public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc r13-1509] Doubleword version of and; cmp to not; test optimization on x86.
@ 2022-07-05 17:08 Roger Sayle
0 siblings, 0 replies; only message in thread
From: Roger Sayle @ 2022-07-05 17:08 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:c73e8d45ca0111f51d7187641963df97f5c9c63f
commit r13-1509-gc73e8d45ca0111f51d7187641963df97f5c9c63f
Author: Roger Sayle <roger@nextmovesoftware.com>
Date: Tue Jul 5 18:06:13 2022 +0100
Doubleword version of and;cmp to not;test optimization on x86.
This patch extends the earlier and;cmp to not;test optimization to also
perform this transformation for TImode on TARGET_64BIT and DImode on -m32,
One motivation for this is that it's a step to fixing the current failure
of gcc.target/i386/pr65105-5.c on -m32.
A more direct benefit for x86_64 is that the following code:
int foo(__int128 x, __int128 y)
{
return (x & y) == y;
}
improves with -O2 from 15 instructions:
movq %rdi, %r8
movq %rsi, %rax
movq %rax, %rdi
movq %r8, %rsi
movq %rdx, %r8
andq %rdx, %rsi
andq %rcx, %rdi
movq %rsi, %rax
movq %rdi, %rdx
xorq %r8, %rax
xorq %rcx, %rdx
orq %rdx, %rax
sete %al
movzbl %al, %eax
ret
to the slightly better 13 instructions:
movq %rdi, %r8
movq %rsi, %rax
movq %r8, %rsi
movq %rax, %rdi
notq %rsi
notq %rdi
andq %rdx, %rsi
andq %rcx, %rdi
movq %rsi, %rax
orq %rdi, %rax
sete %al
movzbl %al, %eax
ret
2022-07-05 Roger Sayle <roger@nextmovesoftware.com>
gcc/ChangeLog
* config/i386/i386.cc (ix86_rtx_costs) <COMPARE>: Provide costs
for double word comparisons and tests (comparisons against zero).
* config/i386/i386.md (*test<mode>_not_doubleword): Split DWI
and;cmp into andn;cmp $0 as a pre-reload splitter.
(*andn<dwi>3_doubleword_bmi): Use <dwi> instead of <mode> in name.
(*<any_or><dwi>3_doubleword): Likewise.
gcc/testsuite/ChangeLog
* gcc.target/i386/testnot-3.c: New test case.
Diff:
---
gcc/config/i386/i386.cc | 13 +++++++++++++
gcc/config/i386/i386.md | 22 ++++++++++++++++++++--
gcc/testsuite/gcc.target/i386/testnot-3.c | 9 +++++++++
3 files changed, 42 insertions(+), 2 deletions(-)
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 0cfe9962f75..95cb1e2ce70 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -20982,6 +20982,19 @@ ix86_rtx_costs (rtx x, machine_mode mode, int outer_code_i, int opno,
return true;
}
+ if (SCALAR_INT_MODE_P (GET_MODE (op0))
+ && GET_MODE_SIZE (GET_MODE (op0)) > UNITS_PER_WORD)
+ {
+ if (op1 == const0_rtx)
+ *total = cost->add
+ + rtx_cost (op0, GET_MODE (op0), outer_code, opno, speed);
+ else
+ *total = 3*cost->add
+ + rtx_cost (op0, GET_MODE (op0), outer_code, opno, speed)
+ + rtx_cost (op1, GET_MODE (op0), outer_code, opno, speed);
+ return true;
+ }
+
/* The embedded comparison operand is completely free. */
if (!general_operand (op0, GET_MODE (op0)) && op1 == const0_rtx)
*total = 0;
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index d11475489fc..bdde577ddb5 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -9792,7 +9792,25 @@
(set (reg:CCZ FLAGS_REG)
(compare:CCZ (and:SWI (match_dup 2) (match_dup 1))
(const_int 0)))]
+ "operands[2] = gen_reg_rtx (<MODE>mode);")
+
+;; Split and;cmp (as optimized by combine) into andn;cmp $0
+(define_insn_and_split "*test<mode>_not_doubleword"
+ [(set (reg:CCZ FLAGS_REG)
+ (compare:CCZ
+ (and:DWI
+ (not:DWI (match_operand:DWI 0 "nonimmediate_operand"))
+ (match_operand:DWI 1 "nonimmediate_operand"))
+ (const_int 0)))]
+ "ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(parallel
+ [(set (match_dup 2) (and:DWI (not:DWI (match_dup 0)) (match_dup 1)))
+ (clobber (reg:CC FLAGS_REG))])
+ (set (reg:CCZ FLAGS_REG) (compare:CCZ (match_dup 2) (const_int 0)))]
{
+ operands[0] = force_reg (<MODE>mode, operands[0]);
operands[2] = gen_reg_rtx (<MODE>mode);
})
@@ -10404,7 +10422,7 @@
operands[2] = gen_int_mode (INTVAL (operands[2]), QImode);
})
-(define_insn_and_split "*andn<mode>3_doubleword_bmi"
+(define_insn_and_split "*andn<dwi>3_doubleword_bmi"
[(set (match_operand:<DWI> 0 "register_operand" "=r")
(and:<DWI>
(not:<DWI> (match_operand:<DWI> 1 "register_operand" "r"))
@@ -10618,7 +10636,7 @@
DONE;
})
-(define_insn_and_split "*<code><mode>3_doubleword"
+(define_insn_and_split "*<code><dwi>3_doubleword"
[(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
(any_or:<DWI>
(match_operand:<DWI> 1 "nonimmediate_operand" "%0,0")
diff --git a/gcc/testsuite/gcc.target/i386/testnot-3.c b/gcc/testsuite/gcc.target/i386/testnot-3.c
new file mode 100644
index 00000000000..7c54dbc3421
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/testnot-3.c
@@ -0,0 +1,9 @@
+/* { dg-do compile { target int128 } } */
+/* { dg-options "-O2" } */
+
+int foo(__int128 x, __int128 y)
+{
+ return (x & y) == y;
+}
+
+/* { dg-final { scan-assembler-not "xorq" } } */
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2022-07-05 17:08 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-07-05 17:08 [gcc r13-1509] Doubleword version of and; cmp to not; test optimization on x86 Roger Sayle
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).