diff mbox series

[v6,07/11] Handle variable-length vector types in store_constructor

Message ID 20251206165518.5449-8-chris.bazley@arm.com
State Superseded
Headers
Series Extend BB SLP vectorization to use predicated tails |

Commit Message

Christopher Bazley Dec. 6, 2025, 4:55 p.m. UTC 
  When given a constructor of variable-length vector type, the
store_constructor function now builds a vector with the number of
elements specified by the constructor and uses it to emit the body
of the kind of insn chosen by the convert_optab_handler function.
Previously, this function used a fallback path of calling
store_constructor_field upon discovering that the number of subparts
in the vector type was not a constant multiple of the number of
subparts in the element type.

For example, this allows GCC to generate the following AArch64 assembly
language output for the tail of a reduction in the slp_6 test:

uaddv d31, p6, z31.b
uaddv d27, p6, z27.b
uaddv d26, p6, z26.b
movi  d30, #0
insr  z30.b, b26
insr  z30.b, b27
insr  z30.b, b31
add   z25.b, z25.b, z30.b

instead of the following output (with predicated tails for basic block
SLP vectorization but without this change):

addvl  x0, sp, #2
movi   d0, #0
st1b   z0.b, p6, [sp, #2, mul vl]
uaddv  d27, p6, z27.b
uaddv  d26, p6, z26.b
uaddv  d25, p6, z25.b
str    b27, [x0]
addvl  x0, sp, #1
add    x0, x0, 1
ptrue  p7.b, vl3
ld1b   z0.b, p6/z, [sp, #2, mul vl]
st1b   z0.b, p6, [sp, #1, mul vl]
str    b26, [x0]
ld1b   z0.b, p6/z, [sp, #1, mul vl]
st1b   z0.b, p6, [sp]
str    b25, [sp, 2]
ld1b   z0.b, p6/z, [sp]
add    z28.b, z28.b, z0.b
st1b   z28.b, p7, [x1]
addvl  sp, sp, #3

or the original assembly language output (with neither predicated tails
for basic block SLP vectorization nor this change):

uaddv  d31, p6, z31.b
fmov   x0, d31
uaddv  d31, p6, z26.b
add    w6, w6, w0
fmov   x0, d31
uaddv  d31, p6, z27.b
add    w5, w5, w0
fmov   x0, d31
add    w4, w4, w0

gcc/ChangeLog:

	* expr.cc (store_constructor): Add an else block to handle
	cases of TREE_CODE (TREE_TYPE (exp)) == VECTOR_TYPE in which
	exact_div (n_elts, GET_MODE_NUNITS (eltmode)).is_constant
	(&const_n_elts) is false similar to the existing "element type
	is not a vector type" case except that const_n_elts is taken
	from the constructor instead of the subparts of the vector
	type.

---
 gcc/expr.cc | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/gcc/expr.cc b/gcc/expr.cc
index 7d84ad9e6fc..622c5be1d59 100644
--- a/gcc/expr.cc
+++ b/gcc/expr.cc
@@ -8058,7 +8058,12 @@  store_constructor (tree exp, rtx target, int cleared, poly_int64 size,
 		   similarly non-const type vectors. */
 		icode = convert_optab_handler (vec_init_optab, mode, eltmode);
 	      }
-
+	    else
+	      {
+		/* Handle variable-length vector types.  */
+		icode = convert_optab_handler (vec_init_optab, mode, eltmode);
+		const_n_elts = CONSTRUCTOR_NELTS (exp);
+	      }
 	  if (const_n_elts && icode != CODE_FOR_nothing)
 	    {
 	      vector = rtvec_alloc (const_n_elts);