aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRichard Earnshaw <rearnsha@arm.com>2019-10-18 19:05:09 +0000
committerRichard Earnshaw <rearnsha@gcc.gnu.org>2019-10-18 19:05:09 +0000
commitead327735c15436cc0516f427da107be0d747822 (patch)
tree9b0b25b1f6956080a0b7948ad71694fc0ed40027
parent238273fe06e3da6dd1d80b04217d53c76cf5fa41 (diff)
downloadgcc-ead327735c15436cc0516f427da107be0d747822.zip
gcc-ead327735c15436cc0516f427da107be0d747822.tar.gz
gcc-ead327735c15436cc0516f427da107be0d747822.tar.bz2
[arm] Early expansion of subvdi4
This patch adds early expansion of subvdi4. The expansion sequence is broadly based on the expansion of usubvdi4. * config/arm/arm.md (subvdi4): Decompose calculation into 32-bit operations. (subdi3_compare1): Delete pattern. (subvsi3_borrow): New insn pattern. (subvsi3_borrow_imm): Likewise. From-SVN: r277190
-rw-r--r--gcc/ChangeLog8
-rw-r--r--gcc/config/arm/arm.md131
2 files changed, 122 insertions, 17 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 153792e..3f2fbb7 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,13 @@
2019-10-18 Richard Earnshaw <rearnsha@arm.com>
+ * config/arm/arm.md (subvdi4): Decompose calculation into 32-bit
+ operations.
+ (subdi3_compare1): Delete pattern.
+ (subvsi3_borrow): New insn pattern.
+ (subvsi3_borrow_imm): Likewise.
+
+2019-10-18 Richard Earnshaw <rearnsha@arm.com>
+
* config/arm/arm.md (subv<mode>4): Delete.
(subvdi4): New expander pattern.
(subvsi4): Likewise. Handle some immediate values.
diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
index 05b735c..5a8175f 100644
--- a/gcc/config/arm/arm.md
+++ b/gcc/config/arm/arm.md
@@ -1395,12 +1395,79 @@
(define_expand "subvdi4"
[(match_operand:DI 0 "s_register_operand")
- (match_operand:DI 1 "s_register_operand")
- (match_operand:DI 2 "s_register_operand")
+ (match_operand:DI 1 "reg_or_int_operand")
+ (match_operand:DI 2 "reg_or_int_operand")
(match_operand 3 "")]
"TARGET_32BIT"
{
- emit_insn (gen_subdi3_compare1 (operands[0], operands[1], operands[2]));
+ rtx lo_result, hi_result;
+ rtx lo_op1, hi_op1, lo_op2, hi_op2;
+ lo_result = gen_lowpart (SImode, operands[0]);
+ hi_result = gen_highpart (SImode, operands[0]);
+ machine_mode mode = CCmode;
+
+ if (CONST_INT_P (operands[1]) && CONST_INT_P (operands[2]))
+ {
+ /* If both operands are constants we can decide the result statically. */
+ wi::overflow_type overflow;
+ wide_int val = wi::sub (rtx_mode_t (operands[1], DImode),
+ rtx_mode_t (operands[2], DImode),
+ SIGNED, &overflow);
+ emit_move_insn (operands[0], GEN_INT (val.to_shwi ()));
+ if (overflow != wi::OVF_NONE)
+ emit_jump_insn (gen_jump (operands[3]));
+ DONE;
+ }
+ else if (CONST_INT_P (operands[1]))
+ {
+ arm_decompose_di_binop (operands[2], operands[1], &lo_op2, &hi_op2,
+ &lo_op1, &hi_op1);
+ if (const_ok_for_arm (INTVAL (lo_op1)))
+ {
+ emit_insn (gen_rsb_imm_compare (lo_result, lo_op1, lo_op2,
+ GEN_INT (~UINTVAL (lo_op1))));
+ /* We could potentially use RSC here in Arm state, but not
+ in Thumb, so it's probably not worth the effort of handling
+ this. */
+ hi_op1 = force_reg (SImode, hi_op1);
+ mode = CC_RSBmode;
+ goto highpart;
+ }
+ operands[1] = force_reg (DImode, operands[1]);
+ }
+
+ arm_decompose_di_binop (operands[1], operands[2], &lo_op1, &hi_op1,
+ &lo_op2, &hi_op2);
+ if (lo_op2 == const0_rtx)
+ {
+ emit_move_insn (lo_result, lo_op1);
+ if (!arm_add_operand (hi_op2, SImode))
+ hi_op2 = force_reg (SImode, hi_op2);
+ emit_insn (gen_subvsi4 (hi_result, hi_op1, hi_op2, operands[3]));
+ DONE;
+ }
+
+ if (CONST_INT_P (lo_op2) && !arm_addimm_operand (lo_op2, SImode))
+ lo_op2 = force_reg (SImode, lo_op2);
+ if (CONST_INT_P (lo_op2))
+ emit_insn (gen_cmpsi2_addneg (lo_result, lo_op1, lo_op2,
+ GEN_INT (-INTVAL (lo_op2))));
+ else
+ emit_insn (gen_subsi3_compare1 (lo_result, lo_op1, lo_op2));
+
+ highpart:
+ if (!arm_not_operand (hi_op2, SImode))
+ hi_op2 = force_reg (SImode, hi_op2);
+ rtx ccreg = gen_rtx_REG (mode, CC_REGNUM);
+ if (CONST_INT_P (hi_op2))
+ emit_insn (gen_subvsi3_borrow_imm (hi_result, hi_op1, hi_op2,
+ gen_rtx_LTU (SImode, ccreg, const0_rtx),
+ gen_rtx_LTU (DImode, ccreg,
+ const0_rtx)));
+ else
+ emit_insn (gen_subvsi3_borrow (hi_result, hi_op1, hi_op2,
+ gen_rtx_LTU (SImode, ccreg, const0_rtx),
+ gen_rtx_LTU (DImode, ccreg, const0_rtx)));
arm_gen_unlikely_cbranch (NE, CC_Vmode, operands[3]);
DONE;
@@ -1523,20 +1590,6 @@
DONE;
})
-(define_insn "subdi3_compare1"
- [(set (reg:CC CC_REGNUM)
- (compare:CC
- (match_operand:DI 1 "s_register_operand" "r")
- (match_operand:DI 2 "s_register_operand" "r")))
- (set (match_operand:DI 0 "s_register_operand" "=&r")
- (minus:DI (match_dup 1) (match_dup 2)))]
- "TARGET_32BIT"
- "subs\\t%Q0, %Q1, %Q2;sbcs\\t%R0, %R1, %R2"
- [(set_attr "conds" "set")
- (set_attr "length" "8")
- (set_attr "type" "multiple")]
-)
-
(define_insn "subsi3_compare1"
[(set (reg:CC CC_REGNUM)
(compare:CC
@@ -2016,6 +2069,50 @@
(set_attr "type" "alus_imm")]
)
+(define_insn "subvsi3_borrow"
+ [(set (reg:CC_V CC_REGNUM)
+ (compare:CC_V
+ (minus:DI
+ (minus:DI
+ (sign_extend:DI (match_operand:SI 1 "s_register_operand" "0,r"))
+ (sign_extend:DI (match_operand:SI 2 "s_register_operand" "l,r")))
+ (match_operand:DI 4 "arm_borrow_operation" ""))
+ (sign_extend:DI
+ (minus:SI (minus:SI (match_dup 1) (match_dup 2))
+ (match_operand:SI 3 "arm_borrow_operation" "")))))
+ (set (match_operand:SI 0 "s_register_operand" "=l,r")
+ (minus:SI (minus:SI (match_dup 1) (match_dup 2))
+ (match_dup 3)))]
+ "TARGET_32BIT"
+ "sbcs%?\\t%0, %1, %2"
+ [(set_attr "conds" "set")
+ (set_attr "arch" "t2,*")
+ (set_attr "length" "2,4")]
+)
+
+(define_insn "subvsi3_borrow_imm"
+ [(set (reg:CC_V CC_REGNUM)
+ (compare:CC_V
+ (minus:DI
+ (minus:DI
+ (sign_extend:DI (match_operand:SI 1 "s_register_operand" "r,r"))
+ (match_operand 2 "arm_adcimm_operand" "I,K"))
+ (match_operand:DI 4 "arm_borrow_operation" ""))
+ (sign_extend:DI
+ (minus:SI (minus:SI (match_dup 1) (match_dup 2))
+ (match_operand:SI 3 "arm_borrow_operation" "")))))
+ (set (match_operand:SI 0 "s_register_operand" "=r,r")
+ (minus:SI (minus:SI (match_dup 1) (match_dup 2))
+ (match_dup 3)))]
+ "TARGET_32BIT
+ && INTVAL (operands[2]) == ARM_SIGN_EXTEND (INTVAL (operands[2]))"
+ "@
+ sbcs%?\\t%0, %1, %2
+ adcs%?\\t%0, %1, #%B2"
+ [(set_attr "conds" "set")
+ (set_attr "type" "alus_imm")]
+)
+
(define_expand "subsf3"
[(set (match_operand:SF 0 "s_register_operand")
(minus:SF (match_operand:SF 1 "s_register_operand")