+2017-11-10 Michael Meissner <meissner@linux.vnet.ibm.com>
+
+ * config/rs6000/rs6000.md (bswaphi2_reg): On ISA 3.0 systems,
+ enable generating XXBRH if the value is in a vector register.
+ (bswapsi2_reg): On ISA 3.0 systems, enable generating XXBRW if the
+ value is in a vector register.
+ (bswapdi2_reg): On ISA 3.0 systems, always use XXBRD to do
+ register to register bswap64's instead of doing the GPR sequence
+ used on previous machines.
+ (bswapdi2_xxbrd): New insn.
+ (bswapdi2_reg): Disallow on ISA 3.0.
+ (register to register bswap64 splitter): Do not split the insn on
+ ISA 3.0 systems that use XXBRD.
+
2017-11-10 Martin Sebor <msebor@redhat.com>
PR c/81117
[(set_attr "type" "store")])
(define_insn_and_split "bswaphi2_reg"
- [(set (match_operand:HI 0 "gpc_reg_operand" "=&r")
+ [(set (match_operand:HI 0 "gpc_reg_operand" "=&r,wo")
(bswap:HI
- (match_operand:HI 1 "gpc_reg_operand" "r")))
- (clobber (match_scratch:SI 2 "=&r"))]
+ (match_operand:HI 1 "gpc_reg_operand" "r,wo")))
+ (clobber (match_scratch:SI 2 "=&r,X"))]
""
- "#"
- "reload_completed"
+ "@
+ #
+ xxbrh %x0,%x1"
+ "reload_completed && int_reg_operand (operands[0], HImode)"
[(set (match_dup 3)
(and:SI (lshiftrt:SI (match_dup 4)
(const_int 8))
operands[3] = simplify_gen_subreg (SImode, operands[0], HImode, 0);
operands[4] = simplify_gen_subreg (SImode, operands[1], HImode, 0);
}
- [(set_attr "length" "12")
- (set_attr "type" "*")])
+ [(set_attr "length" "12,4")
+ (set_attr "type" "*,vecperm")])
;; We are always BITS_BIG_ENDIAN, so the bit positions below in
;; zero_extract insns do not change for -mlittle.
(define_insn_and_split "bswapsi2_reg"
- [(set (match_operand:SI 0 "gpc_reg_operand" "=&r")
+ [(set (match_operand:SI 0 "gpc_reg_operand" "=&r,wo")
(bswap:SI
- (match_operand:SI 1 "gpc_reg_operand" "r")))]
+ (match_operand:SI 1 "gpc_reg_operand" "r,wo")))]
""
- "#"
- "reload_completed"
+ "@
+ #
+ xxbrw %x0,%x1"
+ "reload_completed && int_reg_operand (operands[0], SImode)"
[(set (match_dup 0) ; DABC
(rotate:SI (match_dup 1)
(const_int 24)))
(const_int 255))
(and:SI (match_dup 0)
(const_int -256))))]
- "")
+ ""
+ [(set_attr "length" "12,4")
+ (set_attr "type" "*,vecperm")])
;; On systems with LDBRX/STDBRX generate the loads/stores directly, just like
;; we do for L{H,W}BRX and ST{H,W}BRX above. If not, we have to generate more
emit_insn (gen_bswapdi2_load (dest, src));
else if (MEM_P (dest))
emit_insn (gen_bswapdi2_store (dest, src));
+ else if (TARGET_P9_VECTOR)
+ emit_insn (gen_bswapdi2_xxbrd (dest, src));
else
emit_insn (gen_bswapdi2_reg (dest, src));
DONE;
}
+ if (TARGET_P9_VECTOR && !MEM_P (src) && !MEM_P (dest))
+ {
+ emit_insn (gen_bswapdi2_xxbrd (dest, src));
+ DONE;
+ }
+
if (!TARGET_POWERPC64)
{
/* 32-bit mode needs fewer scratch registers, but 32-bit addressing mode
"stdbrx %1,%y0"
[(set_attr "type" "store")])
+(define_insn "bswapdi2_xxbrd"
+ [(set (match_operand:DI 0 "gpc_reg_operand" "=wo")
+ (bswap:DI (match_operand:DI 1 "gpc_reg_operand" "wo")))]
+ "TARGET_P9_VECTOR"
+ "xxbrd %x0,%x1"
+ [(set_attr "type" "vecperm")])
+
(define_insn "bswapdi2_reg"
[(set (match_operand:DI 0 "gpc_reg_operand" "=&r")
(bswap:DI (match_operand:DI 1 "gpc_reg_operand" "r")))
(clobber (match_scratch:DI 2 "=&r"))
(clobber (match_scratch:DI 3 "=&r"))]
- "TARGET_POWERPC64 && TARGET_LDBRX"
+ "TARGET_POWERPC64 && TARGET_LDBRX && !TARGET_P9_VECTOR"
"#"
[(set_attr "length" "36")])
(bswap:DI (match_operand:DI 1 "gpc_reg_operand" "")))
(clobber (match_operand:DI 2 "gpc_reg_operand" ""))
(clobber (match_operand:DI 3 "gpc_reg_operand" ""))]
- "TARGET_POWERPC64 && reload_completed"
+ "TARGET_POWERPC64 && !TARGET_P9_VECTOR && reload_completed"
[(const_int 0)]
"
{
--- /dev/null
+/* { dg-do compile { target { powerpc*-*-* && lp64 } } } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mpower9-vector -O2" } */
+
+/* Verify that the XXBR{H,W} instructions are generated if the value is
+ forced to be in a vector register, and XXBRD is generated all of the
+ time for register bswap64's. */
+
+unsigned short
+do_bswap16_mem (unsigned short *p)
+{
+ return __builtin_bswap16 (*p); /* LHBRX. */
+}
+
+unsigned short
+do_bswap16_reg (unsigned short a)
+{
+ return __builtin_bswap16 (a); /* gpr sequences. */
+}
+
+void
+do_bswap16_store (unsigned short *p, unsigned short a)
+{
+ *p = __builtin_bswap16 (a); /* STHBRX. */
+}
+
+unsigned short
+do_bswap16_vect (unsigned short a)
+{
+ __asm__ (" # %x0" : "+v" (a));
+ return __builtin_bswap16 (a); /* XXBRW. */
+}
+
+unsigned int
+do_bswap32_mem (unsigned int *p)
+{
+ return __builtin_bswap32 (*p); /* LWBRX. */
+}
+
+unsigned int
+do_bswap32_reg (unsigned int a)
+{
+ return __builtin_bswap32 (a); /* gpr sequences. */
+}
+
+void
+do_bswap32_store (unsigned int *p, unsigned int a)
+{
+ *p = __builtin_bswap32 (a); /* STWBRX. */
+}
+
+unsigned int
+do_bswap32_vect (unsigned int a)
+{
+ __asm__ (" # %x0" : "+v" (a));
+ return __builtin_bswap32 (a); /* XXBRW. */
+}
+
+unsigned long
+do_bswap64_mem (unsigned long *p)
+{
+ return __builtin_bswap64 (*p); /* LDBRX. */
+}
+
+unsigned long
+do_bswap64_reg (unsigned long a)
+{
+ return __builtin_bswap64 (a); /* gpr sequences. */
+}
+
+void
+do_bswap64_store (unsigned long *p, unsigned int a)
+{
+ *p = __builtin_bswap64 (a); /* STDBRX. */
+}
+
+double
+do_bswap64_double (unsigned long a)
+{
+ return (double) __builtin_bswap64 (a); /* XXBRD. */
+}
+
+unsigned long
+do_bswap64_vect (unsigned long a)
+{
+ __asm__ (" # %x0" : "+v" (a)); /* XXBRD. */
+ return __builtin_bswap64 (a);
+}
+
+/* Make sure XXBR{H,W,D} is not generated by default. */
+/* { dg-final { scan-assembler-times "xxbrd" 3 } } */
+/* { dg-final { scan-assembler-times "xxbrh" 1 } } */
+/* { dg-final { scan-assembler-times "xxbrw" 1 } } */
+/* { dg-final { scan-assembler-times "ldbrx" 1 } } */
+/* { dg-final { scan-assembler-times "lhbrx" 1 } } */
+/* { dg-final { scan-assembler-times "lwbrx" 1 } } */
+/* { dg-final { scan-assembler-times "stdbrx" 1 } } */
+/* { dg-final { scan-assembler-times "sthbrx" 1 } } */
+/* { dg-final { scan-assembler-times "stwbrx" 1 } } */
projects / gcc.git / commitdiff