RISC-V: Rework branch costing model for if-conversion

The generic branch costing model for if-conversion assumes a fixed cost
of COSTS_N_INSNS (2) for a conditional branch, and that one half of that
cost comes from a preceding condition-set instruction, such as with
MODE_CC targets, and then the other half of that cost is for the actual
branch instruction.  This is hardcoded for `if_info.original_cost' in
`noce_find_if_block' and regardless of the cost set for branches via
BRANCH_COST.

Then `default_max_noce_ifcvt_seq_cost' instructs if-conversion to prefer
a branchless sequence as costly as high as triple the BRANCH_COST value
set.  This is apparently to make up for the inability to accurately
guess the branch penalty.

Consequently for the BRANCH_COST of 3 we commonly set for tuning,
if-conversion will consider branchless sequences costing 3 * 3 - 2 = 7
instruction units more than a corresponding branch sequence.  For the
BRANCH_COST of 4 such as with `sifive-7-series' tuning this is even
worse, at 3 * 4 - 2 = 10.  Effectively it means a branchless sequence
will always be chosen if available, even a very inefficient one.

Rework the branch costing model to better match our architecture,
observing in particular that we have no preparatory instructions for
branches so that the cost of a branch is naked BRANCH_COST plus any
extra overhead the processing of a branch's source RTX might incur.

Provide TARGET_INSN_COST and TARGET_MAX_NOCE_IFCVT_SEQ_COST handlers
than that return suitable cost based on BRANCH_COST.  The latter hook
usually returns a value that is lower than the cost of the corresponding
branched sequence.  This is because we don't really want to produce a
branchless sequence that is more expensive than the original branched
sequence.  If this turns out too conservative for some corner case, then
this choice might be revisited.

Then we don't want to fiddle with `noce_find_if_block' without a lot of
cross-target verification, so add TARGET_NOCE_CONVERSION_PROFITABLE_P
defined such that it subtracts the fixed COSTS_N_INSNS (2) cost from the
cost of the original branched sequence supplied and instead adds actual
branch cost calculated from the conditional branch instruction used.  It
is then further tweaked according to simple analysis of the replacement
branchless sequence produced so as to cancel the cost of an extraneous
zero extend operation produced by `noce_try_store_flag_mask' as observed
with gcc/testsuite/gcc.target/riscv/pr105314.c.

Tweak the testsuite accordingly and set `-mbranch-cost=' explicitly for
the relevant cases so that the expected if-conversion transformation is
made regardless of the default BRANCH_COST value of tuning in effect.
Some of these settings will be lowered later on as deficiencies in
branchless sequence generation have been fixed that lower their cost
calculated by if-conversion.

	gcc/
	* config/riscv/riscv.cc (riscv_insn_cost): New function.
	(riscv_max_noce_ifcvt_seq_cost): Likewise.
	(riscv_noce_conversion_profitable_p): Likewise.
	(TARGET_INSN_COST): New macro.
	(TARGET_MAX_NOCE_IFCVT_SEQ_COST): New macro.
	(TARGET_NOCE_CONVERSION_PROFITABLE_P): New macro.

	gcc/testsuite/
	* gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_imm.c:
	Explicitly set the branch cost.
	* gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_reg.c:
	Likewise.
	* gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_reg_reg.c:
	Likewise.
	* gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_imm.c:
	Likewise.
	* gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_reg.c:
	Likewise.
	* gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_reg_reg.c:
	Likewise.

diff --git a/gcc/config/riscv/riscv.cc b/gcc/config/riscv/riscv.cc
index 6a7ecdb627f0b4b6ea99257a8879b7d91b2c3b4d..e5f09c024ccf16f414c7b18b6da8af1a6aa8d5b2 100644 (file)
--- a/gcc/config/riscv/riscv.cc
+++ b/gcc/config/riscv/riscv.cc
@@ -43,6 +43,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "calls.h"
 #include "function.h"
 #include "explow.h"
+#include "ifcvt.h"
 #include "memmodel.h"
 #include "emit-rtl.h"
 #include "reload.h"
@@ -3324,6 +3325,118 @@ riscv_address_cost (rtx addr, machine_mode mode,
   return riscv_address_insns (addr, mode, false);
 }
 
+/* Implement TARGET_INSN_COST.  We factor in the branch cost in the cost
+   calculation for conditional branches: one unit is considered the cost
+   of microarchitecture-dependent actual branch execution and therefore
+   multiplied by BRANCH_COST and any remaining units are considered fixed
+   branch overhead.  */
+
+static int
+riscv_insn_cost (rtx_insn *insn, bool speed)
+{
+  rtx x = PATTERN (insn);
+  int cost = pattern_cost (x, speed);
+
+  if (JUMP_P (insn)
+      && GET_CODE (x) == SET
+      && GET_CODE (SET_DEST (x)) == PC
+      && GET_CODE (SET_SRC (x)) == IF_THEN_ELSE)
+    cost += COSTS_N_INSNS (BRANCH_COST (speed, false) - 1);
+  return cost;
+}
+
+/* Implement TARGET_MAX_NOCE_IFCVT_SEQ_COST.  Like the default implementation,
+   but we consider cost units of branch instructions equal to cost units of
+   other instructions.  */
+
+static unsigned int
+riscv_max_noce_ifcvt_seq_cost (edge e)
+{
+  bool predictable_p = predictable_edge_p (e);
+
+  if (predictable_p)
+    {
+      if (OPTION_SET_P (param_max_rtl_if_conversion_predictable_cost))
+       return param_max_rtl_if_conversion_predictable_cost;
+    }
+  else
+    {
+      if (OPTION_SET_P (param_max_rtl_if_conversion_unpredictable_cost))
+       return param_max_rtl_if_conversion_unpredictable_cost;
+    }
+
+  return COSTS_N_INSNS (BRANCH_COST (true, predictable_p));
+}
+
+/* Implement TARGET_NOCE_CONVERSION_PROFITABLE_P.  We replace the cost of a
+   conditional branch assumed by `noce_find_if_block' at `COSTS_N_INSNS (2)'
+   by our actual conditional branch cost, observing that our branches test
+   conditions directly, so there is no preparatory extra condition-set
+   instruction.  */
+
+static bool
+riscv_noce_conversion_profitable_p (rtx_insn *seq,
+                                   struct noce_if_info *if_info)
+{
+  struct noce_if_info riscv_if_info = *if_info;
+
+  riscv_if_info.original_cost -= COSTS_N_INSNS (2);
+  riscv_if_info.original_cost += insn_cost (if_info->jump, if_info->speed_p);
+
+  /* Hack alert!  When `noce_try_store_flag_mask' uses `cstore<mode>4'
+     to emit a conditional set operation on DImode output it comes up
+     with a sequence such as:
+
+     (insn 26 0 27 (set (reg:SI 140)
+            (eq:SI (reg/v:DI 137 [ c ])
+                (const_int 0 [0]))) 302 {*seq_zero_disi}
+         (nil))
+     (insn 27 26 28 (set (reg:DI 139)
+            (zero_extend:DI (reg:SI 140))) 116 {*zero_extendsidi2_internal}
+         (nil))
+
+     because our `cstore<mode>4' pattern expands to an insn that gives
+     a SImode output.  The output of conditional set is 0 or 1 boolean,
+     so it is valid for input in any scalar integer mode and therefore
+     combine later folds the zero extend operation into an equivalent
+     conditional set operation that produces a DImode output, however
+     this redundant zero extend operation counts towards the cost of
+     the replacement sequence.  Compensate for that by incrementing the
+     cost of the original sequence as well as the maximum sequence cost
+     accordingly.  */
+  rtx last_dest = NULL_RTX;
+  for (rtx_insn *insn = seq; insn; insn = NEXT_INSN (insn))
+    {
+      if (!NONDEBUG_INSN_P (insn))
+       continue;
+
+      rtx x = PATTERN (insn);
+      if (NONJUMP_INSN_P (insn)
+         && GET_CODE (x) == SET)
+       {
+         rtx src = SET_SRC (x);
+         if (last_dest != NULL_RTX
+             && GET_CODE (src) == ZERO_EXTEND
+             && REG_P (XEXP (src, 0))
+             && REGNO (XEXP (src, 0)) == REGNO (last_dest))
+           {
+             riscv_if_info.original_cost += COSTS_N_INSNS (1);
+             riscv_if_info.max_seq_cost += COSTS_N_INSNS (1);
+           }
+         last_dest = NULL_RTX;
+         rtx dest = SET_DEST (x);
+         if (COMPARISON_P (src)
+             && REG_P (dest)
+             && GET_MODE (dest) == SImode)
+           last_dest = dest;
+       }
+      else
+       last_dest = NULL_RTX;
+    }
+
+  return default_noce_conversion_profitable_p (seq, &riscv_if_info);
+}
+
 /* Return one word of double-word value OP.  HIGH_P is true to select the
    high part or false to select the low part. */
 
@@ -10143,6 +10256,13 @@ extract_base_offset_in_addr (rtx mem, rtx *base, rtx *offset)
 #define TARGET_RTX_COSTS riscv_rtx_costs
 #undef TARGET_ADDRESS_COST
 #define TARGET_ADDRESS_COST riscv_address_cost
+#undef TARGET_INSN_COST
+#define TARGET_INSN_COST riscv_insn_cost
+
+#undef TARGET_MAX_NOCE_IFCVT_SEQ_COST
+#define TARGET_MAX_NOCE_IFCVT_SEQ_COST riscv_max_noce_ifcvt_seq_cost
+#undef TARGET_NOCE_CONVERSION_PROFITABLE_P
+#define TARGET_NOCE_CONVERSION_PROFITABLE_P riscv_noce_conversion_profitable_p
 
 #undef TARGET_ASM_FILE_START
 #define TARGET_ASM_FILE_START riscv_file_start

diff --git a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_imm.c b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_imm.c
index e806f6f0807f768a3dd2f3b32893d8efbf3c9144..d6d3f013e9bee191cdd753f6a7d22b98ff0b06de 100644 (file)
--- a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_imm.c
+++ b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_imm.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv64gc_zicond -mabi=lp64d" { target { rv64 } } } */
-/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_zicond -mabi=lp64d -mbranch-cost=4" { target { rv64 } } } */
+/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f -mbranch-cost=4" { target { rv32 } } } */
 /* { dg-skip-if "" { *-*-* } {"-O0" "-Og" "-Os" "-Oz"} } */
 
 long primitiveSemantics_compare_imm_return_imm_imm_00(long a, long b) {

diff --git a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_reg.c b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_reg.c
index f976d608a03094743d062f85f8c818d810214784..4c14e892bac8255fa84611e2da0af37b205387ae 100644 (file)
--- a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_reg.c
+++ b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_imm_reg.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv64gc_zicond -mabi=lp64d" { target { rv64 } } } */
-/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_zicond -mabi=lp64d -mbranch-cost=4" { target { rv64 } } } */
+/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f -mbranch-cost=4" { target { rv32 } } } */
 /* { dg-skip-if "" { *-*-* } {"-O0" "-Og" "-Os" "-Oz"} } */
 
 long primitiveSemantics_compare_imm_return_imm_reg_00(long a, long b) {

diff --git a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_reg_reg.c b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_reg_reg.c
index 90e9119237316ddaf5dc5ccaf5b406d9ee33495a..e95318301bf6a4c4dd44f526652b39c96a3df3de 100644 (file)
--- a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_reg_reg.c
+++ b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_imm_return_reg_reg.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv64gc_zicond -mabi=lp64d" { target { rv64 } } } */
-/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_zicond -mabi=lp64d -mbranch-cost=5" { target { rv64 } } } */
+/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f -mbranch-cost=5" { target { rv32 } } } */
 /* { dg-skip-if "" { *-*-* } {"-O0" "-Og" "-Os" "-Oz"} } */
 
 long primitiveSemantics_compare_imm_return_reg_reg_00(long a, long b, long c) {

diff --git a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_imm.c b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_imm.c
index 8ad97abc320abff112fda18a07b48f7ae4ef10b3..cafdf79537d86eee68a732aaa3f461b7688c839e 100644 (file)
--- a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_imm.c
+++ b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_imm.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv64gc_zicond -mabi=lp64d" { target { rv64 } } } */
-/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_zicond -mabi=lp64d -mbranch-cost=4" { target { rv64 } } } */
+/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f -mbranch-cost=4" { target { rv32 } } } */
 /* { dg-skip-if "" { *-*-* } {"-O0" "-Og" "-Os" "-Oz"} } */
 
 long primitiveSemantics_compare_reg_return_imm_imm_00(long a, long b, long c) {

diff --git a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_reg.c b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_reg.c
index 5199ba71ef4ebf9f4c42d92eef3f2449fe039431..dda9a58c38821fa6887c4c9531c15185e80d8706 100644 (file)
--- a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_reg.c
+++ b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_imm_reg.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv64gc_zicond -mabi=lp64d" { target { rv64 } } } */
-/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_zicond -mabi=lp64d -mbranch-cost=4" { target { rv64 } } } */
+/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f -mbranch-cost=4" { target { rv32 } } } */
 /* { dg-skip-if "" { *-*-* } {"-O0" "-Og" "-Os" "-Oz"} } */
 
 long primitiveSemantics_compare_reg_return_imm_reg_00(long a, long b, long c) {

diff --git a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_reg_reg.c b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_reg_reg.c
index eecb95688f47151ea8f1c3dc161e40f3355eb7b2..0c2db3ca59d8c045673b03b33b19cefa0ad6b831 100644 (file)
--- a/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_reg_reg.c
+++ b/gcc/testsuite/gcc.target/riscv/zicond-primitiveSemantics_compare_reg_return_reg_reg.c
@@ -1,6 +1,6 @@
 /* { dg-do compile } */
-/* { dg-options "-march=rv64gc_zicond -mabi=lp64d" { target { rv64 } } } */
-/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f" { target { rv32 } } } */
+/* { dg-options "-march=rv64gc_zicond -mabi=lp64d -mbranch-cost=5" { target { rv64 } } } */
+/* { dg-options "-march=rv32gc_zicond -mabi=ilp32f -mbranch-cost=5" { target { rv32 } } } */
 /* { dg-skip-if "" { *-*-* } {"-O0" "-Og" "-Os" "-Oz"} } */
 
 long primitiveSemantics_compare_reg_return_reg_reg_00(long a, long b, long c,