RISC-V: Use tu policy for first-element vec_set [PR115725].

This patch changes the tail policy for vmv.s.x from ta to tu.
By default the bug does not show up with qemu because qemu's
current vmv.s.x implementation always uses the tail-undisturbed
policy.  With a local qemu version that overwrites the tail
with ones when the tail-agnostic policy is specified, the bug
shows.

gcc/ChangeLog:

	* config/riscv/autovec.md: Add TU policy.
	* config/riscv/riscv-protos.h (enum insn_type): Define
	SCALAR_MOVE_MERGED_OP_TU.

gcc/testsuite/ChangeLog:

	PR target/115725

	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c: Adjust
	test expectation.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c: Ditto.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c: Ditto.
	* gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c: Ditto.

6 files changed, 22 insertions, 33 deletions

diff --git a/gcc/config/riscv/autovec.md b/gcc/config/riscv/autovec.md
index 66d70f6..0fb6316 100644
--- a/gcc/config/riscv/autovec.md
+++ b/gcc/config/riscv/autovec.md
@@ -1341,7 +1341,8 @@
     {
       rtx ops[] = {operands[0], operands[0], operands[1]};
       riscv_vector::emit_nonvlmax_insn (code_for_pred_broadcast (<MODE>mode),
-					riscv_vector::SCALAR_MOVE_MERGED_OP, ops, CONST1_RTX (Pmode));
+					riscv_vector::SCALAR_MOVE_MERGED_OP_TU,
+					ops, CONST1_RTX (Pmode));
     }
   else
     {
diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index a8b7617..abf6e34 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -524,6 +524,10 @@ enum insn_type : unsigned int
   SCALAR_MOVE_MERGED_OP = HAS_DEST_P | HAS_MASK_P | USE_ONE_TRUE_MASK_P
 			  | HAS_MERGE_P | TDEFAULT_POLICY_P | MDEFAULT_POLICY_P
 			  | UNARY_OP_P,
+
+  SCALAR_MOVE_MERGED_OP_TU = HAS_DEST_P | HAS_MASK_P | USE_ONE_TRUE_MASK_P
+			  | HAS_MERGE_P | TU_POLICY_P | MDEFAULT_POLICY_P
+			  | UNARY_OP_P,
 };
 
 enum vlmul_type
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c
index ecb1609..99b0f62 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-1.c
@@ -64,14 +64,10 @@ typedef double vnx2df __attribute__((vector_size (16)));
 TEST_ALL1 (VEC_SET)
 TEST_ALL_VAR1 (VEC_SET_VAR1)
 
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m1,\s*ta,\s*ma} 1 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m1,\s*tu,\s*ma} 5 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m1,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m1,\s*tu,\s*ma} 6 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m1,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m1,\s*tu,\s*ma} 6 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m1,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m1,\s*tu,\s*ma} 4 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m1,\s*tu,\s*ma} 6 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m1,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m1,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m1,\s*tu,\s*ma} 6 } } */
 
 /* { dg-final { scan-assembler-times {\tvmv.v.x} 13 } } */
 /* { dg-final { scan-assembler-times {\tvfmv.v.f} 8 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c
index 194abff..64a4030 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-2.c
@@ -76,14 +76,10 @@ typedef double vnx4df __attribute__((vector_size (32)));
 TEST_ALL2 (VEC_SET)
 TEST_ALL_VAR2 (VEC_SET_VAR2)
 
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m2,\s*ta,\s*ma} 1 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m2,\s*tu,\s*ma} 5 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m2,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m2,\s*tu,\s*ma} 10 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m2,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m2,\s*tu,\s*ma} 10 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m2,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m2,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m2,\s*tu,\s*ma} 6 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m2,\s*tu,\s*ma} 12 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m2,\s*tu,\s*ma} 12 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m2,\s*tu,\s*ma} 10 } } */
 
 /* { dg-final { scan-assembler-times {\tvmv.v.x} 19 } } */
 /* { dg-final { scan-assembler-times {\tvfmv.v.f} 14 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c
index 9495d51..ce029b3 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-3.c
@@ -77,14 +77,10 @@ typedef double vnx8df __attribute__((vector_size (64)));
 TEST_ALL3 (VEC_SET)
 TEST_ALL_VAR3 (VEC_SET_VAR3)
 
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m4,\s*ta,\s*ma} 1 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m4,\s*tu,\s*ma} 5 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m4,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m4,\s*tu,\s*ma} 11 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m4,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m4,\s*tu,\s*ma} 10 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m4,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m4,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m4,\s*tu,\s*ma} 6 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m4,\s*tu,\s*ma} 13 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m4,\s*tu,\s*ma} 12 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m4,\s*tu,\s*ma} 10 } } */
 
 /* { dg-final { scan-assembler-times {\tvmv.v.x} 19 } } */
 /* { dg-final { scan-assembler-times {\tvfmv.v.f} 15 } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c
index 9992bc24..309256d 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls-vlmax/vec_set-4.c
@@ -80,14 +80,10 @@ typedef double vnx16df __attribute__((vector_size (128)));
 TEST_ALL4 (VEC_SET)
 TEST_ALL_VAR4 (VEC_SET_VAR4)
 
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m8,\s*ta,\s*ma} 1 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m8,\s*tu,\s*ma} 6 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m8,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m8,\s*tu,\s*ma} 13 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m8,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m8,\s*tu,\s*ma} 10 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m8,\s*ta,\s*ma} 2 } } */
-/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m8,\s*tu,\s*ma} 8 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e8,\s*m8,\s*tu,\s*ma} 7 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e16,\s*m8,\s*tu,\s*ma} 15 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e32,\s*m8,\s*tu,\s*ma} 12 } } */
+/* { dg-final { scan-assembler-times {vset[i]*vli\s+[a-z0-9,]+,\s*e64,\s*m8,\s*tu,\s*ma} 10 } } */
 
 /* { dg-final { scan-assembler-times {\tvmv.v.x} 20 } } */
 /* { dg-final { scan-assembler-times {\tvfmv.v.f} 17 } } */