On 2022/06/13 12:49, Max Filippov wrote:
> Hi Suwa-san,
hi!
> This change produces a bunch of regression test failures in big-endian
> configuration:
bad news X(
that point is what i was a little worried about...
> E.g. for the test gcc.c-torture/execute/struct-ini-2.c
> the following assembly code is generated now:
> and the following code was generated before this change:
- .literal .LC1, -4096
- l32r a10, .LC1
- and a10, a8, a10
+ extui a10, a8, 16, 4 // wrong! must be 12, 4
+ slli a10, a10, 12
and of course, '(zero_extract)' is endianness-sensitive.
(ref. 14.11 Bit-Fields, gcc-internals)
the all patches that i previouly posted do not match or emit '(zero_extract)',
except for this case.
===
This patch offers several insn-and-split patterns for bitwise AND with
register and constant that can be represented as:
i. 1's least significant N bits and the others 0's (17 <= N <= 31)
ii. 1's most significant N bits and the others 0's (12 <= N <= 31)
iii. M 1's sequence of bits and trailing N 0's bits, that cannot fit into a
"MOVI Ax, simm12" instruction (1 <= M <= 16, 1 <= N <= 30)
And also offers shortcuts for conditional branch if each of the abovementioned
operations is (not) equal to zero.
gcc/ChangeLog:
* config/xtensa/predicates.md (shifted_mask_operand):
New predicate.
* config/xtensa/xtensa.md (*andsi3_const_pow2_minus_one):
New insn-and-split pattern.
(*andsi3_const_negative_pow2, *andsi3_const_shifted_mask,
*masktrue_const_pow2_minus_one, *masktrue_const_negative_pow2,
*masktrue_const_shifted_mask): Ditto.
---
gcc/config/xtensa/predicates.md | 10 ++
gcc/config/xtensa/xtensa.md | 179 ++++++++++++++++++++++++++++++++
2 files changed, 189 insertions(+)
diff --git a/gcc/config/xtensa/predicates.md b/gcc/config/xtensa/predicates.md
index bcc83ada0ae..d63a6cf034c 100644
--- a/gcc/config/xtensa/predicates.md
+++ b/gcc/config/xtensa/predicates.md
@@ -52,6 +52,16 @@
(match_test "xtensa_mask_immediate (INTVAL (op))"))
(match_operand 0 "register_operand")))
+(define_predicate "shifted_mask_operand"
+ (match_code "const_int")
+{
+ HOST_WIDE_INT mask = INTVAL (op);
+ int shift = ctz_hwi (mask);
+
+ return IN_RANGE (shift, 1, 31)
+ && xtensa_mask_immediate ((uint32_t)mask >> shift);
+})
+
(define_predicate "extui_fldsz_operand"
(and (match_code "const_int")
(match_test "IN_RANGE (INTVAL (op), 1, 16)")))
diff --git a/gcc/config/xtensa/xtensa.md b/gcc/config/xtensa/xtensa.md
index a4477e2207e..5d0f346b01a 100644
--- a/gcc/config/xtensa/xtensa.md
+++ b/gcc/config/xtensa/xtensa.md
@@ -645,6 +645,83 @@
(set_attr "mode" "SI")
(set_attr "length" "6")])
+(define_insn_and_split "*andsi3_const_pow2_minus_one"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "const_int_operand" "i")))]
+ "IN_RANGE (exact_log2 (INTVAL (operands[2]) + 1), 17, 31)"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (ashift:SI (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 0)
+ (lshiftrt:SI (match_dup 0)
+ (match_dup 2)))]
+{
+ operands[2] = GEN_INT (32 - floor_log2 (INTVAL (operands[2]) + 1));
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && INTVAL (operands[2]) == 0x7FFFFFFF")
+ (const_int 5)
+ (const_int 6)))])
+
+(define_insn_and_split "*andsi3_const_negative_pow2"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "const_int_operand" "i")))]
+ "IN_RANGE (exact_log2 (-INTVAL (operands[2])), 12, 31)"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (lshiftrt:SI (match_dup 1)
+ (match_dup 2)))
+ (set (match_dup 0)
+ (ashift:SI (match_dup 0)
+ (match_dup 2)))]
+{
+ operands[2] = GEN_INT (floor_log2 (-INTVAL (operands[2])));
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set_attr "length" "6")])
+
+(define_insn_and_split "*andsi3_const_shifted_mask"
+ [(set (match_operand:SI 0 "register_operand" "=a")
+ (and:SI (match_operand:SI 1 "register_operand" "r")
+ (match_operand:SI 2 "shifted_mask_operand" "i")))]
+ "! xtensa_simm12b (INTVAL (operands[2]))"
+ "#"
+ "&& 1"
+ [(set (match_dup 0)
+ (zero_extract:SI (match_dup 1)
+ (match_dup 3)
+ (match_dup 4)))
+ (set (match_dup 0)
+ (ashift:SI (match_dup 0)
+ (match_dup 2)))]
+{
+ HOST_WIDE_INT mask = INTVAL (operands[2]);
+ int shift = ctz_hwi (mask);
+ int mask_size = floor_log2 (((uint32_t)mask >> shift) + 1);
+ int mask_pos = shift;
+ if (BITS_BIG_ENDIAN)
+ mask_pos = (32 - (mask_size + shift)) & 0x1f;
+ operands[2] = GEN_INT (shift);
+ operands[3] = GEN_INT (mask_size);
+ operands[4] = GEN_INT (mask_pos);
+}
+ [(set_attr "type" "arith")
+ (set_attr "mode" "SI")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && ctz_hwi (INTVAL (operands[2])) == 1")
+ (const_int 5)
+ (const_int 6)))])
+
(define_insn "iorsi3"
[(set (match_operand:SI 0 "register_operand" "=a")
(ior:SI (match_operand:SI 1 "register_operand" "%r")
@@ -1649,6 +1726,108 @@
(set_attr "mode" "none")
(set_attr "length" "3")])
+(define_insn_and_split "*masktrue_const_pow2_minus_one"
+ [(set (pc)
+ (if_then_else (match_operator 3 "boolean_operator"
+ [(and:SI (match_operand:SI 0 "register_operand" "r")
+ (match_operand:SI 1 "const_int_operand" "i"))
+ (const_int 0)])
+ (label_ref (match_operand 2 "" ""))
+ (pc)))]
+ "IN_RANGE (exact_log2 (INTVAL (operands[1]) + 1), 17, 31)"
+ "#"
+ "&& can_create_pseudo_p ()"
+ [(set (match_dup 4)
+ (ashift:SI (match_dup 0)
+ (match_dup 1)))
+ (set (pc)
+ (if_then_else (match_op_dup 3
+ [(match_dup 4)
+ (const_int 0)])
+ (label_ref (match_dup 2))
+ (pc)))]
+{
+ operands[1] = GEN_INT (32 - floor_log2 (INTVAL (operands[1]) + 1));
+ operands[4] = gen_reg_rtx (SImode);
+}
+ [(set_attr "type" "jump")
+ (set_attr "mode" "none")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && INTVAL (operands[1]) == 0x7FFFFFFF")
+ (const_int 5)
+ (const_int 6)))])
+
+(define_insn_and_split "*masktrue_const_negative_pow2"
+ [(set (pc)
+ (if_then_else (match_operator 3 "boolean_operator"
+ [(and:SI (match_operand:SI 0 "register_operand" "r")
+ (match_operand:SI 1 "const_int_operand" "i"))
+ (const_int 0)])
+ (label_ref (match_operand 2 "" ""))
+ (pc)))]
+ "IN_RANGE (exact_log2 (-INTVAL (operands[1])), 12, 30)"
+ "#"
+ "&& can_create_pseudo_p ()"
+ [(set (match_dup 4)
+ (lshiftrt:SI (match_dup 0)
+ (match_dup 1)))
+ (set (pc)
+ (if_then_else (match_op_dup 3
+ [(match_dup 4)
+ (const_int 0)])
+ (label_ref (match_dup 2))
+ (pc)))]
+{
+ operands[1] = GEN_INT (floor_log2 (-INTVAL (operands[1])));
+ operands[4] = gen_reg_rtx (SImode);
+}
+ [(set_attr "type" "jump")
+ (set_attr "mode" "none")
+ (set_attr "length" "6")])
+
+(define_insn_and_split "*masktrue_const_shifted_mask"
+ [(set (pc)
+ (if_then_else (match_operator 4 "boolean_operator"
+ [(and:SI (match_operand:SI 0 "register_operand" "r")
+ (match_operand:SI 1 "shifted_mask_operand"
"i"))
+ (match_operand:SI 2 "const_int_operand" "i")])
+ (label_ref (match_operand 3 "" ""))
+ (pc)))]
+ "(INTVAL (operands[2]) & ((1 << ctz_hwi (INTVAL (operands[1]))) - 1)) == 0
+ && xtensa_b4const_or_zero ((uint32_t)INTVAL (operands[2]) >> ctz_hwi
(INTVAL (operands[1])))"
+ "#"
+ "&& can_create_pseudo_p ()"
+ [(set (match_dup 6)
+ (zero_extract:SI (match_dup 0)
+ (match_dup 5)
+ (match_dup 1)))
+ (set (pc)
+ (if_then_else (match_op_dup 4
+ [(match_dup 6)
+ (match_dup 2)])
+ (label_ref (match_dup 3))
+ (pc)))]
+{
+ HOST_WIDE_INT mask = INTVAL (operands[1]);
+ int shift = ctz_hwi (mask);
+ int mask_size = floor_log2 (((uint32_t)mask >> shift) + 1);
+ int mask_pos = shift;
+ if (BITS_BIG_ENDIAN)
+ mask_pos = (32 - (mask_size + shift)) & 0x1f;
+ operands[1] = GEN_INT (mask_pos);
+ operands[2] = GEN_INT ((uint32_t)INTVAL (operands[2]) >> shift);
+ operands[5] = GEN_INT (mask_size);
+ operands[6] = gen_reg_rtx (SImode);
+}
+ [(set_attr "type" "jump")
+ (set_attr "mode" "none")
+ (set (attr "length")
+ (if_then_else (match_test "TARGET_DENSITY
+ && (uint32_t)INTVAL (operands[2]) >> ctz_hwi
(INTVAL (operands[1])) == 0")
+ (const_int 5)
+ (const_int 6)))])
+
;; Zero-overhead looping support.
--
2.20.1
