[PATCH v1 1/2] LoongArch: Accelerate optimization of scalar signed/unsigned popcount.

[PATCH v1 1/2] LoongArch: Accelerate optimization of scalar signed/unsigned popcount.

[Li Wei]

In LoongArch, the vector popcount has corresponding instructions, while
the scalar does not. Currently, the scalar popcount is calculated
through a loop, and the value of a non-power of two needs to be iterated
several times, so the vector popcount instruction is considered for
optimization.

gcc/ChangeLog:

	* config/loongarch/loongarch.md (v2di): Used to simplify the
	  following templates.
	(popcount<mode>2): New.

gcc/testsuite/ChangeLog:

	* gcc.target/loongarch/popcnt.c: New test.
	* gcc.target/loongarch/popcount.c: New test.
---
 gcc/config/loongarch/loongarch.md             | 27 +++++++++++-
 gcc/testsuite/gcc.target/loongarch/popcnt.c   | 41 +++++++++++++++++++
 gcc/testsuite/gcc.target/loongarch/popcount.c | 17 ++++++++
 3 files changed, 83 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/loongarch/popcnt.c
 create mode 100644 gcc/testsuite/gcc.target/loongarch/popcount.c

diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
index cd4ed495697..c440d9c348f 100644
--- a/gcc/config/loongarch/loongarch.md
+++ b/gcc/config/loongarch/loongarch.md
@@ -1515,7 +1515,30 @@ (define_insn "truncdfsf2"
    (set_attr "cnv_mode"	"D2S")
    (set_attr "mode" "SF")])
 
-\f
+;; In vector registers, popcount can be implemented directly through
+;; the vector instruction [X]VPCNT.  For GP registers, we can implement
+;; it through the following method.  Compared with loop implementation
+;; of popcount, the following method has better performance.
+
+;; This attribute used for get connection of scalar mode and corresponding
+;; vector mode.
+(define_mode_attr cntmap [(SI "v4si") (DI "v2di")])
+
+(define_expand "popcount<mode>2"
+  [(set (match_operand:GPR 0 "register_operand")
+	(popcount:GPR (match_operand:GPR 1 "register_operand")))]
+  "ISA_HAS_LSX"
+{
+  rtx in = operands[1];
+  rtx out = operands[0];
+  rtx vreg = <MODE>mode == SImode ? gen_reg_rtx (V4SImode) :
+				    gen_reg_rtx (V2DImode);
+  emit_insn (gen_lsx_vinsgr2vr_<size> (vreg, in, vreg, GEN_INT (1)));
+  emit_insn (gen_popcount<cntmap>2 (vreg, vreg));
+  emit_insn (gen_lsx_vpickve2gr_<size> (out, vreg, GEN_INT (0)));
+  DONE;
+})
+
 ;;
 ;;  ....................
 ;;
@@ -3882,7 +3905,7 @@ (define_peephole2
 		   (any_extend:SI (match_dup 3)))])]
   "")
 
-\f
+
 
 (define_mode_iterator QHSD [QI HI SI DI])
 
diff --git a/gcc/testsuite/gcc.target/loongarch/popcnt.c b/gcc/testsuite/gcc.target/loongarch/popcnt.c
new file mode 100644
index 00000000000..a10fca42092
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/popcnt.c
@@ -0,0 +1,41 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mlsx" } */
+/* { dg-final { scan-assembler-not {popcount} } } */
+/* { dg-final { scan-assembler-times "vpcnt.d" 2 { target { loongarch64*-*-* } } } } */
+/* { dg-final { scan-assembler-times "vpcnt.w" 4 { target { loongarch64*-*-* } } } } */
+
+int
+foo (int x)
+{
+  return __builtin_popcount (x);
+}
+
+long
+foo1 (long x)
+{
+  return __builtin_popcountl (x);
+}
+
+long long
+foo2 (long long x)
+{
+  return __builtin_popcountll (x);
+}
+
+int
+foo3 (int *p)
+{
+  return __builtin_popcount (*p);
+}
+
+unsigned
+foo4 (int x)
+{
+  return __builtin_popcount (x);
+}
+
+unsigned long
+foo5 (int x)
+{
+  return __builtin_popcount (x);
+}
diff --git a/gcc/testsuite/gcc.target/loongarch/popcount.c b/gcc/testsuite/gcc.target/loongarch/popcount.c
new file mode 100644
index 00000000000..390ff067617
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/popcount.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mlsx -fdump-tree-optimized" } */
+/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 1 "optimized" } } */
+
+int
+PopCount (long b)
+{
+  int c = 0;
+
+  while (b)
+    {
+      b &= b - 1;
+      c++;
+    }
+
+  return c;
+}
-- 
2.31.1

Re: [pushed][PATCH v1 1/2] LoongArch: Accelerate optimization of scalar signed/unsigned popcount.

[chenglulu]

Pushed to r14-6072.

在 2023/11/28 下午3:38, Li Wei 写道:
> In LoongArch, the vector popcount has corresponding instructions, while
> the scalar does not. Currently, the scalar popcount is calculated
> through a loop, and the value of a non-power of two needs to be iterated
> several times, so the vector popcount instruction is considered for
> optimization.
>
> gcc/ChangeLog:
>
> 	* config/loongarch/loongarch.md (v2di): Used to simplify the
> 	  following templates.
> 	(popcount<mode>2): New.
>
> gcc/testsuite/ChangeLog:
>
> 	* gcc.target/loongarch/popcnt.c: New test.
> 	* gcc.target/loongarch/popcount.c: New test.
> ---
>   gcc/config/loongarch/loongarch.md             | 27 +++++++++++-
>   gcc/testsuite/gcc.target/loongarch/popcnt.c   | 41 +++++++++++++++++++
>   gcc/testsuite/gcc.target/loongarch/popcount.c | 17 ++++++++
>   3 files changed, 83 insertions(+), 2 deletions(-)
>   create mode 100644 gcc/testsuite/gcc.target/loongarch/popcnt.c
>   create mode 100644 gcc/testsuite/gcc.target/loongarch/popcount.c
>
> diff --git a/gcc/config/loongarch/loongarch.md b/gcc/config/loongarch/loongarch.md
> index cd4ed495697..c440d9c348f 100644
> --- a/gcc/config/loongarch/loongarch.md
> +++ b/gcc/config/loongarch/loongarch.md
> @@ -1515,7 +1515,30 @@ (define_insn "truncdfsf2"
>      (set_attr "cnv_mode"	"D2S")
>      (set_attr "mode" "SF")])
>   
> -\f
> +;; In vector registers, popcount can be implemented directly through
> +;; the vector instruction [X]VPCNT.  For GP registers, we can implement
> +;; it through the following method.  Compared with loop implementation
> +;; of popcount, the following method has better performance.
> +
> +;; This attribute used for get connection of scalar mode and corresponding
> +;; vector mode.
> +(define_mode_attr cntmap [(SI "v4si") (DI "v2di")])
> +
> +(define_expand "popcount<mode>2"
> +  [(set (match_operand:GPR 0 "register_operand")
> +	(popcount:GPR (match_operand:GPR 1 "register_operand")))]
> +  "ISA_HAS_LSX"
> +{
> +  rtx in = operands[1];
> +  rtx out = operands[0];
> +  rtx vreg = <MODE>mode == SImode ? gen_reg_rtx (V4SImode) :
> +				    gen_reg_rtx (V2DImode);
> +  emit_insn (gen_lsx_vinsgr2vr_<size> (vreg, in, vreg, GEN_INT (1)));
> +  emit_insn (gen_popcount<cntmap>2 (vreg, vreg));
> +  emit_insn (gen_lsx_vpickve2gr_<size> (out, vreg, GEN_INT (0)));
> +  DONE;
> +})
> +
>   ;;
>   ;;  ....................
>   ;;
> @@ -3882,7 +3905,7 @@ (define_peephole2
>   		   (any_extend:SI (match_dup 3)))])]
>     "")
>   
> -\f
> +
>   
>   (define_mode_iterator QHSD [QI HI SI DI])
>   
> diff --git a/gcc/testsuite/gcc.target/loongarch/popcnt.c b/gcc/testsuite/gcc.target/loongarch/popcnt.c
> new file mode 100644
> index 00000000000..a10fca42092
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/loongarch/popcnt.c
> @@ -0,0 +1,41 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mlsx" } */
> +/* { dg-final { scan-assembler-not {popcount} } } */
> +/* { dg-final { scan-assembler-times "vpcnt.d" 2 { target { loongarch64*-*-* } } } } */
> +/* { dg-final { scan-assembler-times "vpcnt.w" 4 { target { loongarch64*-*-* } } } } */
> +
> +int
> +foo (int x)
> +{
> +  return __builtin_popcount (x);
> +}
> +
> +long
> +foo1 (long x)
> +{
> +  return __builtin_popcountl (x);
> +}
> +
> +long long
> +foo2 (long long x)
> +{
> +  return __builtin_popcountll (x);
> +}
> +
> +int
> +foo3 (int *p)
> +{
> +  return __builtin_popcount (*p);
> +}
> +
> +unsigned
> +foo4 (int x)
> +{
> +  return __builtin_popcount (x);
> +}
> +
> +unsigned long
> +foo5 (int x)
> +{
> +  return __builtin_popcount (x);
> +}
> diff --git a/gcc/testsuite/gcc.target/loongarch/popcount.c b/gcc/testsuite/gcc.target/loongarch/popcount.c
> new file mode 100644
> index 00000000000..390ff067617
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/loongarch/popcount.c
> @@ -0,0 +1,17 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mlsx -fdump-tree-optimized" } */
> +/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 1 "optimized" } } */
> +
> +int
> +PopCount (long b)
> +{
> +  int c = 0;
> +
> +  while (b)
> +    {
> +      b &= b - 1;
> +      c++;
> +    }
> +
> +  return c;
> +}