf, z20, z23)
+TEST_TYPE (vnx6df, z26, z29)
+
+/* { dg-final { scan-assembler {\tldr\tz0, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz1, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz2, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx48qi 1 z0\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z0.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z1.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz5.d, z2.d\n} } } */
+/* { dg-final { scan-assembler { test vnx48qi 2 z0, z0, z3\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz0, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz1, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz2, \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz6, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz7, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz8, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx24hi 1 z6\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z6.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z7.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z8.d\n} } } */
+/* { dg-final { scan-assembler { test vnx24hi 2 z6, z6, z2\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz6, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz7, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz8, \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz12, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz13, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz14, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx12si 1 z12\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz15.d, z12.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z13.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z14.d\n} } } */
+/* { dg-final { scan-assembler { test vnx12si 2 z12, z12, z15\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz12, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz13, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz14, \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz16, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz17, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz18, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx6di 1 z16\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz13.d, z16.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz14.d, z17.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz15.d, z18.d\n} } } */
+/* { dg-final { scan-assembler { test vnx6di 2 z16, z16, z13\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz16, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz17, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz18, \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz20, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz21, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz22, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx12sf 1 z20\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz23.d, z20.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz24.d, z21.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz25.d, z22.d\n} } } */
+/* { dg-final { scan-assembler { test vnx12sf 2 z20, z20, z23\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz20, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz21, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz22, \[x0, #5, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz26, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz27, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz28, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx6df 1 z26\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz29.d, z26.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz30.d, z27.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz31.d, z28.d\n} } } */
+/* { dg-final { scan-assembler { test vnx6df 2 z26, z26, z29\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz26, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz27, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz28, \[x0, #5, mul vl\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O -msve-vector-bits=256 -mlittle-endian --save-temps" } */
+
+typedef char vnx16qi __attribute__((vector_size(32)));
+typedef struct { vnx16qi a[4]; } vnx64qi;
+
+typedef short vnx8hi __attribute__((vector_size(32)));
+typedef struct { vnx8hi a[4]; } vnx32hi;
+
+typedef int vnx4si __attribute__((vector_size(32)));
+typedef struct { vnx4si a[4]; } vnx16si;
+
+typedef long vnx2di __attribute__((vector_size(32)));
+typedef struct { vnx2di a[4]; } vnx8di;
+
+typedef float vnx4sf __attribute__((vector_size(32)));
+typedef struct { vnx4sf a[4]; } vnx16sf;
+
+typedef double vnx2df __attribute__((vector_size(32)));
+typedef struct { vnx2df a[4]; } vnx8df;
+
+#define TEST_TYPE(TYPE, REG1, REG2) \
+ void \
+ f_##TYPE (TYPE *a) \
+ { \
+ register TYPE x asm (#REG1) = a[0]; \
+ asm volatile ("# test " #TYPE " 1 %S0" :: "w" (x)); \
+ register TYPE y asm (#REG2) = x; \
+ asm volatile ("# test " #TYPE " 2 %S0, %S1, %S2" \
+ : "=&w" (x) : "0" (x), "w" (y)); \
+ a[1] = x; \
+ }
+
+TEST_TYPE (vnx64qi, z0, z4)
+TEST_TYPE (vnx32hi, z6, z2)
+TEST_TYPE (vnx16si, z12, z16)
+TEST_TYPE (vnx8di, z17, z13)
+TEST_TYPE (vnx16sf, z20, z16)
+TEST_TYPE (vnx8df, z24, z28)
+
+/* { dg-final { scan-assembler {\tldr\tz0, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz1, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz2, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz3, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx64qi 1 z0\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z0.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz5.d, z1.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz6.d, z2.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz7.d, z3.d\n} } } */
+/* { dg-final { scan-assembler { test vnx64qi 2 z0, z0, z4\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz0, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz1, \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz2, \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz3, \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz6, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz7, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz8, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz9, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx32hi 1 z6\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz2.d, z6.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz3.d, z7.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz4.d, z8.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz5.d, z9.d\n} } } */
+/* { dg-final { scan-assembler { test vnx32hi 2 z6, z6, z2\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz6, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz7, \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz8, \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz9, \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz12, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz13, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz14, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz15, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16si 1 z12\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z12.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z13.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz18.d, z14.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz19.d, z15.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16si 2 z12, z12, z16\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz12, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz13, \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz14, \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz15, \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz17, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz18, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz19, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz20, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8di 1 z17\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz13.d, z17.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz14.d, z18.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz15.d, z19.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z20.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8di 2 z17, z17, z13\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz17, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz18, \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz19, \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz20, \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz20, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz21, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz22, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz23, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx16sf 1 z20\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz16.d, z20.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz17.d, z21.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz18.d, z22.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz19.d, z23.d\n} } } */
+/* { dg-final { scan-assembler { test vnx16sf 2 z20, z20, z16\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz20, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz21, \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz22, \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz23, \[x0, #7, mul vl\]\n} } } */
+
+/* { dg-final { scan-assembler {\tldr\tz24, \[x0\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz25, \[x0, #1, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz26, \[x0, #2, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tldr\tz27, \[x0, #3, mul vl\]\n} } } */
+/* { dg-final { scan-assembler { test vnx8df 1 z24\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz28.d, z24.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz29.d, z25.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz30.d, z26.d\n} } } */
+/* { dg-final { scan-assembler {\tmov\tz31.d, z27.d\n} } } */
+/* { dg-final { scan-assembler { test vnx8df 2 z24, z24, z28\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz24, \[x0, #4, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz25, \[x0, #5, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz26, \[x0, #6, mul vl\]\n} } } */
+/* { dg-final { scan-assembler {\tstr\tz27, \[x0, #7, mul vl\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#ifndef TYPE
+#define TYPE unsigned char
+#endif
+
+#ifndef NAME
+#define NAME(X) X
+#endif
+
+#define N 1024
+
+void __attribute__ ((noinline, noclone))
+NAME(f2) (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c)
+{
+ for (int i = 0; i < N; ++i)
+ {
+ a[i] = c[i * 2];
+ b[i] = c[i * 2 + 1];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+NAME(f3) (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d)
+{
+ for (int i = 0; i < N; ++i)
+ {
+ a[i] = d[i * 3];
+ b[i] = d[i * 3 + 1];
+ c[i] = d[i * 3 + 2];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+NAME(f4) (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d, TYPE *__restrict e)
+{
+ for (int i = 0; i < N; ++i)
+ {
+ a[i] = e[i * 4];
+ b[i] = e[i * 4 + 1];
+ c[i] = e[i * 4 + 2];
+ d[i] = e[i * 4 + 3];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+NAME(g2) (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c)
+{
+ for (int i = 0; i < N; ++i)
+ {
+ c[i * 2] = a[i];
+ c[i * 2 + 1] = b[i];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+NAME(g3) (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d)
+{
+ for (int i = 0; i < N; ++i)
+ {
+ d[i * 3] = a[i];
+ d[i * 3 + 1] = b[i];
+ d[i * 3 + 2] = c[i];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+NAME(g4) (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d, TYPE *__restrict e)
+{
+ for (int i = 0; i < N; ++i)
+ {
+ e[i * 4] = a[i];
+ e[i * 4 + 1] = b[i];
+ e[i * 4 + 2] = c[i];
+ e[i * 4 + 3] = d[i];
+ }
+}
+
+/* { dg-final { scan-assembler {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned long
+#define ITYPE long
+#include "struct_vect_7.c"
+
+/* { dg-final { scan-assembler {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned long
+#define ITYPE long
+#include "struct_vect_7_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE _Float16
+#define ITYPE short
+#include "struct_vect_7.c"
+
+/* { dg-final { scan-assembler {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE _Float16
+#define ITYPE short
+#include "struct_vect_7_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE float
+#define ITYPE int
+#include "struct_vect_7.c"
+
+/* { dg-final { scan-assembler {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE float
+#define ITYPE int
+#include "struct_vect_7_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE double
+#define ITYPE long
+#include "struct_vect_7.c"
+
+/* { dg-final { scan-assembler {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE double
+#define ITYPE long
+#include "struct_vect_7_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=256 --save-temps" } */
+
+#define TYPE unsigned char
+#define NAME(X) qi_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+#define TYPE unsigned short
+#define NAME(X) hi_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+#define TYPE unsigned int
+#define NAME(X) si_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+#define TYPE unsigned long
+#define NAME(X) di_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+#define TYPE _Float16
+#define NAME(X) hf_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+#define TYPE float
+#define NAME(X) sf_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+#define TYPE double
+#define NAME(X) df_##X
+#include "struct_vect_1.c"
+#undef NAME
+#undef TYPE
+
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=512 --save-temps" } */
+
+#include "struct_vect_14.c"
+
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=1024 --save-temps" } */
+
+#include "struct_vect_14.c"
+
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize -msve-vector-bits=2048 --save-temps" } */
+
+#include "struct_vect_14.c"
+
+/* { dg-final { scan-assembler-times {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+/* { dg-final { scan-assembler-times {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} 1 } } */
+
+/* { dg-final { scan-assembler-times {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+
+/* { dg-final { scan-assembler-times {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
+/* { dg-final { scan-assembler-times {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} 2 } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#include "struct_vect_1.c"
+
+TYPE a[N], b[N], c[N], d[N], e[N * 4];
+
+void __attribute__ ((noinline, noclone))
+init_array (TYPE *array, int n, TYPE base, TYPE step)
+{
+ for (int i = 0; i < n; ++i)
+ array[i] = base + step * i;
+}
+
+void __attribute__ ((noinline, noclone))
+check_array (TYPE *array, int n, TYPE base, TYPE step)
+{
+ for (int i = 0; i < n; ++i)
+ if (array[i] != (TYPE) (base + step * i))
+ __builtin_abort ();
+}
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ init_array (e, 2 * N, 11, 5);
+ f2 (a, b, e);
+ check_array (a, N, 11, 10);
+ check_array (b, N, 16, 10);
+
+ init_array (e, 3 * N, 7, 6);
+ f3 (a, b, c, e);
+ check_array (a, N, 7, 18);
+ check_array (b, N, 13, 18);
+ check_array (c, N, 19, 18);
+
+ init_array (e, 4 * N, 4, 11);
+ f4 (a, b, c, d, e);
+ check_array (a, N, 4, 44);
+ check_array (b, N, 15, 44);
+ check_array (c, N, 26, 44);
+ check_array (d, N, 37, 44);
+
+ init_array (a, N, 2, 8);
+ init_array (b, N, 6, 8);
+ g2 (a, b, e);
+ check_array (e, 2 * N, 2, 4);
+
+ init_array (a, N, 4, 15);
+ init_array (b, N, 9, 15);
+ init_array (c, N, 14, 15);
+ g3 (a, b, c, e);
+ check_array (e, 3 * N, 4, 5);
+
+ init_array (a, N, 14, 36);
+ init_array (b, N, 23, 36);
+ init_array (c, N, 32, 36);
+ init_array (d, N, 41, 36);
+ g4 (a, b, c, d, e);
+ check_array (e, 4 * N, 14, 9);
+
+ return 0;
+}
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned short
+#include "struct_vect_1.c"
+
+/* { dg-final { scan-assembler {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned short
+#include "struct_vect_1_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned int
+#include "struct_vect_1.c"
+
+/* { dg-final { scan-assembler {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned int
+#include "struct_vect_1_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned long
+#include "struct_vect_1.c"
+
+/* { dg-final { scan-assembler {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned long
+#include "struct_vect_1_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE float
+#include "struct_vect_1.c"
+
+/* { dg-final { scan-assembler {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE float
+#include "struct_vect_1_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE double
+#include "struct_vect_1.c"
+
+/* { dg-final { scan-assembler {\tld2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4d\t{z[0-9]+.d - z[0-9]+.d}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE double
+#include "struct_vect_1_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#ifndef TYPE
+#define TYPE unsigned char
+#define ITYPE signed char
+#endif
+
+void __attribute__ ((noinline, noclone))
+f2 (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c, ITYPE n)
+{
+ for (ITYPE i = 0; i < n; ++i)
+ {
+ a[i] = c[i * 2];
+ b[i] = c[i * 2 + 1];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+f3 (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d, ITYPE n)
+{
+ for (ITYPE i = 0; i < n; ++i)
+ {
+ a[i] = d[i * 3];
+ b[i] = d[i * 3 + 1];
+ c[i] = d[i * 3 + 2];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+f4 (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d, TYPE *__restrict e, ITYPE n)
+{
+ for (ITYPE i = 0; i < n; ++i)
+ {
+ a[i] = e[i * 4];
+ b[i] = e[i * 4 + 1];
+ c[i] = e[i * 4 + 2];
+ d[i] = e[i * 4 + 3];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+g2 (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c, ITYPE n)
+{
+ for (ITYPE i = 0; i < n; ++i)
+ {
+ c[i * 2] = a[i];
+ c[i * 2 + 1] = b[i];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+g3 (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d, ITYPE n)
+{
+ for (ITYPE i = 0; i < n; ++i)
+ {
+ d[i * 3] = a[i];
+ d[i * 3 + 1] = b[i];
+ d[i * 3 + 2] = c[i];
+ }
+}
+
+void __attribute__ ((noinline, noclone))
+g4 (TYPE *__restrict a, TYPE *__restrict b, TYPE *__restrict c,
+ TYPE *__restrict d, TYPE *__restrict e, ITYPE n)
+{
+ for (ITYPE i = 0; i < n; ++i)
+ {
+ e[i * 4] = a[i];
+ e[i * 4 + 1] = b[i];
+ e[i * 4 + 2] = c[i];
+ e[i * 4 + 3] = d[i];
+ }
+}
+
+/* { dg-final { scan-assembler {\tld2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4b\t{z[0-9]+.b - z[0-9]+.b}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#include "struct_vect_7.c"
+
+#define N 93
+
+TYPE a[N], b[N], c[N], d[N], e[N * 4];
+
+void __attribute__ ((noinline, noclone))
+init_array (TYPE *array, int n, TYPE base, TYPE step)
+{
+ for (int i = 0; i < n; ++i)
+ array[i] = base + step * i;
+}
+
+void __attribute__ ((noinline, noclone))
+check_array (TYPE *array, int n, TYPE base, TYPE step)
+{
+ for (int i = 0; i < n; ++i)
+ if (array[i] != (TYPE) (base + step * i))
+ __builtin_abort ();
+}
+
+int __attribute__ ((optimize (1)))
+main (void)
+{
+ init_array (e, 2 * N, 11, 5);
+ f2 (a, b, e, N);
+ check_array (a, N, 11, 10);
+ check_array (b, N, 16, 10);
+
+ init_array (e, 3 * N, 7, 6);
+ f3 (a, b, c, e, N);
+ check_array (a, N, 7, 18);
+ check_array (b, N, 13, 18);
+ check_array (c, N, 19, 18);
+
+ init_array (e, 4 * N, 4, 11);
+ f4 (a, b, c, d, e, N);
+ check_array (a, N, 4, 44);
+ check_array (b, N, 15, 44);
+ check_array (c, N, 26, 44);
+ check_array (d, N, 37, 44);
+
+ init_array (a, N, 2, 8);
+ init_array (b, N, 6, 8);
+ g2 (a, b, e, N);
+ check_array (e, 2 * N, 2, 4);
+
+ init_array (a, N, 4, 15);
+ init_array (b, N, 9, 15);
+ init_array (c, N, 14, 15);
+ g3 (a, b, c, e, N);
+ check_array (e, 3 * N, 4, 5);
+
+ init_array (a, N, 14, 36);
+ init_array (b, N, 23, 36);
+ init_array (c, N, 32, 36);
+ init_array (d, N, 41, 36);
+ g4 (a, b, c, d, e, N);
+ check_array (e, 4 * N, 14, 9);
+
+ return 0;
+}
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned short
+#define ITYPE short
+#include "struct_vect_7.c"
+
+/* { dg-final { scan-assembler {\tld2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4h\t{z[0-9]+.h - z[0-9]+.h}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned short
+#define ITYPE short
+#include "struct_vect_7_run.c"
--- /dev/null
+/* { dg-do assemble { target aarch64_asm_sve_ok } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned int
+#define ITYPE int
+#include "struct_vect_7.c"
+
+/* { dg-final { scan-assembler {\tld2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tld4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7]/z, \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst2w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst3w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
+/* { dg-final { scan-assembler {\tst4w\t{z[0-9]+.s - z[0-9]+.s}, p[0-7], \[x[0-9]+\]\n} } } */
--- /dev/null
+/* { dg-do run { target aarch64_sve_hw } } */
+/* { dg-options "-O2 -ftree-vectorize --save-temps" } */
+
+#define TYPE unsigned int
+#define ITYPE int
+#include "struct_vect_7_run.c"
projects / gcc.git / commitdiff