RISC-V: Combine vec_duplicate + vwaddu.vv to vwaddu.vx on GR2VR cost

This patch would like to combine the vec_duplicate + vwaddu.vv to the
vwaddu.vx.  From example as below code.  The related pattern will depend
on the cost of vec_duplicate from GR2VR.  Then the late-combine will
take action if the cost of GR2VR is zero, and reject the combination
if the GR2VR cost is greater than zero.

Assume we have example code like below, GR2VR cost is 0.

Before this patch:
  11       beq a3,zero,.L8
  12       vsetvli a5,zero,e32,m1,ta,ma
  13       vmv.v.x v2,a2
  ...
  16   .L3:
  17       vsetvli a5,a3,e32,m1,ta,ma
  ...
  22       vwaddu.vv v1,v2,v3
  ...
  25       bne a3,zero,.L3

After this patch:
  11       beq a3,zero,.L8
  ...
  14    .L3:
  15       vsetvli a5,a3,e32,m1,ta,ma
  ...
  20       vwaddu.vx v1,a2,v3
  ...
  23       bne a3,zero,.L3

The pattern of this patch only works on DImode, aka below pattern.
v1:RVVM1DImode = (zero_extend:RVVM1DImode v2:RVVM1SImode)
  + (vec_dup:RVVM1DImode (zero_extend:DImode x2:SImode));

Unfortunately, for uint16_t to uint32_t or uint8_t to uint16_t, we loss
this extend op after expand.

For uint16_t => uint32_t we have:
(set (reg:SI 149) (subreg/s/v:SI (reg/v:DI 146 [ rs1 ]) 0))

For uint32_t => uint64_t we have:
(set (reg:DI 148 [ _6 ])
     (zero_extend:DI (subreg/s/u:SI (reg/v:DI 146 [ rs1 ]) 0)))

We can see there is no zero_extend for uint16_t to uint32_t, and we
cannot hit the pattern above.  So the combine will try below pattern
for uint16_t to uint32_t.

v1:RVVM1SImode = (zero_extend:RVVM1SImode v2:RVVM1HImode)
  + (vec_dup:RVVM1SImode (subreg:SIMode (:DImode x2:SImode)))

But it cannot match the vwaddu sematics, thus we need another handing
for the vwaddu.vv for uint16_t to uint32_t, as well as the uint8_t to
uint16_t.

gcc/ChangeLog:

	* config/riscv/autovec-opt.md (*widen_first_<any_extend:su>_vx_<mode>):
	Add helper bridge pattern for vwaddu.vx combine.
	(*widen_<any_widen_binop:optab>_<any_extend:su>_vx_<mode>): Add
	new pattern to match vwaddu.vx combine.
	* config/riscv/iterators.md: Add code attr to get extend CODE.
	* config/riscv/vector-iterators.md: Add Dmode iterator for
	widen.

Signed-off-by: Pan Li <pan2.li@intel.com>

diff --git a/gcc/config/riscv/autovec-opt.md b/gcc/config/riscv/autovec-opt.md
index 315cd1d2ad50731f10144368a915c713c6c6e6d7..a5eb49cc81edfee69b5d587464a3731332a02b48 100644 (file)
--- a/gcc/config/riscv/autovec-opt.md
+++ b/gcc/config/riscv/autovec-opt.md
@@ -1868,6 +1868,48 @@
   }
   [(set_attr "type" "vimuladd")])
 
+(define_insn_and_split "*widen_first_<any_extend:su>_vx_<mode>"
+ [(set (match_operand:VWEXTI_D     0 "register_operand")
+       (vec_duplicate:VWEXTI_D
+        (any_extend:<VEL>
+          (match_operand:<VSUBEL> 1 "register_operand"))))]
+  "TARGET_VECTOR && TARGET_64BIT && can_create_pseudo_p ()"
+  "#"
+  "&& 1"
+  [(const_int 0)]
+  {
+    rtx extend_scalar = gen_reg_rtx (<VEL>mode);
+    emit_insn (gen_<any_extend:extend_name><vsubel><vel>2 (extend_scalar,
+                                                          operands[1]));
+
+    insn_code icode = code_for_pred_broadcast (<MODE>mode);
+    rtx vec_dup_ops[] = {operands[0], extend_scalar};
+    riscv_vector::emit_vlmax_insn (icode, riscv_vector::UNARY_OP, vec_dup_ops);
+
+    DONE;
+  })
+
+(define_insn_and_split "*widen_<any_widen_binop:optab>_<any_extend:su>_vx_<mode>"
+ [(set (match_operand:VWEXTI_D             0 "register_operand")
+       (any_widen_binop:VWEXTI_D
+        (any_extend:VWEXTI_D
+          (match_operand:<V_DOUBLE_TRUNC> 1 "register_operand"))
+        (vec_duplicate:VWEXTI_D
+          (any_extend:<VEL>
+            (match_operand:<VSUBEL>       2 "register_operand")))))]
+  "TARGET_VECTOR && TARGET_64BIT && can_create_pseudo_p ()"
+  "#"
+  "&& 1"
+  [(const_int 0)]
+  {
+    insn_code icode = code_for_pred_dual_widen_scalar (<any_widen_binop:CODE>,
+                                                      <any_extend:CODE>,
+                                                      <MODE>mode);
+    riscv_vector::emit_vlmax_insn (icode, riscv_vector::BINARY_OP, operands);
+
+    DONE;
+  }
+  [(set_attr "type" "viwalu")])
 
 ;; =============================================================================
 ;; Combine vec_duplicate + op.vv to op.vf

diff --git a/gcc/config/riscv/iterators.md b/gcc/config/riscv/iterators.md
index cd8fd7a2b25293c6bb63fe5af47e8d84738ea947..35de17f76cd9b6af90fe50ea9ebe7a739fa65a0e 100644 (file)
--- a/gcc/config/riscv/iterators.md
+++ b/gcc/config/riscv/iterators.md
@@ -207,6 +207,9 @@
 ;; This code iterator allows signed and unsigned widening multiplications
 ;; to use the same template.
 (define_code_iterator any_extend [sign_extend zero_extend])
+(define_code_attr extend_name [
+  (sign_extend "extend") (zero_extend "zero_extend")
+])
 
 ;; These code iterators allow unsigned and signed extraction to be generated
 ;; from the same template.

diff --git a/gcc/config/riscv/vector-iterators.md b/gcc/config/riscv/vector-iterators.md
index ed7e9c3a95160692476b6cace8019316cb7b7d61..45af65642cd96a08971bc26b5be10b58fb84f56b 100644 (file)
--- a/gcc/config/riscv/vector-iterators.md
+++ b/gcc/config/riscv/vector-iterators.md
@@ -943,6 +943,22 @@
   (RVVMF2SF "TARGET_VECTOR_ELEN_FP_32 && TARGET_VECTOR_ELEN_64")
 ])
 
+(define_mode_iterator VWEXTI_D [
+  (RVVM8DI "TARGET_VECTOR_ELEN_64") (RVVM4DI "TARGET_VECTOR_ELEN_64")
+  (RVVM2DI "TARGET_VECTOR_ELEN_64") (RVVM1DI "TARGET_VECTOR_ELEN_64")
+
+  (V1DI "riscv_vector::vls_mode_valid_p (V1DImode) && TARGET_VECTOR_ELEN_64")
+  (V2DI "riscv_vector::vls_mode_valid_p (V2DImode) && TARGET_VECTOR_ELEN_64")
+  (V4DI "riscv_vector::vls_mode_valid_p (V4DImode) && TARGET_VECTOR_ELEN_64")
+  (V8DI "riscv_vector::vls_mode_valid_p (V8DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 64")
+  (V16DI "riscv_vector::vls_mode_valid_p (V16DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 128")
+  (V32DI "riscv_vector::vls_mode_valid_p (V32DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 256")
+  (V64DI "riscv_vector::vls_mode_valid_p (V64DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 512")
+  (V128DI "riscv_vector::vls_mode_valid_p (V128DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 1024")
+  (V256DI "riscv_vector::vls_mode_valid_p (V256DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 2048")
+  (V512DI "riscv_vector::vls_mode_valid_p (V512DImode) && TARGET_VECTOR_ELEN_64 && TARGET_MIN_VLEN >= 4096")
+])
+
 (define_mode_iterator VWEXTI [
   RVVM8HI RVVM4HI RVVM2HI RVVM1HI RVVMF2HI (RVVMF4HI "TARGET_VECTOR_ELEN_64")