+/* Determine whether or not the trip count to ahead ratio is too small based
+ on prefitablility consideration.
+ AHEAD: the iteration ahead distance,
+ EST_NITER: the estimated trip count. */
+
+static bool
+trip_count_to_ahead_ratio_too_small_p (unsigned ahead, HOST_WIDE_INT est_niter)
+{
+ /* Assume trip count to ahead ratio is big enough if the trip count could not
+ be estimated at compile time. */
+ if (est_niter < 0)
+ return false;
+
+ if (est_niter < (HOST_WIDE_INT) (TRIP_COUNT_TO_AHEAD_RATIO * ahead))
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file,
+ "Not prefetching -- loop estimated to roll only %d times\n",
+ (int) est_niter);
+ return true;
+ }
+
+ return false;
+}
+
+/* Determine whether or not the number of memory references in the loop is
+ reasonable based on the profitablity and compilation time considerations.
+ NINSNS: estimated number of instructions in the loop,
+ MEM_REF_COUNT: total number of memory references in the loop. */
+
+static bool
+mem_ref_count_reasonable_p (unsigned ninsns, unsigned mem_ref_count)
+{
+ int insn_to_mem_ratio;
+
+ if (mem_ref_count == 0)
+ return false;
+
+ /* Miss rate computation (is_miss_rate_acceptable) and dependence analysis
+ (compute_all_dependences) have high costs based on quadratic complexity.
+ To avoid huge compilation time, we give up prefetching if mem_ref_count
+ is too large. */
+ if (mem_ref_count > PREFETCH_MAX_MEM_REFS_PER_LOOP)
+ return false;
+
+ /* Prefetching improves performance by overlapping cache missing
+ memory accesses with CPU operations. If the loop does not have
+ enough CPU operations to overlap with memory operations, prefetching
+ won't give a significant benefit. One approximate way of checking
+ this is to require the ratio of instructions to memory references to
+ be above a certain limit. This approximation works well in practice.
+ TODO: Implement a more precise computation by estimating the time
+ for each CPU or memory op in the loop. Time estimates for memory ops
+ should account for cache misses. */
+ insn_to_mem_ratio = ninsns / mem_ref_count;
+
+ if (insn_to_mem_ratio < PREFETCH_MIN_INSN_TO_MEM_RATIO)
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file,
+ "Not prefetching -- instruction to memory reference ratio (%d) too small\n",
+ insn_to_mem_ratio);
+ return false;
+ }
+
+ return true;
+}
+
+/* Determine whether or not the instruction to prefetch ratio in the loop is
+ too small based on the profitablity consideration.
+ NINSNS: estimated number of instructions in the loop,
+ PREFETCH_COUNT: an estimate of the number of prefetches,
+ UNROLL_FACTOR: the factor to unroll the loop if prefetching. */
+
+static bool
+insn_to_prefetch_ratio_too_small_p (unsigned ninsns, unsigned prefetch_count,
+ unsigned unroll_factor)
+{
+ int insn_to_prefetch_ratio;
+
+ /* Prefetching most likely causes performance degradation when the instruction
+ to prefetch ratio is too small. Too many prefetch instructions in a loop
+ may reduce the I-cache performance.
+ (unroll_factor * ninsns) is used to estimate the number of instructions in
+ the unrolled loop. This implementation is a bit simplistic -- the number
+ of issued prefetch instructions is also affected by unrolling. So,
+ prefetch_mod and the unroll factor should be taken into account when
+ determining prefetch_count. Also, the number of insns of the unrolled
+ loop will usually be significantly smaller than the number of insns of the
+ original loop * unroll_factor (at least the induction variable increases
+ and the exit branches will get eliminated), so it might be better to use
+ tree_estimate_loop_size + estimated_unrolled_size. */
+ insn_to_prefetch_ratio = (unroll_factor * ninsns) / prefetch_count;
+ if (insn_to_prefetch_ratio < MIN_INSN_TO_PREFETCH_RATIO)
+ {
+ if (dump_file && (dump_flags & TDF_DETAILS))
+ fprintf (dump_file,
+ "Not prefetching -- instruction to prefetch ratio (%d) too small\n",
+ insn_to_prefetch_ratio);
+ return true;
+ }
+
+ return false;
+}
+
+
OSDN Git Service
