The attached patch provides some improved patterns for "and with
complement" to the s390 machine description. Bootstrapped and
regression tested on s390 and s390x.
Ciao
Dominik ^_^ ^_^
--
Dominik Vogt
IBM Germany
gcc/ChangeLog
* config/s390/s390.h (REG_OR_SUBREG_P): New helper macro.
* config/s390/s390.c (s390_expand_logical_operator): Force operands
from memory into registers for expressions with register destination.
(s390_logical_operator_si3_ok_p)
(s390_andc_split_ok_p): New functions.
* config/s390/s390-protos.h (s390_logical_operator_si3_ok_p)
(s390_andc_split_ok_p): Add prototypes.
* config/s390/s390.md ("*andc_split", "*andc_split2"): New splitters
for and with complement.
("*andsi3_zarch", "*iorsi3_zarch", "xorsi3"): Call
s390_logical_operator_si3_ok_p.
gcc/testsuite/ChangeLog
* gcc.target/s390/md/andc-splitter-1.c: New test case.
* gcc.target/s390/md/andc-splitter-2.c: Likewise.
>From de225e02fe79661642f123fd0505a0bd60f20066 Mon Sep 17 00:00:00 2001
From: Dominik Vogt <v...@linux.vnet.ibm.com>
Date: Mon, 14 Mar 2016 17:48:17 +0100
Subject: [PATCH] S/390: Add splitter for "and" with complement.
Force splitting of logical operator expressions ... with three operands, a
register destination and a memory operand because there are no instructions for
that and combine results in inefficient code.
---
gcc/config/s390/s390-protos.h | 2 +
gcc/config/s390/s390.c | 65 ++++++++++++++++++++++
gcc/config/s390/s390.h | 3 +
gcc/config/s390/s390.md | 52 ++++++++++++++++-
gcc/testsuite/gcc.target/s390/md/andc-splitter-1.c | 61 ++++++++++++++++++++
gcc/testsuite/gcc.target/s390/md/andc-splitter-2.c | 38 +++++++++++++
6 files changed, 218 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/s390/md/andc-splitter-1.c
create mode 100644 gcc/testsuite/gcc.target/s390/md/andc-splitter-2.c
diff --git a/gcc/config/s390/s390-protos.h b/gcc/config/s390/s390-protos.h
index 2ccf0bb..8ba4d5d 100644
--- a/gcc/config/s390/s390-protos.h
+++ b/gcc/config/s390/s390-protos.h
@@ -127,6 +127,8 @@ extern rtx_insn *s390_emit_call (rtx, rtx, rtx, rtx);
extern void s390_expand_logical_operator (enum rtx_code,
machine_mode, rtx *);
extern bool s390_logical_operator_ok_p (rtx *);
+extern bool s390_logical_operator_si3_ok_p (rtx *);
+extern bool s390_andc_split_ok_p (rtx *);
extern void s390_narrow_logical_operator (enum rtx_code, rtx *, rtx *);
extern void s390_split_access_reg (rtx, rtx *, rtx *);
diff --git a/gcc/config/s390/s390.c b/gcc/config/s390/s390.c
index cb5dd5f..1a303d8 100644
--- a/gcc/config/s390/s390.c
+++ b/gcc/config/s390/s390.c
@@ -2558,6 +2558,27 @@ s390_expand_logical_operator (enum rtx_code code, machine_mode mode,
src2 = gen_rtx_SUBREG (wmode, force_reg (mode, src2), 0);
}
+ /* We have no useful instructions with three operands, the source in memory
+ and the destination in a register. Reload memory operands to register if
+ necessary. */
+ if (!s390_logical_operator_si3_ok_p (operands))
+ {
+ if (MEM_P (src1))
+ {
+ rtx temp = gen_reg_rtx (mode);
+
+ emit_move_insn (temp, src1);
+ src1 = temp;
+ }
+ if (MEM_P (src2))
+ {
+ rtx temp = gen_reg_rtx (mode);
+
+ emit_move_insn (temp, src2);
+ src2 = temp;
+ }
+ }
+
/* Emit the instruction. */
op = gen_rtx_SET (dst, gen_rtx_fmt_ee (code, wmode, src1, src2));
clob = gen_rtx_CLOBBER (VOIDmode, gen_rtx_REG (CCmode, CC_REGNUM));
@@ -2583,6 +2604,50 @@ s390_logical_operator_ok_p (rtx *operands)
return true;
}
+/* Rejects operand combinations of logical operations (AND, IOR, XOR) that
+ result in less efficient code later. */
+
+bool
+s390_logical_operator_si3_ok_p (rtx *operands)
+{
+ if (!s390_logical_operator_ok_p (operands))
+ return false;
+ if (reload_completed)
+ return true;
+ /* Reject three operand expressions with register destination if one of the
+ sources is a memory operand and the other is not a const_int operand. */
+ if (REG_OR_SUBREG_P (operands[0])
+ && (MEM_P (operands[1]) || MEM_P (operands[2]))
+ && !(CONST_INT_P (operands[1]) || CONST_INT_P (operands[2])))
+ return false;
+
+ return true;
+}
+
+/* Rejects operand combinations of AND operations that result in less efficient
+ code later. */
+
+bool
+s390_andc_split_ok_p (rtx *operands)
+{
+ if (reload_completed)
+ return false;
+ if (!s390_logical_operator_si3_ok_p (operands))
+ return false;
+ /* Reject two operand expressions with a memory destination that is identical
+ to one of the source operands and the other operand a register or memory
+ because the splitter would replace the destination with a register yielding
+ an undefined pattern. */
+ if (MEM_P (operands[0])
+ && (MEM_P (operands[1]) || REG_OR_SUBREG_P (operands[1]))
+ && (MEM_P (operands[2]) || REG_OR_SUBREG_P (operands[2]))
+ && (rtx_equal_p (operands[0], operands[1])
+ || rtx_equal_p (operands[0], operands[2])))
+ return false;
+
+ return true;
+}
+
/* Narrow logical operation CODE of memory operand MEMOP with immediate
operand IMMOP to switch from SS to SI type instructions. */
diff --git a/gcc/config/s390/s390.h b/gcc/config/s390/s390.h
index 3a7be1a..19185ed 100644
--- a/gcc/config/s390/s390.h
+++ b/gcc/config/s390/s390.h
@@ -389,6 +389,9 @@ extern const char *s390_host_detect_local_cpu (int argc, const char **argv);
#define ACCESS_REG_P(X) (REG_P (X) && ACCESS_REGNO_P (REGNO (X)))
#define VECTOR_NOFP_REG_P(X) (REG_P (X) && VECTOR_NOFP_REGNO_P (REGNO (X)))
#define VECTOR_REG_P(X) (REG_P (X) && VECTOR_REGNO_P (REGNO (X)))
+#define REG_OR_SUBREG_P(x) \
+ (REG_P ((x)) || (SUBREG_P ((x)) && REG_P (SUBREG_REG ((x)))))
+
/* Set up fixed registers and calling convention:
diff --git a/gcc/config/s390/s390.md b/gcc/config/s390/s390.md
index 5f3b0f7..b120197 100644
--- a/gcc/config/s390/s390.md
+++ b/gcc/config/s390/s390.md
@@ -7100,7 +7100,7 @@
(match_operand:SI 2 "general_operand"
" M,M,N0HSF,N1HSF,Os,d,d,R,T,NxxSq,NxQSF,Q")))
(clobber (reg:CC CC_REGNUM))]
- "TARGET_ZARCH && s390_logical_operator_ok_p (operands)"
+ "TARGET_ZARCH && s390_logical_operator_si3_ok_p (operands)"
"@
#
#
@@ -7234,6 +7234,52 @@
(set_attr "z10prop" "z10_super_E1,z10_super,*")])
;
+; And with complement
+;
+; c = ~b & a = (b & a) ^ a
+
+(define_insn_and_split "*andc_split"
+ [(set (match_operand:GPR 0 "nonimmediate_operand" "")
+ (and:GPR (not:GPR (match_operand:GPR 1 "nonimmediate_operand" ""))
+ (match_operand:GPR 2 "general_operand" "")))
+ (clobber (reg:CC CC_REGNUM))]
+ "TARGET_ZARCH && s390_andc_split_ok_p (operands)"
+ "#"
+ "&& 1"
+ [
+ (parallel
+ [(set (match_dup 3) (and:GPR (match_dup 1) (match_dup 2)))
+ (clobber (reg:CC CC_REGNUM))])
+ (parallel
+ [(set (match_dup 0) (xor:GPR (match_dup 3) (match_dup 2)))
+ (clobber (reg:CC CC_REGNUM))])]
+{
+ if (reg_overlap_mentioned_p (operands[0], operands[2]))
+ {
+ gcc_assert (can_create_pseudo_p ());
+ operands[3] = gen_reg_rtx (<MODE>mode);
+ }
+ else
+ operands[3] = operands[0];
+})
+
+; Convert "(xor (operand) (-1))" to "(not (operand))" for low optimization
+; levels so that "*andc_split" matches.
+(define_insn_and_split "*andc_split2"
+ [(set (match_operand:GPR 0 "nonimmediate_operand" "")
+ (and:GPR (xor:GPR (match_operand:GPR 1 "nonimmediate_operand" "")
+ (const_int -1))
+ (match_operand:GPR 2 "general_operand" "")))
+ (clobber (reg:CC CC_REGNUM))]
+ "TARGET_ZARCH && s390_andc_split_ok_p (operands)"
+ "#"
+ "&& 1"
+ [(parallel
+ [(set (match_dup 0) (and:GPR (not:GPR (match_dup 1)) (match_dup 2)))
+ (clobber (reg:CC CC_REGNUM))])]
+)
+
+;
; Block and (NC) patterns.
;
@@ -7429,7 +7475,7 @@
(ior:SI (match_operand:SI 1 "nonimmediate_operand" "%0, 0, 0,0,d,0,0, 0,0")
(match_operand:SI 2 "general_operand" "N0HS0,N1HS0,Os,d,d,R,T,NxQS0,Q")))
(clobber (reg:CC CC_REGNUM))]
- "TARGET_ZARCH && s390_logical_operator_ok_p (operands)"
+ "TARGET_ZARCH && s390_logical_operator_si3_ok_p (operands)"
"@
oilh\t%0,%i2
oill\t%0,%i2
@@ -7751,7 +7797,7 @@
(xor:SI (match_operand:SI 1 "nonimmediate_operand" "%0,0,d,0,0, 0,0")
(match_operand:SI 2 "general_operand" "Os,d,d,R,T,NxQS0,Q")))
(clobber (reg:CC CC_REGNUM))]
- "s390_logical_operator_ok_p (operands)"
+ "s390_logical_operator_si3_ok_p (operands)"
"@
xilf\t%0,%o2
xr\t%0,%2
diff --git a/gcc/testsuite/gcc.target/s390/md/andc-splitter-1.c b/gcc/testsuite/gcc.target/s390/md/andc-splitter-1.c
new file mode 100644
index 0000000..ed78921
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/md/andc-splitter-1.c
@@ -0,0 +1,61 @@
+/* Machine description pattern tests. */
+
+/* { dg-do run { target { lp64 } } } */
+/* { dg-options "-mzarch -save-temps -dP" } */
+/* Skip test if -O0 is present on the command line:
+
+ { dg-skip-if "" { *-*-* } { "-O0" } { "" } }
+
+ Skip test if the -O option is missing from the command line
+ { dg-skip-if "" { *-*-* } { "*" } { "-O*" } }
+*/
+
+__attribute__ ((noinline))
+unsigned long andc_vv(unsigned long a, unsigned long b)
+{ return ~b & a; }
+/* { dg-final { scan-assembler ":15 .\* \{\\*anddi3\}" } } */
+/* { dg-final { scan-assembler ":15 .\* \{\\*xordi3\}" } } */
+
+__attribute__ ((noinline))
+unsigned long andc_pv(unsigned long *a, unsigned long b)
+{ return ~b & *a; }
+/* { dg-final { scan-assembler ":21 .\* \{\\*anddi3\}" } } */
+/* { dg-final { scan-assembler ":21 .\* \{\\*xordi3\}" } } */
+
+__attribute__ ((noinline))
+unsigned long andc_vp(unsigned long a, unsigned long *b)
+{ return ~*b & a; }
+/* { dg-final { scan-assembler ":27 .\* \{\\*anddi3\}" } } */
+/* { dg-final { scan-assembler ":27 .\* \{\\*xordi3\}" } } */
+
+__attribute__ ((noinline))
+unsigned long andc_pp(unsigned long *a, unsigned long *b)
+{ return ~*b & *a; }
+/* { dg-final { scan-assembler ":33 .\* \{\\*anddi3\}" } } */
+/* { dg-final { scan-assembler ":33 .\* \{\\*xordi3\}" } } */
+
+/* { dg-final { scan-assembler-times "\tngr\?k\?\t" 4 } } */
+/* { dg-final { scan-assembler-times "\txgr\?\t" 4 } } */
+
+int
+main (void)
+{
+ unsigned long a = 0xc00000000000000cllu;
+ unsigned long b = 0x500000000000000allu;
+ unsigned long e = 0x8000000000000004llu;
+ unsigned long c;
+
+ c = andc_vv (a, b);
+ if (c != e)
+ __builtin_abort ();
+ c = andc_pv (&a, b);
+ if (c != e)
+ __builtin_abort ();
+ c = andc_vp (a, &b);
+ if (c != e)
+ __builtin_abort ();
+ c = andc_pp (&a, &b);
+ if (c != e)
+ __builtin_abort ();
+ return 0;
+}
diff --git a/gcc/testsuite/gcc.target/s390/md/andc-splitter-2.c b/gcc/testsuite/gcc.target/s390/md/andc-splitter-2.c
new file mode 100644
index 0000000..9e78335
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/md/andc-splitter-2.c
@@ -0,0 +1,38 @@
+/* Machine description pattern tests. */
+
+/* { dg-do compile } */
+/* { dg-options "-mzarch -save-temps -dP" } */
+/* Skip test if -O0 is present on the command line:
+
+ { dg-skip-if "" { *-*-* } { "-O0" } { "" } }
+
+ Skip test if the -O option is missing from the command line
+ { dg-skip-if "" { *-*-* } { "*" } { "-O*" } }
+*/
+
+__attribute__ ((noinline))
+unsigned int andc_vv(unsigned int a, unsigned int b)
+{ return ~b & a; }
+/* { dg-final { scan-assembler ":15 .\* \{\\*andsi3_zarch\}" } } */
+/* { dg-final { scan-assembler ":15 .\* \{\\*xorsi3\}" } } */
+
+__attribute__ ((noinline))
+unsigned int andc_pv(unsigned int *a, unsigned int b)
+{ return ~b & *a; }
+/* { dg-final { scan-assembler ":21 .\* \{\\*andsi3_zarch\}" } } */
+/* { dg-final { scan-assembler ":21 .\* \{\\*xorsi3\}" } } */
+
+__attribute__ ((noinline))
+unsigned int andc_vp(unsigned int a, unsigned int *b)
+{ return ~*b & a; }
+/* { dg-final { scan-assembler ":27 .\* \{\\*andsi3_zarch\}" } } */
+/* { dg-final { scan-assembler ":27 .\* \{\\*xorsi3\}" } } */
+
+__attribute__ ((noinline))
+unsigned int andc_pp(unsigned int *a, unsigned int *b)
+{ return ~*b & *a; }
+/* { dg-final { scan-assembler ":33 .\* \{\\*andsi3_zarch\}" } } */
+/* { dg-final { scan-assembler ":33 .\* \{\\*xorsi3\}" } } */
+
+/* { dg-final { scan-assembler-times "\tnr\?k\?\t" 4 } } */
+/* { dg-final { scan-assembler-times "\txr\?k\?\t" 4 } } */
--
2.3.0
