On Fri, Aug 28, 2020 at 08:47:06AM +0200, Richard Biener via Gcc-patches wrote:
> IIRC elsewhere it was discussed to use ld to perform merging by
> emitting separate rodata sections for constant sizes (4, 8, 16, 32, 64
> byte sizes).
ld does that already, and gcc too.
> ld could always direct 8 byte constant refs to the larger pools (sub-)entry.
But there is no way to express in ELF that something like that would be
acceptable.
I meant something like the following, which on e.g. a dumb:
typedef float V __attribute__((vector_size (4 * sizeof (float))));
void
foo (V *p, float *q)
{
p[0] += (V) { 1.0f, 2.0f, 3.0f, 4.0f };
q[0] += 4.0f;
q[1] -= 3.0f;
q[17] -= 2.0f;
q[31] += 1.0f;
}
testcase merges all the 4 scalar constant pool entries into the CONST_VECTOR
one.
I'm punting for section anchors and not doing it in the per-function (i.e.
non-shared) constant pools simply because I don't know them well enough,
don't know whether backends use the offsets for something etc.
For section anchors, I guess it would need to be done before (re)computing the
offsets and arrange for the desc->mark < 0 entries not to be considered as
objects in the object block, for non-shared pools, perhaps it would be
enough to call the new function from output_constant_pool before calling
recompute_pool_offsets and adjust recompute_pool_offsets to ignore
desc->mark < 0.
2020-08-28 Jakub Jelinek <[email protected]>
* varasm.c (output_constant_pool_contents): Emit desc->mark < 0
entries as aliases.
(optimize_constant_pool): New function.
(output_shared_constant_pool): Call it if TARGET_SUPPORTS_ALIASES.
--- gcc/varasm.c.jj 2020-07-28 15:39:10.091755086 +0200
+++ gcc/varasm.c 2020-08-28 10:38:10.207636849 +0200
@@ -4198,7 +4198,27 @@ output_constant_pool_contents (struct rt
class constant_descriptor_rtx *desc;
for (desc = pool->first; desc ; desc = desc->next)
- if (desc->mark)
+ if (desc->mark < 0)
+ {
+#ifdef ASM_OUTPUT_DEF
+ const char *name = targetm.strip_name_encoding (XSTR (desc->sym, 0));
+ char label[256];
+ char buffer[256 + 32];
+ const char *p;
+
+ ASM_GENERATE_INTERNAL_LABEL (label, "LC", ~desc->mark);
+ p = targetm.strip_name_encoding (label);
+ if (desc->offset)
+ {
+ sprintf (buffer, "%s+%ld", p, (long) (desc->offset));
+ p = buffer;
+ }
+ ASM_OUTPUT_DEF (asm_out_file, name, p);
+#else
+ gcc_unreachable ();
+#endif
+ }
+ else if (desc->mark)
{
/* If the constant is part of an object_block, make sure that
the constant has been positioned within its block, but do not
@@ -4216,6 +4236,52 @@ output_constant_pool_contents (struct rt
}
}
+/* Attempt to optimize constant pool POOL. If it contains both CONST_VECTOR
+ constants and scalar constants with the values of CONST_VECTOR elements,
+ try to alias the scalar constants with the CONST_VECTOR elements. */
+
+static void
+optimize_constant_pool (struct rtx_constant_pool *pool)
+{
+ for (constant_descriptor_rtx *desc = pool->first; desc; desc = desc->next)
+ if (desc->mark > 0
+ && GET_CODE (desc->constant) == CONST_VECTOR
+ && VECTOR_MODE_P (desc->mode)
+ && GET_MODE_CLASS (desc->mode) != MODE_VECTOR_BOOL
+ && !(SYMBOL_REF_HAS_BLOCK_INFO_P (desc->sym)
+ && SYMBOL_REF_BLOCK (desc->sym))
+ && desc->labelno >= 0)
+ {
+ scalar_mode submode = GET_MODE_INNER (desc->mode);
+ unsigned int subalign = MIN (desc->align, GET_MODE_BITSIZE (submode));
+ int units = GET_MODE_NUNITS (desc->mode);
+
+ for (int i = 0; i < units; i++)
+ {
+ if (i != 0
+ && rtx_equal_p (CONST_VECTOR_ELT (desc->constant, i),
+ CONST_VECTOR_ELT (desc->constant, i - 1)))
+ continue;
+
+ constant_descriptor_rtx tmp;
+ tmp.constant = CONST_VECTOR_ELT (desc->constant, i);
+ tmp.mode = submode;
+ hashval_t hash = const_rtx_hash (tmp.constant);
+ constant_descriptor_rtx *eldesc
+ = pool->const_rtx_htab->find_with_hash (&tmp, hash);
+ if (eldesc
+ && eldesc->mark > 0
+ && eldesc->align <= subalign
+ && !(SYMBOL_REF_HAS_BLOCK_INFO_P (eldesc->sym)
+ && SYMBOL_REF_BLOCK (eldesc->sym)))
+ {
+ eldesc->mark = ~desc->labelno;
+ eldesc->offset = i * GET_MODE_SIZE (submode);
+ }
+ }
+ }
+}
+
/* Mark all constants that are used in the current function, then write
out the function's private constant pool. */
@@ -4251,6 +4317,9 @@ output_constant_pool (const char *fnname
void
output_shared_constant_pool (void)
{
+ if (TARGET_SUPPORTS_ALIASES)
+ optimize_constant_pool (shared_constant_pool);
+
output_constant_pool_contents (shared_constant_pool);
}
Jakub
