[to-be-committed,RISC-V] Eliminate unnecessary sign extension after inlined str[n]cmp

This patch eliminates an unnecessary sign extension for scalar inlined
string comparisons on rv64.

Conceptually this is pretty simple.  Prove all the paths which "return"
a value from the inlined string comparison already have sign extended
values.

FINAL_LABEL is the point after the calculation of the return value.  So
if we have a jump to FINAL_LABEL, we must have a properly extended
result value at that point.

Second we're going to arrange in the .md part of the expander to use an
X mode temporary for the result.  After computing the result we will (if
necessary) extract the low part of the result using a SUBREG tagged with
the appropriate SUBREG_PROMOTED_* bits.

So with that background.

We find a jump to FINAL_LABEL in emit_strcmp_scalar_compare_byte.  Since
we know the result is X mode, we can just emit the subtraction of the
two chars in X mode and we'll have a properly sign extended result.

There's 4 jumps to final_label in emit_strcmp_scalar.

The first is just returning zero and needs trivial simplification to not
force the result into SImode.

The second is after calling strcmp in the library.  The ABI mandates
that value is sign extended, so there's nothing to do for that case.

The 3rd occurs after a call to
emit_strcmp_scalar_result_calculation_nonul.  If we dive into that
routine it needs simplificationq similar to what we did in
emit_strcmp_scalar_compare_byte

The 4th occurs after a call to emit_strcmp_scalar_result_calculation
which again needs trivial adjustment like we've done in the other routines.

Finally, at the end of expand_strcmp, just store the X mode result
sitting in SUB to RESULT.

The net of all that is we know every path has its result properly
extended to X mode.  Standard redundant extension removal will take care
of the rest.

We've been running this within Ventana for about 6 months, so naturally
it's been through various QA cycles, dhrystone, spec2017, etc.  It's
also been through a build/test cycle in my tester.  Waiting on results
from the pre-commit testing before moving forward.

gcc/
	* config/riscv/riscv-string.cc
	(emit_strcmp_scalar_compare_byte): Set RESULT directly rather
	than using a new temporary.
	(emit_strcmp_scalar_result_calculation_nonul): Likewise.
	(emit_strcmp_scalar_result_calculation): Likewise.
	(riscv_expand_strcmp_scalar): Use CONST0_RTX rather than
	generating a new node.
	(expand_strcmp): Copy directly from SUB to RESULT.
	* config/riscv/riscv.md (cmpstrnsi, cmpstrsi): Pass an X
	mode temporary to the expansion routines.  If necessary
	extract low part of the word to store in final result location.

diff --git a/gcc/config/riscv/riscv-string.cc b/gcc/config/riscv/riscv-string.cc
index 257a514d29013724dd8ab48879552aa1fabc2eb8..4736228e6f148364eb5bb0afbbb43bb16291219c 100644 (file)
--- a/gcc/config/riscv/riscv-string.cc
+++ b/gcc/config/riscv/riscv-string.cc
@@ -140,9 +140,7 @@ static void
 emit_strcmp_scalar_compare_byte (rtx result, rtx data1, rtx data2,
                                 rtx final_label)
 {
-  rtx tmp = gen_reg_rtx (Xmode);
-  do_sub3 (tmp, data1, data2);
-  emit_insn (gen_movsi (result, gen_lowpart (SImode, tmp)));
+  do_sub3 (result, data1, data2);
   emit_jump_insn (gen_jump (final_label));
   emit_barrier (); /* No fall-through.  */
 }
@@ -310,8 +308,7 @@ emit_strcmp_scalar_result_calculation_nonul (rtx result, rtx data1, rtx data2)
   rtx tmp = gen_reg_rtx (Xmode);
   emit_insn (gen_slt_3 (LTU, Xmode, Xmode, tmp, data1, data2));
   do_neg2 (tmp, tmp);
-  do_ior3 (tmp, tmp, const1_rtx);
-  emit_insn (gen_movsi (result, gen_lowpart (SImode, tmp)));
+  do_ior3 (result, tmp, const1_rtx);
 }
 
 /* strcmp-result calculation.
@@ -367,9 +364,7 @@ emit_strcmp_scalar_result_calculation (rtx result, rtx data1, rtx data2,
   unsigned int shiftr = (xlen - 1) * BITS_PER_UNIT;
   do_lshr3 (data1, data1, GEN_INT (shiftr));
   do_lshr3 (data2, data2, GEN_INT (shiftr));
-  rtx tmp = gen_reg_rtx (Xmode);
-  do_sub3 (tmp, data1, data2);
-  emit_insn (gen_movsi (result, gen_lowpart (SImode, tmp)));
+  do_sub3 (result, data1, data2);
 }
 
 /* Expand str(n)cmp using Zbb/TheadBb instructions.
@@ -444,7 +439,7 @@ riscv_expand_strcmp_scalar (rtx result, rtx src1, rtx src2,
   /* All compared and everything was equal.  */
   if (ncompare)
     {
-      emit_insn (gen_rtx_SET (result, gen_rtx_CONST_INT (SImode, 0)));
+      emit_insn (gen_rtx_SET (result, CONST0_RTX (GET_MODE (result))));
       emit_jump_insn (gen_jump (final_label));
       emit_barrier (); /* No fall-through.  */
     }
@@ -1512,7 +1507,7 @@ expand_strcmp (rtx result, rtx src1, rtx src2, rtx nbytes,
   if (with_length)
     emit_label (done);
 
-  emit_insn (gen_movsi (result, gen_lowpart (SImode, sub)));
+  emit_move_insn (result, sub);
   return true;
 }
 

diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index c0c960353eb996138bedfb3fedc56b2d0b8d9743..2e2379dfca4f8be2230d8ab6793c886dcb392be8 100644 (file)
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -4162,9 +4162,19 @@
   "riscv_inline_strncmp && !optimize_size
     && (TARGET_ZBB || TARGET_XTHEADBB || TARGET_VECTOR)"
 {
-  if (riscv_expand_strcmp (operands[0], operands[1], operands[2],
+  rtx temp = gen_reg_rtx (word_mode);
+  if (riscv_expand_strcmp (temp, operands[1], operands[2],
                            operands[3], operands[4]))
-    DONE;
+    {
+      if (TARGET_64BIT)
+       {
+         temp = gen_lowpart (SImode, temp);
+         SUBREG_PROMOTED_VAR_P (temp) = 1;
+         SUBREG_PROMOTED_SET (temp, SRP_SIGNED);
+       }
+      emit_move_insn (operands[0], temp);
+      DONE;
+    }
   else
     FAIL;
 })
@@ -4183,9 +4193,19 @@
   "riscv_inline_strcmp && !optimize_size
     && (TARGET_ZBB || TARGET_XTHEADBB || TARGET_VECTOR)"
 {
-  if (riscv_expand_strcmp (operands[0], operands[1], operands[2],
+  rtx temp = gen_reg_rtx (word_mode);
+  if (riscv_expand_strcmp (temp, operands[1], operands[2],
                            NULL_RTX, operands[3]))
-    DONE;
+    {
+      if (TARGET_64BIT)
+       {
+         temp = gen_lowpart (SImode, temp);
+         SUBREG_PROMOTED_VAR_P (temp) = 1;
+         SUBREG_PROMOTED_SET (temp, SRP_SIGNED);
+       }
+      emit_move_insn (operands[0], temp);
+      DONE;
+    }
   else
     FAIL;
 })