diff mbox

[AArch64,array_mode,7/8] Combine the expanders using VSTRUCT:nregs

Message ID 1442323210-14455-1-git-send-email-alan.lawrence@arm.com
State New
Headers show

Commit Message

Alan Lawrence Sept. 15, 2015, 1:20 p.m. UTC 
On 15/09/15 10:43, James Greenhalgh wrote:
>
> It is convenient that this falls out, but likely surprising for nregs.
> Please add a comment to nregs explaining the dual use of nregs to represent
> both the number of Q registers used for the type, and the number of elements
> touched by the structure load/store operations.

The counterargument is that the type uses some number N of Q-Registers to hold it, because it is N vectors each of size 1 Q-reg; and the structure load/store operations operate on one lane per vector, which is therefore N elements...

However, comment added, as attached, and pushed as r227793.

Regards,
Alan

gcc/ChangeLog:

	* config/aarch64/aarch64-simd.md (aarch64_ld2r<mode>,
	aarch64_ld3r<mode>, aarch64_ld4r<mode>): Combine together, making...
	(aarch64_simd_ld<VSTRUCT:nregs>r<VALLDIF:mode>): ...this.
	(aarch64_ld2_lane<mode>, aarch64_ld3_lane<mode>,
	aarch64_ld4_lane<mode>): Combine together, making...
	(aarch64_ld<VSTRUCT:nregs>_lane<VALLDIF:mode>): ...this.
	(aarch64_st2_lane<VALLDIF:mode>, aarch64_st3_lane<VQ:mode>,
	aarch64_st4_lane<VQ:mode>): Combine together, making...
	(aarch64_st<VSTRUCT:nregs>_lane<VALLDIF:mode>): ...this.
	* config/aarch64/iterators.md (nregs): Add comment.
---
 gcc/config/aarch64/aarch64-simd.md | 138 +++++++------------------------------
 gcc/config/aarch64/iterators.md    |   3 +
 2 files changed, 26 insertions(+), 115 deletions(-)
diff mbox

Patch

diff --git a/gcc/config/aarch64/aarch64-simd.md b/gcc/config/aarch64/aarch64-simd.md
index f239ee7..dbe5259 100644
--- a/gcc/config/aarch64/aarch64-simd.md
+++ b/gcc/config/aarch64/aarch64-simd.md
@@ -4381,42 +4381,18 @@ 
     FAIL;
 })
 
-(define_expand "aarch64_ld2r<mode>"
-  [(match_operand:OI 0 "register_operand" "=w")
+(define_expand "aarch64_ld<VSTRUCT:nregs>r<VALLDIF:mode>"
+  [(match_operand:VSTRUCT 0 "register_operand" "=w")
    (match_operand:DI 1 "register_operand" "w")
    (unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
   "TARGET_SIMD"
 {
   rtx mem = gen_rtx_MEM (BLKmode, operands[1]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 2);
+  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<VALLDIF:MODE>mode))
+		     * <VSTRUCT:nregs>);
 
-  emit_insn (gen_aarch64_simd_ld2r<mode> (operands[0], mem));
-  DONE;
-})
-
-(define_expand "aarch64_ld3r<mode>"
-  [(match_operand:CI 0 "register_operand" "=w")
-   (match_operand:DI 1 "register_operand" "w")
-   (unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
-  "TARGET_SIMD"
-{
-  rtx mem = gen_rtx_MEM (BLKmode, operands[1]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 3);
-
-  emit_insn (gen_aarch64_simd_ld3r<mode> (operands[0], mem));
-  DONE;
-})
-
-(define_expand "aarch64_ld4r<mode>"
-  [(match_operand:XI 0 "register_operand" "=w")
-   (match_operand:DI 1 "register_operand" "w")
-   (unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
-  "TARGET_SIMD"
-{
-  rtx mem = gen_rtx_MEM (BLKmode, operands[1]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 4);
-
-  emit_insn (gen_aarch64_simd_ld4r<mode> (operands[0],mem));
+  emit_insn (gen_aarch64_simd_ld<VSTRUCT:nregs>r<VALLDIF:mode> (operands[0],
+								mem));
   DONE;
 })
 
@@ -4599,62 +4575,26 @@ 
   DONE;
 })
 
-(define_expand "aarch64_ld2_lane<mode>"
-  [(match_operand:OI 0 "register_operand" "=w")
-	(match_operand:DI 1 "register_operand" "w")
-	(match_operand:OI 2 "register_operand" "0")
-	(match_operand:SI 3 "immediate_operand" "i")
-	(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
-  "TARGET_SIMD"
-{
-  rtx mem = gen_rtx_MEM (BLKmode, operands[1]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 2);
-
-  emit_insn (gen_aarch64_vec_load_lanesoi_lane<mode> (operands[0],
-						      mem,
-						      operands[2],
-						      operands[3]));
-  DONE;
-})
-
-(define_expand "aarch64_ld3_lane<mode>"
-  [(match_operand:CI 0 "register_operand" "=w")
+(define_expand "aarch64_ld<VSTRUCT:nregs>_lane<VALLDIF:mode>"
+  [(match_operand:VSTRUCT 0 "register_operand" "=w")
 	(match_operand:DI 1 "register_operand" "w")
-	(match_operand:CI 2 "register_operand" "0")
+	(match_operand:VSTRUCT 2 "register_operand" "0")
 	(match_operand:SI 3 "immediate_operand" "i")
 	(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
   "TARGET_SIMD"
 {
   rtx mem = gen_rtx_MEM (BLKmode, operands[1]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 3);
-
-  emit_insn (gen_aarch64_vec_load_lanesci_lane<mode> (operands[0],
-						      mem,
-						      operands[2],
-						      operands[3]));
+  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<VALLDIF:MODE>mode))
+		     * <VSTRUCT:nregs>);
+
+  aarch64_simd_lane_bounds (operands[3], 0,
+			    GET_MODE_NUNITS (<VALLDIF:MODE>mode),
+			    NULL);
+  emit_insn (gen_aarch64_vec_load_lanes<VSTRUCT:mode>_lane<VALLDIF:mode> (
+	operands[0], mem, operands[2], operands[3]));
   DONE;
 })
 
-(define_expand "aarch64_ld4_lane<mode>"
-  [(match_operand:XI 0 "register_operand" "=w")
-	(match_operand:DI 1 "register_operand" "w")
-	(match_operand:XI 2 "register_operand" "0")
-	(match_operand:SI 3 "immediate_operand" "i")
-	(unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)]
-  "TARGET_SIMD"
-{
-  rtx mem = gen_rtx_MEM (BLKmode, operands[1]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 4);
-
-  emit_insn (gen_aarch64_vec_load_lanesxi_lane<mode> (operands[0],
-						      mem,
-						      operands[2],
-						      operands[3]));
-  DONE;
-})
-
-
-
 ;; Expanders for builtins to extract vector registers from large
 ;; opaque integer modes.
 
@@ -4882,51 +4822,19 @@ 
   DONE;
 })
 
-(define_expand "aarch64_st2_lane<mode>"
- [(match_operand:DI 0 "register_operand" "r")
-  (match_operand:OI 1 "register_operand" "w")
-  (unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)
-  (match_operand:SI 2 "immediate_operand")]
-  "TARGET_SIMD"
-{
-  rtx mem = gen_rtx_MEM (BLKmode, operands[0]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 2);
-
-  emit_insn (gen_aarch64_vec_store_lanesoi_lane<mode> (mem,
-						       operands[1],
-						       operands[2]));
-  DONE;
-})
-
-(define_expand "aarch64_st3_lane<mode>"
- [(match_operand:DI 0 "register_operand" "r")
-  (match_operand:CI 1 "register_operand" "w")
-  (unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)
-  (match_operand:SI 2 "immediate_operand")]
-  "TARGET_SIMD"
-{
-  rtx mem = gen_rtx_MEM (BLKmode, operands[0]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 3);
-
-  emit_insn (gen_aarch64_vec_store_lanesci_lane<mode> (mem,
-						       operands[1],
-						       operands[2]));
-  DONE;
-})
-
-(define_expand "aarch64_st4_lane<mode>"
+(define_expand "aarch64_st<VSTRUCT:nregs>_lane<VALLDIF:mode>"
  [(match_operand:DI 0 "register_operand" "r")
-  (match_operand:XI 1 "register_operand" "w")
+  (match_operand:VSTRUCT 1 "register_operand" "w")
   (unspec:VALLDIF [(const_int 0)] UNSPEC_VSTRUCTDUMMY)
   (match_operand:SI 2 "immediate_operand")]
   "TARGET_SIMD"
 {
   rtx mem = gen_rtx_MEM (BLKmode, operands[0]);
-  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<MODE>mode)) * 4);
+  set_mem_size (mem, GET_MODE_SIZE (GET_MODE_INNER (<VALLDIF:MODE>mode))
+		     * <VSTRUCT:nregs>);
 
-  emit_insn (gen_aarch64_vec_store_lanesxi_lane<mode> (mem,
-						       operands[1],
-						       operands[2]));
+  emit_insn (gen_aarch64_vec_store_lanes<VSTRUCT:mode>_lane<VALLDIF:mode> (
+		mem, operands[1], operands[2]));
   DONE;
 })
 
diff --git a/gcc/config/aarch64/iterators.md b/gcc/config/aarch64/iterators.md
index 12c626f..bab0834 100644
--- a/gcc/config/aarch64/iterators.md
+++ b/gcc/config/aarch64/iterators.md
@@ -574,6 +574,9 @@ 
 
 (define_mode_attr Vendreg [(OI "T") (CI "U") (XI "V")])
 
+;; This is both the number of Q-Registers needed to hold the corresponding
+;; opaque large integer mode, and the number of elements touched by the
+;; ld..._lane and st..._lane operations.
 (define_mode_attr nregs [(OI "2") (CI "3") (XI "4")])
 
 (define_mode_attr VRL2 [(V8QI "V32QI") (V4HI "V16HI")