1. Update vec_duplicate to allow to fail so that backend can only allow
broadcasting an integer constant to a vector when broadcast instruction
is available. This can be used by memset expander to avoid vec_duplicate
when loading from constant pool is more efficient.
2. Add vec_duplicate<mode> expander and enable vec_duplicate from a
non-standard SSE constant integer only if vector broadcast is available.
* config/i386/i386-expand.c (ix86_expand_integer_vec_duplicate):
New function.
* config/i386/i386-protos.h (ix86_expand_integer_vec_duplicat):
New prototype.
* config/i386/sse.md (INT_BROADCAST_MODE): New mode iterator.
(vec_duplicate<mode>): New expander.
* doc/md.texi: Update vec_duplicate.
---
gcc/config/i386/i386-expand.c | 24 ++++++++++++++++++++++++
gcc/config/i386/i386-protos.h | 1 +
gcc/config/i386/sse.md | 28 ++++++++++++++++++++++++++++
gcc/doc/md.texi | 2 --
4 files changed, 53 insertions(+), 2 deletions(-)
diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index e9e89c82764..75c160d4349 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -15742,6 +15742,30 @@ ix86_expand_vector_extract (bool mmx_ok, rtx target,
rtx vec, int elt)
}
}
+/* Expand integer vec_duplicate. Return true if successful. */
+
+bool
+ix86_expand_integer_vec_duplicate (rtx *operands)
+{
+ /* Enable VEC_DUPLICATE from a non-standard SSE constant integer only
+ if vector broadcast is available. */
+ machine_mode mode = GET_MODE (operands[0]);
+ if (CONST_INT_P (operands[1])
+ && (!(TARGET_AVX2
+ || (TARGET_AVX
+ && (GET_MODE_INNER (mode) == SImode
+ || GET_MODE_INNER (mode) == DImode)))
+ || standard_sse_constant_p (operands[1], mode)))
+ return false;
+
+ bool ok = ix86_expand_vector_init_duplicate (false, mode,
+ operands[0],
+ operands[1]);
+ gcc_assert (ok);
+
+ return true;
+}
+
/* Generate code to copy vector bits i / 2 ... i - 1 from vector SRC
to bits 0 ... i / 2 - 1 of vector DEST, which has the same mode.
The upper bits of DEST are undefined, though they shouldn't cause
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index 71745b9a1ea..a6cc09bb75b 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -258,6 +258,7 @@ extern void ix86_expand_mul_widen_hilo (rtx, rtx, rtx,
bool, bool);
extern void ix86_expand_sse2_mulv4si3 (rtx, rtx, rtx);
extern void ix86_expand_sse2_mulvxdi3 (rtx, rtx, rtx);
extern void ix86_expand_sse2_abs (rtx, rtx);
+extern bool ix86_expand_integer_vec_duplicate (rtx *);
/* In i386-c.c */
extern void ix86_target_macros (void);
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index e4f01e64bc1..53a703fb466 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -24640,3 +24640,31 @@ (define_insn "*aes<aeswideklvariant>u8"
"TARGET_WIDEKL"
"aes<aeswideklvariant>\t{%0}"
[(set_attr "type" "other")])
+
+;; Modes handled by broadcast patterns. NB: Allow V64QI and V32HI with
+;; TARGET_AVX512F since ix86_expand_integer_vec_duplicate can expand
+;; without TARGET_AVX512BW which is used by memset vector broadcast
+;; expander to XI with:
+;; vmovd %edi, %xmm15
+;; vpbroadcastb %xmm15, %ymm15
+;; vinserti64x4 $0x1, %ymm15, %zmm15, %zmm15
+
+(define_mode_iterator INT_BROADCAST_MODE
+ [(V64QI "TARGET_AVX512F") (V32QI "TARGET_AVX") V16QI
+ (V32HI "TARGET_AVX512F") (V16HI "TARGET_AVX") V8HI
+ (V16SI "TARGET_AVX512F") (V8SI "TARGET_AVX") V4SI
+ (V8DI "TARGET_AVX512F && TARGET_64BIT")
+ (V4DI "TARGET_AVX && TARGET_64BIT") (V2DI "TARGET_64BIT")])
+
+;; Broadcast from an integer. NB: Enable broadcast only if we can move
+;; from GPR to SSE register directly.
+(define_expand "vec_duplicate<mode>"
+ [(set (match_operand:INT_BROADCAST_MODE 0 "register_operand")
+ (vec_duplicate:INT_BROADCAST_MODE
+ (match_operand:<ssescalarmode> 1 "general_operand")))]
+ "TARGET_SSE2 && TARGET_INTER_UNIT_MOVES_TO_VEC"
+{
+ if (!ix86_expand_integer_vec_duplicate (operands))
+ FAIL;
+ DONE;
+})
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index 1b918144330..a892c94d163 100644
--- a/gcc/doc/md.texi
+++ b/gcc/doc/md.texi
@@ -5077,8 +5077,6 @@ the mode appropriate for one element of @var{m}.
This pattern only handles duplicates of non-constant inputs. Constant
vectors go through the @code{mov@var{m}} pattern instead.
-This pattern is not allowed to @code{FAIL}.
-
@cindex @code{vec_series@var{m}} instruction pattern
@item @samp{vec_series@var{m}}
Initialize vector output operand 0 so that element @var{i} is equal to
--
2.31.1
