+2013-09-28 Jan Hubicka <jh@suse.cz>
+
+ * x86-tune.def (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL): Enable for generic.
+ (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL): Likewise.
+ (X86_TUNE_FOUR_JUMP_LIMIT): Drop for generic and buldozer.
+ (X86_TUNE_PAD_RETURNS): Drop for buldozer chips.
+ (X86_TUNE_AVOID_VECTOR_DECODE): Drop for generic.
+ (X86_TUNE_REASSOC_FP_TO_PARALLEL): Enable for generic.
+
2013-09-28 Richard Sandiford <rdsandiford@googlemail.com>
* alloc-pool.c, asan.c, auto-inc-dec.c, basic-block.h, bb-reorder.c,
m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_ATOM | m_SLM | m_AMDFAM10
| m_BDVER | m_GENERIC)
DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal",
- m_COREI7 | m_AMDFAM10 | m_BDVER | m_BTVER | m_SLM)
+ m_COREI7 | m_AMDFAM10 | m_BDVER | m_BTVER | m_SLM | m_GENERIC)
DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal",
- m_COREI7 | m_BDVER | m_SLM)
+ m_COREI7 | m_BDVER | m_SLM | m_GENERIC)
DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optimal",
m_BDVER)
/* X86_TUNE_SSE_SPLIT_REGS: Set for machines where the type and dependencies
/* X86_TUNE_FOUR_JUMP_LIMIT: Some CPU cores are not able to predict more
than 4 branch instructions in the 16 byte window. */
DEF_TUNE (X86_TUNE_FOUR_JUMP_LIMIT, "four_jump_limit",
- m_PPRO | m_P4_NOCONA | m_ATOM | m_SLM | m_AMD_MULTIPLE
- | m_GENERIC)
+ m_PPRO | m_P4_NOCONA | m_ATOM | m_SLM | m_ATHLON_K8 | m_AMDFAM10)
DEF_TUNE (X86_TUNE_SCHEDULE, "schedule",
m_PENT | m_PPRO | m_CORE_ALL | m_ATOM | m_SLM | m_K6_GEODE
| m_AMD_MULTIPLE | m_GENERIC)
DEF_TUNE (X86_TUNE_USE_INCDEC, "use_incdec",
~(m_P4_NOCONA | m_CORE_ALL | m_ATOM | m_SLM | m_GENERIC))
DEF_TUNE (X86_TUNE_PAD_RETURNS, "pad_returns",
- m_AMD_MULTIPLE | m_GENERIC)
+ m_ATHLON_K8 | m_AMDFAM10 | m_GENERIC)
DEF_TUNE (X86_TUNE_PAD_SHORT_FUNCTION, "pad_short_function", m_ATOM)
DEF_TUNE (X86_TUNE_EXT_80387_CONSTANTS, "ext_80387_constants",
m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_ATOM | m_SLM | m_K6_GEODE
| m_ATHLON_K8 | m_GENERIC)
DEF_TUNE (X86_TUNE_AVOID_VECTOR_DECODE, "avoid_vector_decode",
- m_K8 | m_GENERIC)
+ m_K8)
/* X86_TUNE_PROMOTE_HIMODE_IMUL: Modern CPUs have same latency for HImode
and SImode multiply, but 386 and 486 do HImode multiply faster. */
DEF_TUNE (X86_TUNE_PROMOTE_HIMODE_IMUL, "promote_himode_imul",
/* X86_TUNE_REASSOC_FP_TO_PARALLEL: Try to produce parallel computations
during reassociation of fp computation. */
DEF_TUNE (X86_TUNE_REASSOC_FP_TO_PARALLEL, "reassoc_fp_to_parallel",
- m_ATOM | m_SLM | m_HASWELL | m_BDVER1 | m_BDVER2)
+ m_ATOM | m_SLM | m_HASWELL | m_BDVER1 | m_BDVER2 | m_GENERIC)
/* X86_TUNE_GENERAL_REGS_SSE_SPILL: Try to spill general regs to SSE
regs instead of memory. */
DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill",