Hi,
This patch enables vector compare for 16-byte memory equality compare.
The 16-byte memory equality compare can be efficiently implemented by
instruction "vcmpequb." It reduces one branch and one compare compared
with two 8-byte compare sequence.
16-byte vector compare is not enabled on 32bit sub-targets as TImode
hasn't been supported well on 32bit sub-targets.
Bootstrapped and tested on powerpc64-linux BE and LE with no regressions.
Thanks
Gui Haochen
ChangeLog
rs6000: Enable vector compare for 16-byte memory equality compare
gcc/
PR target/111449
* config/rs6000/altivec.md (cbranchti4): New expand pattern.
* config/rs6000/rs6000.cc (rs6000_generate_compare): Generate insn
sequence for TImode vector equality compare.
* config/rs6000/rs6000.h (MOVE_MAX_PIECES): Define.
(COMPARE_MAX_PIECES): Define.
gcc/testsuite/
PR target/111449
* gcc.target/powerpc/pr111449.c: New.
patch.diff
diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index e8a596fb7e9..99264235cbe 100644
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -2605,6 +2605,24 @@ (define_insn "altivec_vupklpx"
}
[(set_attr "type" "vecperm")])
+(define_expand "cbranchti4"
+ [(use (match_operator 0 "equality_operator"
+ [(match_operand:TI 1 "memory_operand")
+ (match_operand:TI 2 "memory_operand")]))
+ (use (match_operand 3))]
+ "VECTOR_UNIT_ALTIVEC_P (V16QImode)"
+{
+ rtx op1 = simplify_subreg (V16QImode, operands[1], TImode, 0);
+ rtx op2 = simplify_subreg (V16QImode, operands[2], TImode, 0);
+ operands[1] = force_reg (V16QImode, op1);
+ operands[2] = force_reg (V16QImode, op2);
+ rtx_code code = GET_CODE (operands[0]);
+ operands[0] = gen_rtx_fmt_ee (code, V16QImode, operands[1],
+ operands[2]);
+ rs6000_emit_cbranch (TImode, operands);
+ DONE;
+})
+
;; Compare vectors producing a vector result and a predicate, setting CR6 to
;; indicate a combined status
(define_insn "altivec_vcmpequ<VI_char>_p"
diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc
index efe9adce1f8..c6b935a64e7 100644
--- a/gcc/config/rs6000/rs6000.cc
+++ b/gcc/config/rs6000/rs6000.cc
@@ -15264,6 +15264,15 @@ rs6000_generate_compare (rtx cmp, machine_mode mode)
else
emit_insn (gen_stack_protect_testsi (compare_result, op0, op1b));
}
+ else if (mode == TImode)
+ {
+ gcc_assert (code == EQ || code == NE);
+
+ rtx result_vector = gen_reg_rtx (V16QImode);
+ compare_result = gen_rtx_REG (CCmode, CR6_REGNO);
+ emit_insn (gen_altivec_vcmpequb_p (result_vector, op0, op1));
+ code = (code == NE) ? GE : LT;
+ }
else
emit_insn (gen_rtx_SET (compare_result,
gen_rtx_COMPARE (comp_mode, op0, op1)));
diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index 3503614efbd..dc33bca0802 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -1730,6 +1730,8 @@ typedef struct rs6000_args
in one reasonably fast instruction. */
#define MOVE_MAX (! TARGET_POWERPC64 ? 4 : 8)
#define MAX_MOVE_MAX 8
+#define MOVE_MAX_PIECES (!TARGET_POWERPC64 ? 4 : 16)
+#define COMPARE_MAX_PIECES (!TARGET_POWERPC64 ? 4 : 16)
/* Nonzero if access to memory by bytes is no faster than for words.
Also nonzero if doing byte operations (specifically shifts) in registers
diff --git a/gcc/testsuite/gcc.target/powerpc/pr111449.c
b/gcc/testsuite/gcc.target/powerpc/pr111449.c
new file mode 100644
index 00000000000..ab9583f47bb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr111449.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-options "-maltivec -O2" } */
+/* { dg-require-effective-target has_arch_ppc64 } */
+
+/* Ensure vector comparison is used for 16-byte memory equality compare. */
+
+int compare (const char* s1, const char* s2)
+{
+ return __builtin_memcmp (s1, s2, 16) == 0;
+}
+
+/* { dg-final { scan-assembler-times {\mvcmpequb\M} 1 } } */
+/* { dg-final { scan-assembler-not {\mcmpd\M} } } */
