For CONST_VECTOR_DUPLICATE_P in constant_pool, it is just broadcast or variants in ix86_vector_duplicate_simode_const. Adjust the cost to COSTS_N_INSNS (2) + speed which should be a little bit larger than broadcast.
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}. Ok for trunk? gcc/ChangeLog: PR target/114428 * config/i386/i386.cc (ix86_rtx_costs): Adjust cost for CONST_VECTOR_DUPLICATE_P in constant_pool. gcc/testsuite/ChangeLog: * gcc.target/i386/pr114428.c: New test. --- gcc/config/i386/i386-expand.cc | 2 +- gcc/config/i386/i386-protos.h | 1 + gcc/config/i386/i386.cc | 13 +++++++++++++ gcc/testsuite/gcc.target/i386/pr114428.c | 18 ++++++++++++++++++ 4 files changed, 33 insertions(+), 1 deletion(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr114428.c diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 4e16aedc5c1..d96c365e144 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -588,7 +588,7 @@ ix86_expand_move (machine_mode mode, rtx operands[]) /* OP is a memref of CONST_VECTOR, return scalar constant mem if CONST_VECTOR is a vec_duplicate, else return NULL. */ -static rtx +rtx ix86_broadcast_from_constant (machine_mode mode, rtx op) { int nunits = GET_MODE_NUNITS (mode); diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h index dbc861fb1ea..90712769200 100644 --- a/gcc/config/i386/i386-protos.h +++ b/gcc/config/i386/i386-protos.h @@ -107,6 +107,7 @@ extern void ix86_expand_clear (rtx); extern void ix86_expand_move (machine_mode, rtx[]); extern void ix86_expand_vector_move (machine_mode, rtx[]); extern void ix86_expand_vector_move_misalign (machine_mode, rtx[]); +extern rtx ix86_broadcast_from_constant (machine_mode, rtx); extern rtx ix86_fixup_binary_operands (enum rtx_code, machine_mode, rtx[], bool = false); extern void ix86_fixup_binary_operands_no_copy (enum rtx_code, machine_mode, diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc index b4838b7939e..fdd9343e47a 100644 --- a/gcc/config/i386/i386.cc +++ b/gcc/config/i386/i386.cc @@ -22197,6 +22197,19 @@ ix86_rtx_costs (rtx x, machine_mode mode, int outer_code_i, int opno, return true; case MEM: + /* CONST_VECTOR_DUPLICATE_P in constant_pool is just broadcast. + or variants in ix86_vector_duplicate_simode_const. */ + + if (GET_MODE_SIZE (mode) >= 16 + && VECTOR_MODE_P (mode) + && SYMBOL_REF_P (XEXP (x, 0)) + && CONSTANT_POOL_ADDRESS_P (XEXP (x, 0)) + && ix86_broadcast_from_constant (mode, x)) + { + *total = COSTS_N_INSNS (2) + speed; + return true; + } + /* An insn that accesses memory is slightly more expensive than one that does not. */ if (speed) diff --git a/gcc/testsuite/gcc.target/i386/pr114428.c b/gcc/testsuite/gcc.target/i386/pr114428.c new file mode 100644 index 00000000000..bbbc5a080f6 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr114428.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-march=x86-64-v3 -mno-avx512f -O2" } */ +/* { dg-final { scan-assembler-not "vpsra[dw]" } } */ + +void +foo2 (char* __restrict a, short* b) +{ + for (int i = 0; i != 32; i++) + a[i] = b[i] >> (short)8; +} + +void +foo3 (char* __restrict a, short* b) +{ + for (int i = 0; i != 16; i++) + a[i] = b[i] >> (short)8; +} + -- 2.31.1