From: Xi Ruoyao <xry111@xry111.site>
Date: Mon, 20 Jan 2025 15:13:19 +0000 (+0800)
Subject: LoongArch: Implement [su]dot_prod* for LSX and LASX modes
X-Git-Tag: basepoints/gcc-16~1930
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=cef5f23adb6f9f052d03286ad8ccf352eefccf86;p=thirdparty%2Fgcc.git

LoongArch: Implement [su]dot_prod* for LSX and LASX modes

Despite it's just a special case of "a widening product of which the
result used for reduction," having these standard names allows to
recognize the dot product pattern earlier and it may be beneficial to
optimization.  Also fix some test failures with the test cases:

- gcc.dg/vect/vect-reduc-chain-2.c
- gcc.dg/vect/vect-reduc-chain-3.c
- gcc.dg/vect/vect-reduc-chain-dot-slp-3.c
- gcc.dg/vect/vect-reduc-chain-dot-slp-4.c

gcc/ChangeLog:

	* config/loongarch/simd.md (wvec_half): New define_mode_attr.
	(<su>dot_prod<wvec_half><mode>): New define_expand.

gcc/testsuite/ChangeLog:

	* gcc.target/loongarch/wide-mul-reduc-2.c (dg-final): Scan
	DOT_PROD_EXPR in optimized tree.
---

diff --git a/gcc/config/loongarch/simd.md b/gcc/config/loongarch/simd.md
index 661f5dc8dda..45d2bcaec2e 100644
--- a/gcc/config/loongarch/simd.md
+++ b/gcc/config/loongarch/simd.md
@@ -90,6 +90,12 @@
 			     (V8HI "V4SI") (V16HI "V8SI")
 			     (V16QI "V8HI") (V32QI "V16HI")])
 
+;; Lower-case version.
+(define_mode_attr wvec_half [(V2DI "v1ti") (V4DI "v2ti")
+			     (V4SI "v2di") (V8SI "v4di")
+			     (V8HI "v4si") (V16HI "v8si")
+			     (V16QI "v8hi") (V32QI "v16hi")])
+
 ;; Integer vector modes with the same length and unit size as a mode.
 (define_mode_attr VIMODE [(V2DI "V2DI") (V4SI "V4SI")
 			  (V8HI "V8HI") (V16QI "V16QI")
@@ -786,6 +792,29 @@
   DONE;
 })
 
+(define_expand "<su>dot_prod<wvec_half><mode>"
+  [(match_operand:<WVEC_HALF> 0 "register_operand" "=f,f")
+   (match_operand:IVEC	      1 "register_operand" " f,f")
+   (match_operand:IVEC	      2 "register_operand" " f,f")
+   (match_operand:<WVEC_HALF> 3 "reg_or_0_operand" " 0,YG")
+   (any_extend (const_int 0))]
+  ""
+{
+  auto [op0, op1, op2, op3] = operands;
+
+  if (op3 == CONST0_RTX (<WVEC_HALF>mode))
+    emit_insn (
+      gen_<simd_isa>_<x>vmulwev_<simdfmt_w>_<simdfmt><u> (op0, op1, op2));
+  else
+    emit_insn (
+      gen_<simd_isa>_<x>vmaddwev_<simdfmt_w>_<simdfmt><u> (op0, op3, op1,
+							   op2));
+
+  emit_insn (
+    gen_<simd_isa>_<x>vmaddwod_<simdfmt_w>_<simdfmt><u> (op0, op0, op1, op2));
+  DONE;
+})
+
 (define_insn "simd_maddw_evod_<mode>_hetero"
   [(set (match_operand:<WVEC_HALF> 0 "register_operand" "=f")
 	(plus:<WVEC_HALF>
diff --git a/gcc/testsuite/gcc.target/loongarch/wide-mul-reduc-2.c b/gcc/testsuite/gcc.target/loongarch/wide-mul-reduc-2.c
index 07a7601888a..61e92e58fc3 100644
--- a/gcc/testsuite/gcc.target/loongarch/wide-mul-reduc-2.c
+++ b/gcc/testsuite/gcc.target/loongarch/wide-mul-reduc-2.c
@@ -1,6 +1,7 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -mlasx" } */
+/* { dg-options "-O2 -mlasx -fdump-tree-optimized" } */
 /* { dg-final { scan-assembler "xvmaddw(ev|od)\\.d\\.w" } } */
+/* { dg-final { scan-tree-dump "DOT_PROD_EXPR" "optimized" } } */
 
 typedef __INT32_TYPE__ i32;
 typedef __INT64_TYPE__ i64;