diff options
| author | Richard Biener <rguenther@suse.de> | 2022-03-11 11:51:13 +0100 |
|---|---|---|
| committer | Richard Biener <rguenther@suse.de> | 2022-03-11 14:11:59 +0100 |
| commit | 69619acd8d9b5856f5af6e5323d9c7c4ec9ad08f (patch) | |
| tree | c60870eeb11a2b981f82dfbb1742a734588b7c5d | |
| parent | db494fd68d12f3b49ad5f4747c234f3a94d10c72 (diff) | |
| download | gcc-69619acd8d9b5856f5af6e5323d9c7c4ec9ad08f.zip gcc-69619acd8d9b5856f5af6e5323d9c7c4ec9ad08f.tar.gz gcc-69619acd8d9b5856f5af6e5323d9c7c4ec9ad08f.tar.bz2 | |
target/104762 - vectorization costs of CONSTRUCTORs
After accounting for GPR -> XMM move cost for vec_construct the
base cost needs adjustments to not double-cost those. This also
lowers the cost when such move is not necessary.
2022-03-11 Richard Biener <rguenther@suse.de>
PR target/104762
* config/i386/i386.cc (ix86_builtin_vectorization_cost): Do not
cost the first lane of SSE pieces as inserts for vec_construct.
| -rw-r--r-- | gcc/config/i386/i386.cc | 17 |
1 files changed, 11 insertions, 6 deletions
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc index 4121f98..23bedea 100644 --- a/gcc/config/i386/i386.cc +++ b/gcc/config/i386/i386.cc @@ -22597,16 +22597,21 @@ ix86_builtin_vectorization_cost (enum vect_cost_for_stmt type_of_cost, case vec_construct: { - /* N element inserts into SSE vectors. */ - int cost = TYPE_VECTOR_SUBPARTS (vectype) * ix86_cost->sse_op; + int n = TYPE_VECTOR_SUBPARTS (vectype); + /* N - 1 element inserts into an SSE vector, the possible + GPR -> XMM move is accounted for in add_stmt_cost. */ + if (GET_MODE_BITSIZE (mode) <= 128) + return (n - 1) * ix86_cost->sse_op; /* One vinserti128 for combining two SSE vectors for AVX256. */ - if (GET_MODE_BITSIZE (mode) == 256) - cost += ix86_vec_cost (mode, ix86_cost->addss); + else if (GET_MODE_BITSIZE (mode) == 256) + return ((n - 2) * ix86_cost->sse_op + + ix86_vec_cost (mode, ix86_cost->addss)); /* One vinserti64x4 and two vinserti128 for combining SSE and AVX256 vectors to AVX512. */ else if (GET_MODE_BITSIZE (mode) == 512) - cost += 3 * ix86_vec_cost (mode, ix86_cost->addss); - return cost; + return ((n - 4) * ix86_cost->sse_op + + 3 * ix86_vec_cost (mode, ix86_cost->addss)); + gcc_unreachable (); } default: |