[PATCH v1] RTL: Bugfix ICE after allow vector type in DSE

[pan2.li@intel.com]

From: Pan Li <pan2.li@intel.com>

We allowed vector type for get_stored_val when read is less than or
equal to store in previous.  Unfortunately, we missed to adjust the
validate_subreg part accordingly.  For vector type, we don't need to
restrict the mode size is greater than the vector register size.

Thus, for example when gen_lowpart from E_V2SFmode to E_V4QImode, it
will have NULL_RTX(of course ICE after that) because of the mode size
is less than vector register size.  That also explain that gen_lowpart
from E_V8SFmode to E_V16QImode is valid here.

This patch would like to remove the the restriction for vector mode, to
rid of the ICE when gen_lowpart because of validate_subreg fails.

The below test are passed for this patch:

* The X86 bootstrap test.
* The fully riscv regression tests.

gcc/ChangeLog:

	* emit-rtl.cc (validate_subreg): Bypass register size check
	if the mode is vector.

gcc/testsuite/ChangeLog:

	* gcc.dg/tree-ssa/ssa-fre-44.c: Add ftree-vectorize to trigger
	the ICE.
	* gcc.target/riscv/rvv/base/bug-6.c: New test.

Signed-off-by: Pan Li <pan2.li@intel.com>
---
 gcc/emit-rtl.cc                               |  3 ++-
 gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-44.c    |  2 +-
 .../gcc.target/riscv/rvv/base/bug-6.c         | 22 +++++++++++++++++++
 3 files changed, 25 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/bug-6.c

diff --git a/gcc/emit-rtl.cc b/gcc/emit-rtl.cc
index 1856fa4884f..45c6301b487 100644
--- a/gcc/emit-rtl.cc
+++ b/gcc/emit-rtl.cc
@@ -934,7 +934,8 @@ validate_subreg (machine_mode omode, machine_mode imode,
     ;
   /* ??? Similarly, e.g. with (subreg:DF (reg:TI)).  Though store_bit_field
      is the culprit here, and not the backends.  */
-  else if (known_ge (osize, regsize) && known_ge (isize, osize))
+  else if (known_ge (isize, osize) && (known_ge (osize, regsize)
+    || (VECTOR_MODE_P (imode) || VECTOR_MODE_P (omode))))
     ;
   /* Allow component subregs of complex and vector.  Though given the below
      extraction rules, it's not always clear what that means.  */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-44.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-44.c
index f79b4c142ae..624a00a4f32 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-44.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-44.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O -fdump-tree-fre1" } */
+/* { dg-options "-O -fdump-tree-fre1 -O3 -ftree-vectorize" } */
 
 struct A { float x, y; };
 struct B { struct A u; };
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/bug-6.c b/gcc/testsuite/gcc.target/riscv/rvv/base/bug-6.c
new file mode 100644
index 00000000000..5bb00b8f587
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/bug-6.c
@@ -0,0 +1,22 @@
+/* Test that we do not have ice when compile */
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize" } */
+
+struct A { float x, y; };
+struct B { struct A u; };
+
+extern void bar (struct A *);
+
+float
+f3 (struct B *x, int y)
+{
+  struct A p = {1.0f, 2.0f};
+  struct A *q = &x[y].u;
+
+  __builtin_memcpy (&q->x, &p.x, sizeof (float));
+  __builtin_memcpy (&q->y, &p.y, sizeof (float));
+
+  bar (&p);
+
+  return x[y].u.x + x[y].u.y;
+}
-- 
2.34.1