[gcc r14-6642] LoongArch: Fix instruction costs [PR112936]

[Xi Ruoyao]

https://gcc.gnu.org/g:50b3f596bd943ec6110c1987f14e5497ce39622f

commit r14-6642-g50b3f596bd943ec6110c1987f14e5497ce39622f
Author: Xi Ruoyao <xry111@xry111.site>
Date:   Sat Dec 9 17:41:32 2023 +0800

    LoongArch: Fix instruction costs [PR112936]
    
    Replace the instruction costs in loongarch_rtx_cost_data constructor
    based on micro-benchmark results on LA464 and LA664.
    
    This allows optimizations like "x * 17" to alsl, and "x * 68" to alsl
    and slli.
    
    gcc/ChangeLog:
    
            PR target/112936
            * config/loongarch/loongarch-def.cc
            (loongarch_rtx_cost_data::loongarch_rtx_cost_data): Update
            instruction costs per micro-benchmark results.
            (loongarch_rtx_cost_optimize_size): Set all instruction costs
            to (COSTS_N_INSNS (1) + 1).
            * config/loongarch/loongarch.cc (loongarch_rtx_costs): Remove
            special case for multiplication when optimizing for size.
            Adjust division cost when TARGET_64BIT && !TARGET_DIV32.
            Account the extra cost when TARGET_CHECK_ZERO_DIV and
            optimizing for speed.
    
    gcc/testsuite/ChangeLog
    
            PR target/112936
            * gcc.target/loongarch/mul-const-reduction.c: New test.

Diff:
---
 gcc/config/loongarch/loongarch-def.cc              | 39 ++++++++++++----------
 gcc/config/loongarch/loongarch.cc                  | 22 ++++++------
 .../gcc.target/loongarch/mul-const-reduction.c     | 11 ++++++
 3 files changed, 43 insertions(+), 29 deletions(-)

diff --git a/gcc/config/loongarch/loongarch-def.cc b/gcc/config/loongarch/loongarch-def.cc
index 6217b19268c..4a8885e8343 100644
--- a/gcc/config/loongarch/loongarch-def.cc
+++ b/gcc/config/loongarch/loongarch-def.cc
@@ -92,15 +92,15 @@ array_tune<loongarch_align> loongarch_cpu_align =
 
 /* Default RTX cost initializer.  */
 loongarch_rtx_cost_data::loongarch_rtx_cost_data ()
-  : fp_add (COSTS_N_INSNS (1)),
-    fp_mult_sf (COSTS_N_INSNS (2)),
-    fp_mult_df (COSTS_N_INSNS (4)),
-    fp_div_sf (COSTS_N_INSNS (6)),
+  : fp_add (COSTS_N_INSNS (5)),
+    fp_mult_sf (COSTS_N_INSNS (5)),
+    fp_mult_df (COSTS_N_INSNS (5)),
+    fp_div_sf (COSTS_N_INSNS (8)),
     fp_div_df (COSTS_N_INSNS (8)),
-    int_mult_si (COSTS_N_INSNS (1)),
-    int_mult_di (COSTS_N_INSNS (1)),
-    int_div_si (COSTS_N_INSNS (4)),
-    int_div_di (COSTS_N_INSNS (6)),
+    int_mult_si (COSTS_N_INSNS (4)),
+    int_mult_di (COSTS_N_INSNS (4)),
+    int_div_si (COSTS_N_INSNS (5)),
+    int_div_di (COSTS_N_INSNS (5)),
     branch_cost (6),
     memory_latency (4) {}
 
@@ -111,18 +111,21 @@ loongarch_rtx_cost_data::loongarch_rtx_cost_data ()
 array_tune<loongarch_rtx_cost_data> loongarch_cpu_rtx_cost_data =
   array_tune<loongarch_rtx_cost_data> ();
 
-/* RTX costs to use when optimizing for size.  */
+/* RTX costs to use when optimizing for size.
+   We use a value slightly larger than COSTS_N_INSNS (1) for all of them
+   because they are slower than simple instructions.  */
+#define COST_COMPLEX_INSN (COSTS_N_INSNS (1) + 1)
 const loongarch_rtx_cost_data loongarch_rtx_cost_optimize_size =
   loongarch_rtx_cost_data ()
-    .fp_add_ (4)
-    .fp_mult_sf_ (4)
-    .fp_mult_df_ (4)
-    .fp_div_sf_ (4)
-    .fp_div_df_ (4)
-    .int_mult_si_ (4)
-    .int_mult_di_ (4)
-    .int_div_si_ (4)
-    .int_div_di_ (4);
+    .fp_add_ (COST_COMPLEX_INSN)
+    .fp_mult_sf_ (COST_COMPLEX_INSN)
+    .fp_mult_df_ (COST_COMPLEX_INSN)
+    .fp_div_sf_ (COST_COMPLEX_INSN)
+    .fp_div_df_ (COST_COMPLEX_INSN)
+    .int_mult_si_ (COST_COMPLEX_INSN)
+    .int_mult_di_ (COST_COMPLEX_INSN)
+    .int_div_si_ (COST_COMPLEX_INSN)
+    .int_div_di_ (COST_COMPLEX_INSN);
 
 array_tune<int> loongarch_cpu_issue_rate = array_tune<int> ()
   .set (CPU_NATIVE, 4)
diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index 860e6e8229f..390e3206a17 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -3801,8 +3801,6 @@ loongarch_rtx_costs (rtx x, machine_mode mode, int outer_code,
 	*total = (speed
 		  ? loongarch_cost->int_mult_si * 3 + 6
 		  : COSTS_N_INSNS (7));
-      else if (!speed)
-	*total = COSTS_N_INSNS (1) + 1;
       else if (mode == DImode)
 	*total = loongarch_cost->int_mult_di;
       else
@@ -3837,14 +3835,18 @@ loongarch_rtx_costs (rtx x, machine_mode mode, int outer_code,
 
     case UDIV:
     case UMOD:
-      if (!speed)
-	{
-	  *total = COSTS_N_INSNS (loongarch_idiv_insns (mode));
-	}
-      else if (mode == DImode)
+      if (mode == DImode)
 	*total = loongarch_cost->int_div_di;
       else
-	*total = loongarch_cost->int_div_si;
+	{
+	  *total = loongarch_cost->int_div_si;
+	  if (TARGET_64BIT && !TARGET_DIV32)
+	    *total += COSTS_N_INSNS (2);
+	}
+
+      if (TARGET_CHECK_ZERO_DIV)
+	*total += COSTS_N_INSNS (2);
+
       return false;
 
     case SIGN_EXTEND:
@@ -3876,9 +3878,7 @@ loongarch_rtx_costs (rtx x, machine_mode mode, int outer_code,
 		  && (GET_CODE (XEXP (XEXP (XEXP (x, 0), 0), 1))
 		      == ZERO_EXTEND))))
 	{
-	  if (!speed)
-	    *total = COSTS_N_INSNS (1) + 1;
-	  else if (mode == DImode)
+	  if (mode == DImode)
 	    *total = loongarch_cost->int_mult_di;
 	  else
 	    *total = loongarch_cost->int_mult_si;
diff --git a/gcc/testsuite/gcc.target/loongarch/mul-const-reduction.c b/gcc/testsuite/gcc.target/loongarch/mul-const-reduction.c
new file mode 100644
index 00000000000..02d9a4876d8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/mul-const-reduction.c
@@ -0,0 +1,11 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mtune=la464" } */
+/* { dg-final { scan-assembler "alsl\.w" } } */
+/* { dg-final { scan-assembler "slli\.w" } } */
+/* { dg-final { scan-assembler-not "mul\.w" } } */
+
+int
+test (int a)
+{
+  return a * 68;
+}