===================================================================
@@ -78,7 +78,7 @@
extern int expand_block_clear (rtx[]);
extern int expand_block_move (rtx[]);
extern bool expand_block_compare (rtx[]);
-extern bool expand_strn_compare (rtx[]);
+extern bool expand_strn_compare (rtx[], int);
extern const char * rs6000_output_load_multiple (rtx[]);
extern bool rs6000_is_valid_mask (rtx, int *, int *, machine_mode);
extern bool rs6000_is_valid_and_mask (rtx, machine_mode);
===================================================================
@@ -19635,22 +19635,36 @@
OPERANDS[0] is the target (result).
OPERANDS[1] is the first source.
OPERANDS[2] is the second source.
+ If NO_LENGTH is zero, then:
OPERANDS[3] is the length.
- OPERANDS[4] is the alignment in bytes. */
+ OPERANDS[4] is the alignment in bytes.
+ If NO_LENGTH is nonzero, then:
+ OPERANDS[3] is the alignment in bytes. */
bool
-expand_strn_compare (rtx operands[])
+expand_strn_compare (rtx operands[], int no_length)
{
rtx target = operands[0];
rtx orig_src1 = operands[1];
rtx orig_src2 = operands[2];
- rtx bytes_rtx = operands[3];
- rtx align_rtx = operands[4];
+ rtx bytes_rtx, align_rtx;
+ if (no_length)
+ {
+ bytes_rtx = NULL;
+ align_rtx = operands[3];
+ }
+ else
+ {
+ bytes_rtx = operands[3];
+ align_rtx = operands[4];
+ }
HOST_WIDE_INT cmp_bytes = 0;
rtx src1 = orig_src1;
rtx src2 = orig_src2;
- /* If this is not a fixed size compare, just call strncmp. */
- if (!CONST_INT_P (bytes_rtx))
+ /* If we have a length, it must be constant. This simplifies things
+ a bit as we don't have to generate code to check if we've exceeded
+ the length. Later this could be expanded to handle this case. */
+ if (!no_length && !CONST_INT_P (bytes_rtx))
return false;
/* This must be a fixed size alignment. */
@@ -19668,8 +19682,6 @@
gcc_assert (GET_MODE (target) == SImode);
- HOST_WIDE_INT bytes = INTVAL (bytes_rtx);
-
/* If we have an LE target without ldbrx and word_mode is DImode,
then we must avoid using word_mode. */
int word_mode_ok = !(!BYTES_BIG_ENDIAN && !TARGET_LDBRX
@@ -19678,16 +19690,37 @@
int word_mode_size = GET_MODE_SIZE (word_mode);
int offset = 0;
+ HOST_WIDE_INT bytes; /* N from the strncmp args if available. */
+ HOST_WIDE_INT compare_length; /* How much we are going to compare inline. */
+ if (no_length)
+ /* Use this as a standin to determine the mode to use. */
+ bytes = rs6000_string_compare_inline_limit * word_mode_size;
+ else
+ bytes = INTVAL (bytes_rtx);
+
machine_mode load_mode =
select_block_compare_mode (offset, bytes, base_align, word_mode_ok);
int load_mode_size = GET_MODE_SIZE (load_mode);
+ compare_length = rs6000_string_compare_inline_limit * load_mode_size;
- /* We don't want to generate too much code. Also if bytes is
- 4096 or larger we always want the library strncmp anyway. */
- int groups = ROUND_UP (bytes, load_mode_size) / load_mode_size;
- if (bytes >= 4096 || groups > rs6000_string_compare_inline_limit)
- return false;
+ /* If we have equality at the end of the last compare and we have not
+ found the end of the string, we need to call strcmp/strncmp to
+ compare the remainder. */
+ bool equality_compare_rest = false;
+ if (no_length)
+ {
+ bytes = compare_length;
+ equality_compare_rest = true;
+ }
+ else
+ {
+ if (bytes <= compare_length)
+ compare_length = bytes;
+ else
+ equality_compare_rest = true;
+ }
+
rtx result_reg = gen_reg_rtx (word_mode);
rtx final_move_label = gen_label_rtx ();
rtx final_label = gen_label_rtx ();
@@ -19706,9 +19739,9 @@
bgt cr7,L(pagecross) */
if (align1 < 8)
- expand_strncmp_align_check (strncmp_label, src1, bytes);
+ expand_strncmp_align_check (strncmp_label, src1, compare_length);
if (align2 < 8)
- expand_strncmp_align_check (strncmp_label, src2, bytes);
+ expand_strncmp_align_check (strncmp_label, src2, compare_length);
/* Now generate the following sequence:
- branch to begin_compare
@@ -19737,22 +19770,30 @@
src2 = replace_equiv_address (src2, src2_reg);
}
- /* -m32 -mpowerpc64 results in word_mode being DImode even
- though otherwise it is 32-bit. The length arg to strncmp
- is a size_t which will be the same size as pointers. */
- rtx len_rtx;
- if (TARGET_64BIT)
- len_rtx = gen_reg_rtx(DImode);
+ if (no_length)
+ emit_library_call_value (gen_rtx_SYMBOL_REF (Pmode, "strcmp"),
+ target, LCT_NORMAL, GET_MODE (target), 2,
+ force_reg (Pmode, XEXP (src1, 0)), Pmode,
+ force_reg (Pmode, XEXP (src2, 0)), Pmode);
else
- len_rtx = gen_reg_rtx(SImode);
+ {
+ /* -m32 -mpowerpc64 results in word_mode being DImode even
+ though otherwise it is 32-bit. The length arg to strncmp
+ is a size_t which will be the same size as pointers. */
+ rtx len_rtx;
+ if (TARGET_64BIT)
+ len_rtx = gen_reg_rtx(DImode);
+ else
+ len_rtx = gen_reg_rtx(SImode);
- emit_move_insn (len_rtx, bytes_rtx);
+ emit_move_insn (len_rtx, bytes_rtx);
- emit_library_call_value (gen_rtx_SYMBOL_REF (Pmode, "strncmp"),
- target, LCT_NORMAL, GET_MODE (target), 3,
- force_reg (Pmode, XEXP (src1, 0)), Pmode,
- force_reg (Pmode, XEXP (src2, 0)), Pmode,
- len_rtx, GET_MODE (len_rtx));
+ emit_library_call_value (gen_rtx_SYMBOL_REF (Pmode, "strncmp"),
+ target, LCT_NORMAL, GET_MODE (target), 3,
+ force_reg (Pmode, XEXP (src1, 0)), Pmode,
+ force_reg (Pmode, XEXP (src2, 0)), Pmode,
+ len_rtx, GET_MODE (len_rtx));
+ }
rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
jmp = emit_jump_insn (gen_rtx_SET (pc_rtx, fin_ref));
@@ -19768,10 +19809,12 @@
/* Generate sequence of ld/ldbrx, cmpb to compare out
to the length specified. */
- while (bytes > 0)
+ HOST_WIDE_INT bytes_to_compare = compare_length;
+ while (bytes_to_compare > 0)
{
/* Compare sequence:
check each 8B with: ld/ld cmpd bne
+ If equal, use rldicr/cmpb to check for zero byte.
cleanup code at end:
cmpb get byte that differs
cmpb look for zero byte
@@ -19785,24 +19828,25 @@
result is zero because the strings are exactly equal. */
int align = compute_current_alignment (base_align, offset);
if (TARGET_EFFICIENT_OVERLAPPING_UNALIGNED)
- load_mode = select_block_compare_mode (offset, bytes, align,
+ load_mode = select_block_compare_mode (offset, bytes_to_compare, align,
word_mode_ok);
else
- load_mode = select_block_compare_mode (0, bytes, align, word_mode_ok);
+ load_mode = select_block_compare_mode (0, bytes_to_compare, align,
+ word_mode_ok);
load_mode_size = GET_MODE_SIZE (load_mode);
- if (bytes >= load_mode_size)
+ if (bytes_to_compare >= load_mode_size)
cmp_bytes = load_mode_size;
else if (TARGET_EFFICIENT_OVERLAPPING_UNALIGNED)
{
/* Move this load back so it doesn't go past the end.
P8/P9 can do this efficiently. */
- int extra_bytes = load_mode_size - bytes;
- cmp_bytes = bytes;
+ int extra_bytes = load_mode_size - bytes_to_compare;
+ cmp_bytes = bytes_to_compare;
if (extra_bytes < offset)
{
offset -= extra_bytes;
cmp_bytes = load_mode_size;
- bytes = cmp_bytes;
+ bytes_to_compare = cmp_bytes;
}
}
else
@@ -19809,7 +19853,7 @@
/* P7 and earlier can't do the overlapping load trick fast,
so this forces a non-overlapping load and a shift to get
rid of the extra bytes. */
- cmp_bytes = bytes;
+ cmp_bytes = bytes_to_compare;
src1 = adjust_address (orig_src1, load_mode, offset);
src2 = adjust_address (orig_src2, load_mode, offset);
@@ -19872,37 +19916,45 @@
}
}
- int remain = bytes - cmp_bytes;
+ /* Cases to handle. A and B are chunks of the two strings.
+ 1: Not end of comparison:
+ A != B: branch to cleanup code to compute result.
+ A == B: check for 0 byte, next block if not found.
+ 2: End of the inline comparison:
+ A != B: branch to cleanup code to compute result.
+ A == B: check for 0 byte, call strcmp/strncmp
+ 3: compared requested N bytes:
+ A == B: branch to result 0.
+ A != B: cleanup code to compute result. */
+ int remain = bytes_to_compare - cmp_bytes;
+
rtx dst_label;
- if (remain > 0)
+ if (remain > 0 || equality_compare_rest)
{
+ /* Branch to cleanup code, otherwise fall through to do
+ more compares. */
if (!cleanup_label)
cleanup_label = gen_label_rtx ();
dst_label = cleanup_label;
}
else
+ /* Branch to end and produce result of 0. */
dst_label = final_move_label;
rtx lab_ref = gen_rtx_LABEL_REF (VOIDmode, dst_label);
rtx cond = gen_reg_rtx (CCmode);
- if (remain == 0)
- {
- /* For the last chunk, subf. also
- generates the zero result we need. */
- rtx tmp = gen_rtx_MINUS (word_mode, tmp_reg_src1, tmp_reg_src2);
- rs6000_emit_dot_insn (result_reg, tmp, 1, cond);
- }
- else
- emit_move_insn (cond, gen_rtx_COMPARE (CCmode,
- tmp_reg_src1, tmp_reg_src2));
+ /* Always produce the 0 result, it is needed if
+ cmpb finds a 0 byte in this chunk. */
+ rtx tmp = gen_rtx_MINUS (word_mode, tmp_reg_src1, tmp_reg_src2);
+ rs6000_emit_dot_insn (result_reg, tmp, 1, cond);
rtx cmp_rtx;
- if (remain > 0)
+ if (remain == 0 && !equality_compare_rest)
+ cmp_rtx = gen_rtx_EQ (VOIDmode, cond, const0_rtx);
+ else
cmp_rtx = gen_rtx_NE (VOIDmode, cond, const0_rtx);
- else
- cmp_rtx = gen_rtx_EQ (VOIDmode, cond, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp_rtx,
lab_ref, pc_rtx);
@@ -19910,10 +19962,104 @@
JUMP_LABEL (j) = dst_label;
LABEL_NUSES (dst_label) += 1;
+ if (remain > 0 || equality_compare_rest)
+ {
+ /* Generate a cmpb to test for a 0 byte and branch
+ to final result if found. */
+ rtx cmpb_zero = gen_reg_rtx (word_mode);
+ rtx lab_ref_fin = gen_rtx_LABEL_REF (VOIDmode, final_move_label);
+ rtx condz = gen_reg_rtx (CCmode);
+ rtx zero_reg = gen_reg_rtx (word_mode);
+ if (word_mode == SImode)
+ {
+ emit_insn (gen_movsi (zero_reg, GEN_INT(0)));
+ emit_insn (gen_cmpbsi3 (cmpb_zero, tmp_reg_src1, zero_reg));
+ if ( cmp_bytes < word_mode_size )
+ { /* Don't want to look at zero bytes past end. */
+ HOST_WIDE_INT mb =
+ BITS_PER_UNIT * (word_mode_size - cmp_bytes);
+ rtx mask = GEN_INT (HOST_WIDE_INT_M1U << mb);
+ emit_insn (gen_andsi3_mask (cmpb_zero, cmpb_zero, mask));
+ }
+ }
+ else
+ {
+ emit_insn (gen_movdi (zero_reg, GEN_INT(0)));
+ emit_insn (gen_cmpbdi3 (cmpb_zero, tmp_reg_src1, zero_reg));
+ if ( cmp_bytes < word_mode_size )
+ { /* Don't want to look at zero bytes past end. */
+ HOST_WIDE_INT mb =
+ BITS_PER_UNIT * (word_mode_size - cmp_bytes);
+ rtx mask = GEN_INT (HOST_WIDE_INT_M1U << mb);
+ emit_insn (gen_anddi3_mask (cmpb_zero, cmpb_zero, mask));
+ }
+ }
+
+ emit_move_insn (condz, gen_rtx_COMPARE (CCmode, cmpb_zero, zero_reg));
+ rtx cmpnz_rtx = gen_rtx_NE (VOIDmode, condz, const0_rtx);
+ rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmpnz_rtx,
+ lab_ref_fin, pc_rtx);
+ rtx j2 = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
+ JUMP_LABEL (j2) = final_move_label;
+ LABEL_NUSES (final_move_label) += 1;
+
+ }
+
offset += cmp_bytes;
- bytes -= cmp_bytes;
+ bytes_to_compare -= cmp_bytes;
}
+ if (equality_compare_rest)
+ {
+ /* Update pointers past what has been compared already. */
+ src1 = adjust_address (orig_src1, load_mode, offset);
+ src2 = adjust_address (orig_src2, load_mode, offset);
+
+ if (!REG_P (XEXP (src1, 0)))
+ {
+ rtx src1_reg = copy_addr_to_reg (XEXP (src1, 0));
+ src1 = replace_equiv_address (src1, src1_reg);
+ }
+ set_mem_size (src1, cmp_bytes);
+
+ if (!REG_P (XEXP (src2, 0)))
+ {
+ rtx src2_reg = copy_addr_to_reg (XEXP (src2, 0));
+ src2 = replace_equiv_address (src2, src2_reg);
+ }
+ set_mem_size (src2, cmp_bytes);
+
+ /* Construct call to strcmp/strncmp to compare the rest of the string. */
+ if (no_length)
+ emit_library_call_value (gen_rtx_SYMBOL_REF (Pmode, "strcmp"),
+ target, LCT_NORMAL, GET_MODE (target), 2,
+ force_reg (Pmode, XEXP (src1, 0)), Pmode,
+ force_reg (Pmode, XEXP (src2, 0)), Pmode);
+ else
+ {
+ rtx len_rtx;
+ if (TARGET_64BIT)
+ len_rtx = gen_reg_rtx(DImode);
+ else
+ len_rtx = gen_reg_rtx(SImode);
+
+ rtx len_remain = gen_rtx_MINUS (GET_MODE (len_rtx),
+ bytes_rtx, GEN_INT (bytes_to_compare));
+ emit_move_insn (len_rtx, len_remain);
+ emit_library_call_value (gen_rtx_SYMBOL_REF (Pmode, "strncmp"),
+ target, LCT_NORMAL, GET_MODE (target), 3,
+ force_reg (Pmode, XEXP (src1, 0)), Pmode,
+ force_reg (Pmode, XEXP (src2, 0)), Pmode,
+ len_rtx, GET_MODE (len_rtx));
+ }
+
+ rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
+ rtx jmp = emit_jump_insn (gen_rtx_SET (pc_rtx, fin_ref));
+ JUMP_LABEL (jmp) = final_label;
+ LABEL_NUSES (final_label) += 1;
+ emit_barrier ();
+ }
+
if (cleanup_label)
emit_label (cleanup_label);
===================================================================
@@ -9106,12 +9106,31 @@
(use (match_operand:SI 4))])]
"TARGET_CMPB && (BYTES_BIG_ENDIAN || TARGET_LDBRX)"
{
- if (expand_strn_compare (operands))
+ if (expand_strn_compare (operands, 0))
DONE;
else
FAIL;
})
+;; String compare insn.
+;; Argument 0 is the target (result)
+;; Argument 1 is the destination
+;; Argument 2 is the source
+;; Argument 3 is the alignment
+
+(define_expand "cmpstrsi"
+ [(parallel [(set (match_operand:SI 0)
+ (compare:SI (match_operand:BLK 1)
+ (match_operand:BLK 2)))
+ (use (match_operand:SI 3))])]
+ "TARGET_CMPB && (BYTES_BIG_ENDIAN || TARGET_LDBRX)"
+{
+ if (expand_strn_compare (operands, 1))
+ DONE;
+ else
+ FAIL;
+})
+
;; Block compare insn.
;; Argument 0 is the target (result)
;; Argument 1 is the destination
===================================================================
@@ -0,0 +1,635 @@
+/* Test strcmp builtin expansion for compilation and proper execution. */
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+/* { dg-require-effective-target ptr32plus } */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#define RUN_TEST(SZ, ALIGN) test_strcmp_ ## SZ ## _ ## ALIGN ()
+
+#define DEF_TEST(SZ, ALIGN) \
+static void test_strcmp_ ## SZ ## _ ## ALIGN (void) { \
+ char one[3 * (SZ > 10 ? SZ : 10)]; \
+ char two[3 * (SZ > 10 ? SZ : 10)]; \
+ char three[8192] __attribute__ ((aligned (4096))); \
+ char four[8192] __attribute__ ((aligned (4096))); \
+ int i,j; \
+ memset(one,0,sizeof(one)); \
+ memset(two,0,sizeof(two)); \
+ memset(three,0,sizeof(three)); \
+ memset(four,0,sizeof(four)); \
+ for (i = 0 ; i < SZ ; i++) \
+ { \
+ int r1; \
+ char *a = one + (i & 1) * ALIGN; \
+ char *b = two + (i & 1) * ALIGN; \
+ memset(a, '-', SZ); \
+ memset(b, '-', SZ); \
+ a[i] = '1'; \
+ b[i] = '2'; \
+ a[SZ] = 0; \
+ b[SZ] = 0; \
+ if (!((r1 = strcmp (b, a)) > 0)) \
+ abort (); \
+ if (!((r1 = strcmp (a, b)) < 0)) \
+ abort (); \
+ b[i] = '1'; \
+ if (!((r1 = strcmp (a, b)) == 0)) \
+ abort (); \
+ for(j = i; j < SZ ; j++) \
+ { \
+ a[j] = '1'; \
+ b[j] = '2'; \
+ } \
+ if (!((r1 = strcmp (b, a)) > 0)) \
+ abort (); \
+ if (!((r1 = strcmp (a, b)) < 0)) \
+ abort (); \
+ for(j = 0; j < i ; j++) \
+ { \
+ memset(a, '-', SZ); \
+ memset(b, '-', SZ); \
+ a[j] = '\0'; \
+ a[j+1] = '1'; \
+ b[j] = '\0'; \
+ b[j+1] = '2'; \
+ if ((r1 = strcmp (b, a)) != 0) \
+ abort (); \
+ } \
+ a = three + 4096 - (SZ / 2 + (i & 1) * ALIGN); \
+ b = four + 4096 - (SZ / 2 + (i & 1) * ALIGN); \
+ memset(a, '-', SZ); \
+ memset(b, '-', SZ); \
+ a[i] = '1'; \
+ b[i] = '2'; \
+ a[SZ] = 0; \
+ b[SZ] = 0; \
+ if (!((r1 = strcmp(b, a)) > 0)) \
+ abort (); \
+ if (!((r1 = strcmp(a, b)) < 0)) \
+ abort (); \
+ b[i] = '1'; \
+ if (!((r1 = strcmp(a, b)) == 0)) \
+ abort (); \
+ } \
+}
+
+#ifdef TEST_ALL
+DEF_TEST(1,1)
+DEF_TEST(1,2)
+DEF_TEST(1,4)
+DEF_TEST(1,8)
+DEF_TEST(1,16)
+DEF_TEST(2,1)
+DEF_TEST(2,2)
+DEF_TEST(2,4)
+DEF_TEST(2,8)
+DEF_TEST(2,16)
+DEF_TEST(3,1)
+DEF_TEST(3,2)
+DEF_TEST(3,4)
+DEF_TEST(3,8)
+DEF_TEST(3,16)
+DEF_TEST(4,1)
+DEF_TEST(4,2)
+DEF_TEST(4,4)
+DEF_TEST(4,8)
+DEF_TEST(4,16)
+DEF_TEST(5,1)
+DEF_TEST(5,2)
+DEF_TEST(5,4)
+DEF_TEST(5,8)
+DEF_TEST(5,16)
+DEF_TEST(6,1)
+DEF_TEST(6,2)
+DEF_TEST(6,4)
+DEF_TEST(6,8)
+DEF_TEST(6,16)
+DEF_TEST(7,1)
+DEF_TEST(7,2)
+DEF_TEST(7,4)
+DEF_TEST(7,8)
+DEF_TEST(7,16)
+DEF_TEST(8,1)
+DEF_TEST(8,2)
+DEF_TEST(8,4)
+DEF_TEST(8,8)
+DEF_TEST(8,16)
+DEF_TEST(9,1)
+DEF_TEST(9,2)
+DEF_TEST(9,4)
+DEF_TEST(9,8)
+DEF_TEST(9,16)
+DEF_TEST(10,1)
+DEF_TEST(10,2)
+DEF_TEST(10,4)
+DEF_TEST(10,8)
+DEF_TEST(10,16)
+DEF_TEST(11,1)
+DEF_TEST(11,2)
+DEF_TEST(11,4)
+DEF_TEST(11,8)
+DEF_TEST(11,16)
+DEF_TEST(12,1)
+DEF_TEST(12,2)
+DEF_TEST(12,4)
+DEF_TEST(12,8)
+DEF_TEST(12,16)
+DEF_TEST(13,1)
+DEF_TEST(13,2)
+DEF_TEST(13,4)
+DEF_TEST(13,8)
+DEF_TEST(13,16)
+DEF_TEST(14,1)
+DEF_TEST(14,2)
+DEF_TEST(14,4)
+DEF_TEST(14,8)
+DEF_TEST(14,16)
+DEF_TEST(15,1)
+DEF_TEST(15,2)
+DEF_TEST(15,4)
+DEF_TEST(15,8)
+DEF_TEST(15,16)
+DEF_TEST(16,1)
+DEF_TEST(16,2)
+DEF_TEST(16,4)
+DEF_TEST(16,8)
+DEF_TEST(16,16)
+DEF_TEST(17,1)
+DEF_TEST(17,2)
+DEF_TEST(17,4)
+DEF_TEST(17,8)
+DEF_TEST(17,16)
+DEF_TEST(18,1)
+DEF_TEST(18,2)
+DEF_TEST(18,4)
+DEF_TEST(18,8)
+DEF_TEST(18,16)
+DEF_TEST(19,1)
+DEF_TEST(19,2)
+DEF_TEST(19,4)
+DEF_TEST(19,8)
+DEF_TEST(19,16)
+DEF_TEST(20,1)
+DEF_TEST(20,2)
+DEF_TEST(20,4)
+DEF_TEST(20,8)
+DEF_TEST(20,16)
+DEF_TEST(21,1)
+DEF_TEST(21,2)
+DEF_TEST(21,4)
+DEF_TEST(21,8)
+DEF_TEST(21,16)
+DEF_TEST(22,1)
+DEF_TEST(22,2)
+DEF_TEST(22,4)
+DEF_TEST(22,8)
+DEF_TEST(22,16)
+DEF_TEST(23,1)
+DEF_TEST(23,2)
+DEF_TEST(23,4)
+DEF_TEST(23,8)
+DEF_TEST(23,16)
+DEF_TEST(24,1)
+DEF_TEST(24,2)
+DEF_TEST(24,4)
+DEF_TEST(24,8)
+DEF_TEST(24,16)
+DEF_TEST(25,1)
+DEF_TEST(25,2)
+DEF_TEST(25,4)
+DEF_TEST(25,8)
+DEF_TEST(25,16)
+DEF_TEST(26,1)
+DEF_TEST(26,2)
+DEF_TEST(26,4)
+DEF_TEST(26,8)
+DEF_TEST(26,16)
+DEF_TEST(27,1)
+DEF_TEST(27,2)
+DEF_TEST(27,4)
+DEF_TEST(27,8)
+DEF_TEST(27,16)
+DEF_TEST(28,1)
+DEF_TEST(28,2)
+DEF_TEST(28,4)
+DEF_TEST(28,8)
+DEF_TEST(28,16)
+DEF_TEST(29,1)
+DEF_TEST(29,2)
+DEF_TEST(29,4)
+DEF_TEST(29,8)
+DEF_TEST(29,16)
+DEF_TEST(30,1)
+DEF_TEST(30,2)
+DEF_TEST(30,4)
+DEF_TEST(30,8)
+DEF_TEST(30,16)
+DEF_TEST(31,1)
+DEF_TEST(31,2)
+DEF_TEST(31,4)
+DEF_TEST(31,8)
+DEF_TEST(31,16)
+DEF_TEST(32,1)
+DEF_TEST(32,2)
+DEF_TEST(32,4)
+DEF_TEST(32,8)
+DEF_TEST(32,16)
+DEF_TEST(33,1)
+DEF_TEST(33,2)
+DEF_TEST(33,4)
+DEF_TEST(33,8)
+DEF_TEST(33,16)
+DEF_TEST(34,1)
+DEF_TEST(34,2)
+DEF_TEST(34,4)
+DEF_TEST(34,8)
+DEF_TEST(34,16)
+DEF_TEST(35,1)
+DEF_TEST(35,2)
+DEF_TEST(35,4)
+DEF_TEST(35,8)
+DEF_TEST(35,16)
+DEF_TEST(36,1)
+DEF_TEST(36,2)
+DEF_TEST(36,4)
+DEF_TEST(36,8)
+DEF_TEST(36,16)
+DEF_TEST(37,1)
+DEF_TEST(37,2)
+DEF_TEST(37,4)
+DEF_TEST(37,8)
+DEF_TEST(37,16)
+DEF_TEST(38,1)
+DEF_TEST(38,2)
+DEF_TEST(38,4)
+DEF_TEST(38,8)
+DEF_TEST(38,16)
+DEF_TEST(39,1)
+DEF_TEST(39,2)
+DEF_TEST(39,4)
+DEF_TEST(39,8)
+DEF_TEST(39,16)
+DEF_TEST(40,1)
+DEF_TEST(40,2)
+DEF_TEST(40,4)
+DEF_TEST(40,8)
+DEF_TEST(40,16)
+DEF_TEST(41,1)
+DEF_TEST(41,2)
+DEF_TEST(41,4)
+DEF_TEST(41,8)
+DEF_TEST(41,16)
+DEF_TEST(42,1)
+DEF_TEST(42,2)
+DEF_TEST(42,4)
+DEF_TEST(42,8)
+DEF_TEST(42,16)
+DEF_TEST(43,1)
+DEF_TEST(43,2)
+DEF_TEST(43,4)
+DEF_TEST(43,8)
+DEF_TEST(43,16)
+DEF_TEST(44,1)
+DEF_TEST(44,2)
+DEF_TEST(44,4)
+DEF_TEST(44,8)
+DEF_TEST(44,16)
+DEF_TEST(45,1)
+DEF_TEST(45,2)
+DEF_TEST(45,4)
+DEF_TEST(45,8)
+DEF_TEST(45,16)
+DEF_TEST(46,1)
+DEF_TEST(46,2)
+DEF_TEST(46,4)
+DEF_TEST(46,8)
+DEF_TEST(46,16)
+DEF_TEST(47,1)
+DEF_TEST(47,2)
+DEF_TEST(47,4)
+DEF_TEST(47,8)
+DEF_TEST(47,16)
+DEF_TEST(48,1)
+DEF_TEST(48,2)
+DEF_TEST(48,4)
+DEF_TEST(48,8)
+DEF_TEST(48,16)
+DEF_TEST(49,1)
+DEF_TEST(49,2)
+DEF_TEST(49,4)
+DEF_TEST(49,8)
+DEF_TEST(49,16)
+DEF_TEST(100,1)
+DEF_TEST(100,2)
+DEF_TEST(100,4)
+DEF_TEST(100,8)
+DEF_TEST(100,16)
+#else
+DEF_TEST(3,1)
+DEF_TEST(4,1)
+DEF_TEST(4,2)
+DEF_TEST(4,4)
+DEF_TEST(5,1)
+DEF_TEST(6,1)
+DEF_TEST(7,1)
+DEF_TEST(8,1)
+DEF_TEST(8,2)
+DEF_TEST(8,4)
+DEF_TEST(8,8)
+DEF_TEST(9,1)
+DEF_TEST(16,1)
+DEF_TEST(16,2)
+DEF_TEST(16,4)
+DEF_TEST(16,8)
+DEF_TEST(16,16)
+DEF_TEST(32,1)
+DEF_TEST(32,2)
+DEF_TEST(32,4)
+DEF_TEST(32,8)
+DEF_TEST(32,16)
+DEF_TEST(100,1)
+DEF_TEST(100,2)
+DEF_TEST(100,4)
+DEF_TEST(100,8)
+DEF_TEST(100,16)
+#endif
+
+int
+main(int argc, char **argv)
+{
+
+#ifdef TEST_ALL
+ RUN_TEST(1,1);
+ RUN_TEST(1,2);
+ RUN_TEST(1,4);
+ RUN_TEST(1,8);
+ RUN_TEST(1,16);
+ RUN_TEST(2,1);
+ RUN_TEST(2,2);
+ RUN_TEST(2,4);
+ RUN_TEST(2,8);
+ RUN_TEST(2,16);
+ RUN_TEST(3,1);
+ RUN_TEST(3,2);
+ RUN_TEST(3,4);
+ RUN_TEST(3,8);
+ RUN_TEST(3,16);
+ RUN_TEST(4,1);
+ RUN_TEST(4,2);
+ RUN_TEST(4,4);
+ RUN_TEST(4,8);
+ RUN_TEST(4,16);
+ RUN_TEST(5,1);
+ RUN_TEST(5,2);
+ RUN_TEST(5,4);
+ RUN_TEST(5,8);
+ RUN_TEST(5,16);
+ RUN_TEST(6,1);
+ RUN_TEST(6,2);
+ RUN_TEST(6,4);
+ RUN_TEST(6,8);
+ RUN_TEST(6,16);
+ RUN_TEST(7,1);
+ RUN_TEST(7,2);
+ RUN_TEST(7,4);
+ RUN_TEST(7,8);
+ RUN_TEST(7,16);
+ RUN_TEST(8,1);
+ RUN_TEST(8,2);
+ RUN_TEST(8,4);
+ RUN_TEST(8,8);
+ RUN_TEST(8,16);
+ RUN_TEST(9,1);
+ RUN_TEST(9,2);
+ RUN_TEST(9,4);
+ RUN_TEST(9,8);
+ RUN_TEST(9,16);
+ RUN_TEST(10,1);
+ RUN_TEST(10,2);
+ RUN_TEST(10,4);
+ RUN_TEST(10,8);
+ RUN_TEST(10,16);
+ RUN_TEST(11,1);
+ RUN_TEST(11,2);
+ RUN_TEST(11,4);
+ RUN_TEST(11,8);
+ RUN_TEST(11,16);
+ RUN_TEST(12,1);
+ RUN_TEST(12,2);
+ RUN_TEST(12,4);
+ RUN_TEST(12,8);
+ RUN_TEST(12,16);
+ RUN_TEST(13,1);
+ RUN_TEST(13,2);
+ RUN_TEST(13,4);
+ RUN_TEST(13,8);
+ RUN_TEST(13,16);
+ RUN_TEST(14,1);
+ RUN_TEST(14,2);
+ RUN_TEST(14,4);
+ RUN_TEST(14,8);
+ RUN_TEST(14,16);
+ RUN_TEST(15,1);
+ RUN_TEST(15,2);
+ RUN_TEST(15,4);
+ RUN_TEST(15,8);
+ RUN_TEST(15,16);
+ RUN_TEST(16,1);
+ RUN_TEST(16,2);
+ RUN_TEST(16,4);
+ RUN_TEST(16,8);
+ RUN_TEST(16,16);
+ RUN_TEST(17,1);
+ RUN_TEST(17,2);
+ RUN_TEST(17,4);
+ RUN_TEST(17,8);
+ RUN_TEST(17,16);
+ RUN_TEST(18,1);
+ RUN_TEST(18,2);
+ RUN_TEST(18,4);
+ RUN_TEST(18,8);
+ RUN_TEST(18,16);
+ RUN_TEST(19,1);
+ RUN_TEST(19,2);
+ RUN_TEST(19,4);
+ RUN_TEST(19,8);
+ RUN_TEST(19,16);
+ RUN_TEST(20,1);
+ RUN_TEST(20,2);
+ RUN_TEST(20,4);
+ RUN_TEST(20,8);
+ RUN_TEST(20,16);
+ RUN_TEST(21,1);
+ RUN_TEST(21,2);
+ RUN_TEST(21,4);
+ RUN_TEST(21,8);
+ RUN_TEST(21,16);
+ RUN_TEST(22,1);
+ RUN_TEST(22,2);
+ RUN_TEST(22,4);
+ RUN_TEST(22,8);
+ RUN_TEST(22,16);
+ RUN_TEST(23,1);
+ RUN_TEST(23,2);
+ RUN_TEST(23,4);
+ RUN_TEST(23,8);
+ RUN_TEST(23,16);
+ RUN_TEST(24,1);
+ RUN_TEST(24,2);
+ RUN_TEST(24,4);
+ RUN_TEST(24,8);
+ RUN_TEST(24,16);
+ RUN_TEST(25,1);
+ RUN_TEST(25,2);
+ RUN_TEST(25,4);
+ RUN_TEST(25,8);
+ RUN_TEST(25,16);
+ RUN_TEST(26,1);
+ RUN_TEST(26,2);
+ RUN_TEST(26,4);
+ RUN_TEST(26,8);
+ RUN_TEST(26,16);
+ RUN_TEST(27,1);
+ RUN_TEST(27,2);
+ RUN_TEST(27,4);
+ RUN_TEST(27,8);
+ RUN_TEST(27,16);
+ RUN_TEST(28,1);
+ RUN_TEST(28,2);
+ RUN_TEST(28,4);
+ RUN_TEST(28,8);
+ RUN_TEST(28,16);
+ RUN_TEST(29,1);
+ RUN_TEST(29,2);
+ RUN_TEST(29,4);
+ RUN_TEST(29,8);
+ RUN_TEST(29,16);
+ RUN_TEST(30,1);
+ RUN_TEST(30,2);
+ RUN_TEST(30,4);
+ RUN_TEST(30,8);
+ RUN_TEST(30,16);
+ RUN_TEST(31,1);
+ RUN_TEST(31,2);
+ RUN_TEST(31,4);
+ RUN_TEST(31,8);
+ RUN_TEST(31,16);
+ RUN_TEST(32,1);
+ RUN_TEST(32,2);
+ RUN_TEST(32,4);
+ RUN_TEST(32,8);
+ RUN_TEST(32,16);
+ RUN_TEST(33,1);
+ RUN_TEST(33,2);
+ RUN_TEST(33,4);
+ RUN_TEST(33,8);
+ RUN_TEST(33,16);
+ RUN_TEST(34,1);
+ RUN_TEST(34,2);
+ RUN_TEST(34,4);
+ RUN_TEST(34,8);
+ RUN_TEST(34,16);
+ RUN_TEST(35,1);
+ RUN_TEST(35,2);
+ RUN_TEST(35,4);
+ RUN_TEST(35,8);
+ RUN_TEST(35,16);
+ RUN_TEST(36,1);
+ RUN_TEST(36,2);
+ RUN_TEST(36,4);
+ RUN_TEST(36,8);
+ RUN_TEST(36,16);
+ RUN_TEST(37,1);
+ RUN_TEST(37,2);
+ RUN_TEST(37,4);
+ RUN_TEST(37,8);
+ RUN_TEST(37,16);
+ RUN_TEST(38,1);
+ RUN_TEST(38,2);
+ RUN_TEST(38,4);
+ RUN_TEST(38,8);
+ RUN_TEST(38,16);
+ RUN_TEST(39,1);
+ RUN_TEST(39,2);
+ RUN_TEST(39,4);
+ RUN_TEST(39,8);
+ RUN_TEST(39,16);
+ RUN_TEST(40,1);
+ RUN_TEST(40,2);
+ RUN_TEST(40,4);
+ RUN_TEST(40,8);
+ RUN_TEST(40,16);
+ RUN_TEST(41,1);
+ RUN_TEST(41,2);
+ RUN_TEST(41,4);
+ RUN_TEST(41,8);
+ RUN_TEST(41,16);
+ RUN_TEST(42,1);
+ RUN_TEST(42,2);
+ RUN_TEST(42,4);
+ RUN_TEST(42,8);
+ RUN_TEST(42,16);
+ RUN_TEST(43,1);
+ RUN_TEST(43,2);
+ RUN_TEST(43,4);
+ RUN_TEST(43,8);
+ RUN_TEST(43,16);
+ RUN_TEST(44,1);
+ RUN_TEST(44,2);
+ RUN_TEST(44,4);
+ RUN_TEST(44,8);
+ RUN_TEST(44,16);
+ RUN_TEST(45,1);
+ RUN_TEST(45,2);
+ RUN_TEST(45,4);
+ RUN_TEST(45,8);
+ RUN_TEST(45,16);
+ RUN_TEST(46,1);
+ RUN_TEST(46,2);
+ RUN_TEST(46,4);
+ RUN_TEST(46,8);
+ RUN_TEST(46,16);
+ RUN_TEST(47,1);
+ RUN_TEST(47,2);
+ RUN_TEST(47,4);
+ RUN_TEST(47,8);
+ RUN_TEST(47,16);
+ RUN_TEST(48,1);
+ RUN_TEST(48,2);
+ RUN_TEST(48,4);
+ RUN_TEST(48,8);
+ RUN_TEST(48,16);
+ RUN_TEST(49,1);
+ RUN_TEST(49,2);
+ RUN_TEST(49,4);
+ RUN_TEST(49,8);
+ RUN_TEST(49,16);
+#else
+ RUN_TEST(3,1);
+ RUN_TEST(4,1);
+ RUN_TEST(4,2);
+ RUN_TEST(4,4);
+ RUN_TEST(5,1);
+ RUN_TEST(6,1);
+ RUN_TEST(7,1);
+ RUN_TEST(8,1);
+ RUN_TEST(8,2);
+ RUN_TEST(8,4);
+ RUN_TEST(8,8);
+ RUN_TEST(9,1);
+ RUN_TEST(16,1);
+ RUN_TEST(16,2);
+ RUN_TEST(16,4);
+ RUN_TEST(16,8);
+ RUN_TEST(16,16);
+ RUN_TEST(32,1);
+ RUN_TEST(32,2);
+ RUN_TEST(32,4);
+ RUN_TEST(32,8);
+ RUN_TEST(32,16);
+#endif
+ return 0;
+}
===================================================================
@@ -1,4 +1,4 @@
-/* Test memcmp builtin expansion for compilation and proper execution. */
+/* Test strncmp builtin expansion for compilation and proper execution. */
/* { dg-do run } */
/* { dg-options "-O2" } */
/* { dg-require-effective-target ptr32plus } */
@@ -32,31 +32,32 @@
a[SZ] = 0; \
b[SZ] = 0; \
if (!((r1 = strncmp (b, a, SZ)) > 0)) \
- { \
- abort (); \
- } \
+ abort (); \
if (!((r1 = strncmp (a, b, SZ)) < 0)) \
- { \
- abort (); \
- } \
+ abort (); \
b[i] = '1'; \
if (!((r1 = strncmp (a, b, SZ)) == 0)) \
- { \
- abort (); \
- } \
+ abort (); \
for(j = i; j < SZ ; j++) \
{ \
a[j] = '1'; \
b[j] = '2'; \
} \
- if (!((r1 = strncmp(b, a, SZ)) > 0)) \
+ if (!((r1 = strncmp (b, a, SZ)) > 0)) \
+ abort (); \
+ if (!((r1 = strncmp (a, b, SZ)) < 0)) \
+ abort (); \
+ for(j = 0; j < i ; j++) \
{ \
- abort (); \
- } \
- if (!((r1 = strncmp(a, b, SZ)) < 0)) \
- { \
- abort (); \
- } \
+ memset(a, '-', SZ); \
+ memset(b, '-', SZ); \
+ a[j] = '\0'; \
+ a[j+1] = '1'; \
+ b[j] = '\0'; \
+ b[j+1] = '2'; \
+ if ((r1 = strncmp (b, a, SZ)) != 0) \
+ abort (); \
+ } \
a = three + 4096 - (SZ / 2 + (i & 1) * ALIGN); \
b = four + 4096 - (SZ / 2 + (i & 1) * ALIGN); \
memset(a, '-', SZ); \
@@ -66,18 +67,12 @@
a[SZ] = 0; \
b[SZ] = 0; \
if (!((r1 = strncmp(b, a, SZ)) > 0)) \
- { \
- abort (); \
- } \
+ abort (); \
if (!((r1 = strncmp(a, b, SZ)) < 0)) \
- { \
- abort (); \
- } \
+ abort (); \
b[i] = '1'; \
if (!((r1 = strncmp(a, b, SZ)) == 0)) \
- { \
- abort (); \
- } \
+ abort (); \
} \
}
@@ -327,6 +322,11 @@
DEF_TEST(49,4)
DEF_TEST(49,8)
DEF_TEST(49,16)
+DEF_TEST(100,1)
+DEF_TEST(100,2)
+DEF_TEST(100,4)
+DEF_TEST(100,8)
+DEF_TEST(100,16)
#else
DEF_TEST(3,1)
DEF_TEST(4,1)
@@ -350,6 +350,11 @@
DEF_TEST(32,4)
DEF_TEST(32,8)
DEF_TEST(32,16)
+DEF_TEST(100,1)
+DEF_TEST(100,2)
+DEF_TEST(100,4)
+DEF_TEST(100,8)
+DEF_TEST(100,16)
#endif
int
This expands on the previous patch. For strcmp and for strncmp with N larger than 64, the first 64 bytes of comparison is expanded inline and then a call to strcmp or strncmp is emitted to compare the remainder if the strings are found to be equal at that point. -mstring-compare-inline-limit=N determines how many block comparisons are emitted. With the default 8, and 64-bit code, you get 64 bytes. Performance testing on a power8 system shows that the code is anywhere from 2-8 times faster than RHEL7.2 glibc strcmp/strncmp depending on alignment and length. In the process of adding this I discovered that the expansion being generated for strncmp had a bug in that it was not testing for a zero byte to terminate the comparison. As a result inputs like strncmp("AB\0CDEFGX", "AB\0CDEFGY", 9) would be compared not equal. The initial comparison of a doubleword would be equal so a second one would be fetched and compared, ignoring the zero byte that should have terminated comparison. The fix is to use a cmpb to check for zero bytes in the equality case before comparing the next chunk. I updated the strncmp-1.c test case to check for this, and also added a new strcmp-1.c test case to check strcmp expansion. Also both now have a length 100 tests to check the transition from the inline comparison to the library call for the remainder. ChangeLog 2017-01-11 Aaron Sawdey <acsawdey@linux.vnet.ibm.com> * config/rs6000/rs6000-protos.h (expand_strn_compare): Add arg. * config/rs6000/rs6000.c (expand_strn_compare): Add ability to expand strcmp. Fix bug where comparison didn't stop with zero byte. * config/rs6000/rs6000.md (cmpstrnsi): Args to expand_strn_compare. (cmpstrsi): Add pattern. gcc.dg/ChangeLog 2017-01-11 Aaron Sawdey <acsawdey@linux.vnet.ibm.com> * gcc.dg/strcmp-1.c: New. * gcc.dg/strncmp-1.c: Add test for a bug that escaped.