From: Jiahao Xu <xujiahao@loongson.cn>
Date: Fri, 5 Jan 2024 07:37:13 +0000 (+0800)
Subject: LoongArch: Improve lasx_xvpermi_q_<LASX:mode> insn pattern
X-Git-Tag: basepoints/gcc-15~3171
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=7b158e036a95b1ab40793dd53bed7dbd770ffdaf;p=thirdparty%2Fgcc.git

LoongArch: Improve lasx_xvpermi_q_<LASX:mode> insn pattern

For instruction xvpermi.q, unused bits in operands[3] need be set to 0 to avoid
causing undefined behavior on LA464.

gcc/ChangeLog:

	* config/loongarch/lasx.md: Set the unused bits in operand[3] to 0.

gcc/testsuite/ChangeLog:

	* gcc.target/loongarch/vector/lasx/lasx-xvpremi.c: Removed.
	* gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c: New test.
---

diff --git a/gcc/config/loongarch/lasx.md b/gcc/config/loongarch/lasx.md
index cabf16a8ca0a..6c7e373f7c8d 100644
--- a/gcc/config/loongarch/lasx.md
+++ b/gcc/config/loongarch/lasx.md
@@ -635,6 +635,8 @@
    (set_attr "mode" "<MODE>")])
 
 ;; xvpermi.q
+;; Unused bits in operands[3] need be set to 0 to avoid
+;; causing undefined behavior on LA464.
 (define_insn "lasx_xvpermi_q_<LASX:mode>"
   [(set (match_operand:LASX 0 "register_operand" "=f")
 	(unspec:LASX
@@ -643,7 +645,12 @@
 	   (match_operand     3 "const_uimm8_operand")]
 	  UNSPEC_LASX_XVPERMI_Q))]
   "ISA_HAS_LASX"
-  "xvpermi.q\t%u0,%u2,%3"
+{
+  int mask = 0x33;
+  mask &= INTVAL (operands[3]);
+  operands[3] = GEN_INT (mask);
+  return "xvpermi.q\t%u0,%u2,%3";
+}
   [(set_attr "type" "simd_splat")
    (set_attr "mode" "<MODE>")])
 
diff --git a/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c
new file mode 100644
index 000000000000..dbc29d2fb22c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpermi_q.c
@@ -0,0 +1,64 @@
+/* { dg-options "-mlasx -w -fno-strict-aliasing" } */
+#include "../simd_correctness_check.h"
+#include <lasxintrin.h>
+
+int
+main ()
+{
+  __m256i __m256i_op0, __m256i_op1, __m256i_op2, __m256i_out, __m256i_result;
+  __m256 __m256_op0, __m256_op1, __m256_op2, __m256_out, __m256_result;
+  __m256d __m256d_op0, __m256d_op1, __m256d_op2, __m256d_out, __m256d_result;
+
+  int int_op0, int_op1, int_op2, int_out, int_result, i = 1, fail;
+  long int long_op0, long_op1, long_op2, lont_out, lont_result;
+  long int long_int_out, long_int_result;
+  unsigned int unsigned_int_out, unsigned_int_result;
+  unsigned long int unsigned_long_int_out, unsigned_long_int_result;
+
+  *((unsigned long*)& __m256i_op0[3]) = 0x7fe37fe3001d001d;
+  *((unsigned long*)& __m256i_op0[2]) = 0x7fff7fff7fff0000;
+  *((unsigned long*)& __m256i_op0[1]) = 0x7fe37fe3001d001d;
+  *((unsigned long*)& __m256i_op0[0]) = 0x7fff7fff7fff0000;
+  *((unsigned long*)& __m256i_op1[3]) = 0x7575757575757575;
+  *((unsigned long*)& __m256i_op1[2]) = 0x7575757575757575;
+  *((unsigned long*)& __m256i_op1[1]) = 0x7575757575757575;
+  *((unsigned long*)& __m256i_op1[0]) = 0x7575757575757575;
+  *((unsigned long*)& __m256i_result[3]) = 0x7fe37fe3001d001d;
+  *((unsigned long*)& __m256i_result[2]) = 0x7fff7fff7fff0000;
+  *((unsigned long*)& __m256i_result[1]) = 0x7fe37fe3001d001d;
+  *((unsigned long*)& __m256i_result[0]) = 0x7fff7fff7fff0000;
+  __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0x2a);
+  ASSERTEQ_64 (__LINE__, __m256i_result, __m256i_out);
+
+  *((unsigned long*)& __m256i_op0[3]) = 0x0000000000000000;
+  *((unsigned long*)& __m256i_op0[2]) = 0x000000000019001c;
+  *((unsigned long*)& __m256i_op0[1]) = 0x0000000000000000;
+  *((unsigned long*)& __m256i_op0[0]) = 0x000000000019001c;
+  *((unsigned long*)& __m256i_op1[3]) = 0x0000000000000000;
+  *((unsigned long*)& __m256i_op1[2]) = 0x00000000000001fe;
+  *((unsigned long*)& __m256i_op1[1]) = 0x0000000000000000;
+  *((unsigned long*)& __m256i_op1[0]) = 0x00000000000001fe;
+  *((unsigned long*)& __m256i_result[3]) = 0x0000000000000000;
+  *((unsigned long*)& __m256i_result[2]) = 0x000000000019001c;
+  *((unsigned long*)& __m256i_result[1]) = 0x0000000000000000;
+  *((unsigned long*)& __m256i_result[0]) = 0x00000000000001fe;
+  __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0xb9);
+  ASSERTEQ_64 (__LINE__, __m256i_result, __m256i_out);
+
+  *((unsigned long*)& __m256i_op0[3]) = 0x00ff00ff00ff00ff;
+  *((unsigned long*)& __m256i_op0[2]) = 0x00ff00ff00ff00ff;
+  *((unsigned long*)& __m256i_op0[1]) = 0x00ff00ff00ff00ff;
+  *((unsigned long*)& __m256i_op0[0]) = 0x00ff00ff00ff00ff;
+  *((unsigned long*)& __m256i_op1[3]) = 0xffffffffffffffff;
+  *((unsigned long*)& __m256i_op1[2]) = 0xffff0000ffff0000;
+  *((unsigned long*)& __m256i_op1[1]) = 0xffffffffffffffff;
+  *((unsigned long*)& __m256i_op1[0]) = 0xffff0000ffff0000;
+  *((unsigned long*)& __m256i_result[3]) = 0xffffffffffffffff;
+  *((unsigned long*)& __m256i_result[2]) = 0xffff0000ffff0000;
+  *((unsigned long*)& __m256i_result[1]) = 0x00ff00ff00ff00ff;
+  *((unsigned long*)& __m256i_result[0]) = 0x00ff00ff00ff00ff;
+  __m256i_out = __lasx_xvpermi_q (__m256i_op0, __m256i_op1, 0xca);
+  ASSERTEQ_64 (__LINE__, __m256i_result, __m256i_out);
+
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpremi.c b/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpremi.c
deleted file mode 100644
index e9fc1d7d3b87..000000000000
--- a/gcc/testsuite/gcc.target/loongarch/vector/lasx/lasx-xvpremi.c
+++ /dev/null
@@ -1,19 +0,0 @@
-/* { dg-options "-mlasx -w -fno-strict-aliasing" } */
-#include "../simd_correctness_check.h"
-#include <lasxintrin.h>
-
-int
-main ()
-{
-  __m256i __m256i_op0, __m256i_op1, __m256i_op2, __m256i_out, __m256i_result;
-  __m256 __m256_op0, __m256_op1, __m256_op2, __m256_out, __m256_result;
-  __m256d __m256d_op0, __m256d_op1, __m256d_op2, __m256d_out, __m256d_result;
-
-  int int_op0, int_op1, int_op2, int_out, int_result, i = 1, fail;
-  long int long_op0, long_op1, long_op2, lont_out, lont_result;
-  long int long_int_out, long_int_result;
-  unsigned int unsigned_int_out, unsigned_int_result;
-  unsigned long int unsigned_long_int_out, unsigned_long_int_result;
-
-  return 0;
-}