[v1] RISC-V: Add xfail test case for highpart register overlap of vx/vf widen

From: Pan Li <pan2.li@intel.com>

We reverted below patch for register group overlap, add the related
insn test and mark it as xfail.  And we will remove the xfail
after we support the register overlap in GCC-15.

a23415d7572 RISC-V: Support highpart register overlap for widen vx/vf instructions

The below test suites are passed.
* The rv64gcv fully regression test.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/pr112431-22.c: New test.
	* gcc.target/riscv/rvv/base/pr112431-23.c: New test.
	* gcc.target/riscv/rvv/base/pr112431-24.c: New test.
	* gcc.target/riscv/rvv/base/pr112431-25.c: New test.
	* gcc.target/riscv/rvv/base/pr112431-26.c: New test.
	* gcc.target/riscv/rvv/base/pr112431-27.c: New test.

Signed-off-by: Pan Li <pan2.li@intel.com>
---
 .../gcc.target/riscv/rvv/base/pr112431-22.c   | 188 ++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr112431-23.c   | 119 +++++++++++
 .../gcc.target/riscv/rvv/base/pr112431-24.c   |  86 ++++++++
 .../gcc.target/riscv/rvv/base/pr112431-25.c   | 104 ++++++++++
 .../gcc.target/riscv/rvv/base/pr112431-26.c   |  68 +++++++
 .../gcc.target/riscv/rvv/base/pr112431-27.c   |  51 +++++
 6 files changed, 616 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-22.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-23.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-24.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-25.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-26.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-27.c

LGTM



juzhe.zhong@rivai.ai
 
From: pan2.li
Date: 2024-04-21 13:01
To: gcc-patches
CC: juzhe.zhong; kito.cheng; rdapp.gcc; Pan Li
Subject: [PATCH v1] RISC-V: Add xfail test case for highpart register overlap of vx/vf widen
From: Pan Li <pan2.li@intel.com>
 
We reverted below patch for register group overlap, add the related
insn test and mark it as xfail.  And we will remove the xfail
after we support the register overlap in GCC-15.
 
a23415d7572 RISC-V: Support highpart register overlap for widen vx/vf instructions
 
The below test suites are passed.
* The rv64gcv fully regression test.
 
gcc/testsuite/ChangeLog:
 
* gcc.target/riscv/rvv/base/pr112431-22.c: New test.
* gcc.target/riscv/rvv/base/pr112431-23.c: New test.
* gcc.target/riscv/rvv/base/pr112431-24.c: New test.
* gcc.target/riscv/rvv/base/pr112431-25.c: New test.
* gcc.target/riscv/rvv/base/pr112431-26.c: New test.
* gcc.target/riscv/rvv/base/pr112431-27.c: New test.
 
Signed-off-by: Pan Li <pan2.li@intel.com>
---
.../gcc.target/riscv/rvv/base/pr112431-22.c   | 188 ++++++++++++++++++
.../gcc.target/riscv/rvv/base/pr112431-23.c   | 119 +++++++++++
.../gcc.target/riscv/rvv/base/pr112431-24.c   |  86 ++++++++
.../gcc.target/riscv/rvv/base/pr112431-25.c   | 104 ++++++++++
.../gcc.target/riscv/rvv/base/pr112431-26.c   |  68 +++++++
.../gcc.target/riscv/rvv/base/pr112431-27.c   |  51 +++++
6 files changed, 616 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-22.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-23.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-24.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-25.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-26.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-27.c
 
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-22.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-22.c
new file mode 100644
index 00000000000..ac56703c75c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-22.c
@@ -0,0 +1,188 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+   size_t sum5, size_t sum6, size_t sum7, size_t sum8, size_t sum9,
+   size_t sum10, size_t sum11, size_t sum12, size_t sum13, size_t sum14,
+   size_t sum15)
+{
+  return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7 + sum8 + sum9
+ + sum10 + sum11 + sum12 + sum13 + sum14 + sum15;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vint8m1_t v0 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v1 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v2 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v3 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v4 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v5 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v6 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v7 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v8 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v9 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v10 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v11 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v12 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v13 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v14 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v15 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      
+      asm volatile("nop" ::: "memory");
+      vint16m2_t vw0 = __riscv_vwadd_vx_i16m2 (v0, 33, vl);
+      vint16m2_t vw1 = __riscv_vwadd_vx_i16m2 (v1, 33, vl);
+      vint16m2_t vw2 = __riscv_vwadd_vx_i16m2 (v2, 33, vl);
+      vint16m2_t vw3 = __riscv_vwadd_vx_i16m2 (v3, 33, vl);
+      vint16m2_t vw4 = __riscv_vwadd_vx_i16m2 (v4, 33, vl);
+      vint16m2_t vw5 = __riscv_vwadd_vx_i16m2 (v5, 33, vl);
+      vint16m2_t vw6 = __riscv_vwadd_vx_i16m2 (v6, 33, vl);
+      vint16m2_t vw7 = __riscv_vwadd_vx_i16m2 (v7, 33, vl);
+      vint16m2_t vw8 = __riscv_vwadd_vx_i16m2 (v8, 33, vl);
+      vint16m2_t vw9 = __riscv_vwadd_vx_i16m2 (v9, 33, vl);
+      vint16m2_t vw10 = __riscv_vwadd_vx_i16m2 (v10, 33, vl);
+      vint16m2_t vw11 = __riscv_vwadd_vx_i16m2 (v11, 33, vl);
+      vint16m2_t vw12 = __riscv_vwadd_vx_i16m2 (v12, 33, vl);
+      vint16m2_t vw13 = __riscv_vwadd_vx_i16m2 (v13, 33, vl);
+      vint16m2_t vw14 = __riscv_vwadd_vx_i16m2 (v14, 33, vl);
+      vint16m2_t vw15 = __riscv_vwadd_vx_i16m2 (v15, 33, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i16m2_i16 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i16m2_i16 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i16m2_i16 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i16m2_i16 (vw3);
+      size_t sum4 = __riscv_vmv_x_s_i16m2_i16 (vw4);
+      size_t sum5 = __riscv_vmv_x_s_i16m2_i16 (vw5);
+      size_t sum6 = __riscv_vmv_x_s_i16m2_i16 (vw6);
+      size_t sum7 = __riscv_vmv_x_s_i16m2_i16 (vw7);
+      size_t sum8 = __riscv_vmv_x_s_i16m2_i16 (vw8);
+      size_t sum9 = __riscv_vmv_x_s_i16m2_i16 (vw9);
+      size_t sum10 = __riscv_vmv_x_s_i16m2_i16 (vw10);
+      size_t sum11 = __riscv_vmv_x_s_i16m2_i16 (vw11);
+      size_t sum12 = __riscv_vmv_x_s_i16m2_i16 (vw12);
+      size_t sum13 = __riscv_vmv_x_s_i16m2_i16 (vw13);
+      size_t sum14 = __riscv_vmv_x_s_i16m2_i16 (vw14);
+      size_t sum15 = __riscv_vmv_x_s_i16m2_i16 (vw15);
+
+      sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7, sum8,
+        sum9, sum10, sum11, sum12, sum13, sum14, sum15);
+    }
+  return sum;
+}
+
+size_t
+foo2 (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vint8m1_t v0 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v1 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v2 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v3 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v4 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v5 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v6 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v7 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v8 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v9 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v10 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v11 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v12 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v13 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v14 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      vint8m1_t v15 = __riscv_vle8_v_i8m1 ((void *) it, vl);
+      it += vl;
+      
+      asm volatile("nop" ::: "memory");
+      vint16m2_t vw0 = __riscv_vwmulsu_vx_i16m2 (v0, 33, vl);
+      vint16m2_t vw1 = __riscv_vwmulsu_vx_i16m2 (v1, 33, vl);
+      vint16m2_t vw2 = __riscv_vwmulsu_vx_i16m2 (v2, 33, vl);
+      vint16m2_t vw3 = __riscv_vwmulsu_vx_i16m2 (v3, 33, vl);
+      vint16m2_t vw4 = __riscv_vwmulsu_vx_i16m2 (v4, 33, vl);
+      vint16m2_t vw5 = __riscv_vwmulsu_vx_i16m2 (v5, 33, vl);
+      vint16m2_t vw6 = __riscv_vwmulsu_vx_i16m2 (v6, 33, vl);
+      vint16m2_t vw7 = __riscv_vwmulsu_vx_i16m2 (v7, 33, vl);
+      vint16m2_t vw8 = __riscv_vwmulsu_vx_i16m2 (v8, 33, vl);
+      vint16m2_t vw9 = __riscv_vwmulsu_vx_i16m2 (v9, 33, vl);
+      vint16m2_t vw10 = __riscv_vwmulsu_vx_i16m2 (v10, 33, vl);
+      vint16m2_t vw11 = __riscv_vwmulsu_vx_i16m2 (v11, 33, vl);
+      vint16m2_t vw12 = __riscv_vwmulsu_vx_i16m2 (v12, 33, vl);
+      vint16m2_t vw13 = __riscv_vwmulsu_vx_i16m2 (v13, 33, vl);
+      vint16m2_t vw14 = __riscv_vwmulsu_vx_i16m2 (v14, 33, vl);
+      vint16m2_t vw15 = __riscv_vwmulsu_vx_i16m2 (v15, 33, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i16m2_i16 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i16m2_i16 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i16m2_i16 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i16m2_i16 (vw3);
+      size_t sum4 = __riscv_vmv_x_s_i16m2_i16 (vw4);
+      size_t sum5 = __riscv_vmv_x_s_i16m2_i16 (vw5);
+      size_t sum6 = __riscv_vmv_x_s_i16m2_i16 (vw6);
+      size_t sum7 = __riscv_vmv_x_s_i16m2_i16 (vw7);
+      size_t sum8 = __riscv_vmv_x_s_i16m2_i16 (vw8);
+      size_t sum9 = __riscv_vmv_x_s_i16m2_i16 (vw9);
+      size_t sum10 = __riscv_vmv_x_s_i16m2_i16 (vw10);
+      size_t sum11 = __riscv_vmv_x_s_i16m2_i16 (vw11);
+      size_t sum12 = __riscv_vmv_x_s_i16m2_i16 (vw12);
+      size_t sum13 = __riscv_vmv_x_s_i16m2_i16 (vw13);
+      size_t sum14 = __riscv_vmv_x_s_i16m2_i16 (vw14);
+      size_t sum15 = __riscv_vmv_x_s_i16m2_i16 (vw15);
+
+      sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7, sum8,
+        sum9, sum10, sum11, sum12, sum13, sum14, sum15);
+    }
+  return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} { xfail riscv*-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-23.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-23.c
new file mode 100644
index 00000000000..f91119307f4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-23.c
@@ -0,0 +1,119 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+   size_t sum5, size_t sum6, size_t sum7)
+{
+  return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vint8m2_t v0 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v1 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v2 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v3 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v4 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v5 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v6 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v7 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+
+      asm volatile("nop" ::: "memory");
+      vint16m4_t vw0 = __riscv_vwadd_vx_i16m4 (v0, 55, vl);
+      vint16m4_t vw1 = __riscv_vwadd_vx_i16m4 (v1, 55, vl);
+      vint16m4_t vw2 = __riscv_vwadd_vx_i16m4 (v2, 55, vl);
+      vint16m4_t vw3 = __riscv_vwadd_vx_i16m4 (v3, 55, vl);
+      vint16m4_t vw4 = __riscv_vwadd_vx_i16m4 (v4, 55, vl);
+      vint16m4_t vw5 = __riscv_vwadd_vx_i16m4 (v5, 55, vl);
+      vint16m4_t vw6 = __riscv_vwadd_vx_i16m4 (v6, 55, vl);
+      vint16m4_t vw7 = __riscv_vwadd_vx_i16m4 (v7, 55, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i16m4_i16 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i16m4_i16 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i16m4_i16 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i16m4_i16 (vw3);
+      size_t sum4 = __riscv_vmv_x_s_i16m4_i16 (vw4);
+      size_t sum5 = __riscv_vmv_x_s_i16m4_i16 (vw5);
+      size_t sum6 = __riscv_vmv_x_s_i16m4_i16 (vw6);
+      size_t sum7 = __riscv_vmv_x_s_i16m4_i16 (vw7);
+
+      sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7);
+    }
+  return sum;
+}
+
+size_t
+foo2 (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vint8m2_t v0 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v1 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v2 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v3 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v4 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v5 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v6 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+      vint8m2_t v7 = __riscv_vle8_v_i8m2 ((void *) it, vl);
+      it += vl;
+
+      asm volatile("nop" ::: "memory");
+      vint16m4_t vw0 = __riscv_vwmulsu_vx_i16m4 (v0, 55, vl);
+      vint16m4_t vw1 = __riscv_vwmulsu_vx_i16m4 (v1, 55, vl);
+      vint16m4_t vw2 = __riscv_vwmulsu_vx_i16m4 (v2, 55, vl);
+      vint16m4_t vw3 = __riscv_vwmulsu_vx_i16m4 (v3, 55, vl);
+      vint16m4_t vw4 = __riscv_vwmulsu_vx_i16m4 (v4, 55, vl);
+      vint16m4_t vw5 = __riscv_vwmulsu_vx_i16m4 (v5, 55, vl);
+      vint16m4_t vw6 = __riscv_vwmulsu_vx_i16m4 (v6, 55, vl);
+      vint16m4_t vw7 = __riscv_vwmulsu_vx_i16m4 (v7, 55, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i16m4_i16 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i16m4_i16 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i16m4_i16 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i16m4_i16 (vw3);
+      size_t sum4 = __riscv_vmv_x_s_i16m4_i16 (vw4);
+      size_t sum5 = __riscv_vmv_x_s_i16m4_i16 (vw5);
+      size_t sum6 = __riscv_vmv_x_s_i16m4_i16 (vw6);
+      size_t sum7 = __riscv_vmv_x_s_i16m4_i16 (vw7);
+
+      sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7);
+    }
+  return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} { xfail riscv*-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-24.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-24.c
new file mode 100644
index 00000000000..bcd60c0a7c3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-24.c
@@ -0,0 +1,86 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3)
+{
+  return sum0 + sum1 + sum2 + sum3;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vint8m4_t v0 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+      vint8m4_t v1 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+      vint8m4_t v2 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+      vint8m4_t v3 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+
+      asm volatile("nop" ::: "memory");
+      vint16m8_t vw0 = __riscv_vwadd_vx_i16m8 (v0, 66, vl);
+      vint16m8_t vw1 = __riscv_vwadd_vx_i16m8 (v1, 66, vl);
+      vint16m8_t vw2 = __riscv_vwadd_vx_i16m8 (v2, 66, vl);
+      vint16m8_t vw3 = __riscv_vwadd_vx_i16m8 (v3, 66, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i16m8_i16 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i16m8_i16 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i16m8_i16 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i16m8_i16 (vw3);
+
+      sum += sumation (sum0, sum1, sum2, sum3);
+    }
+  return sum;
+}
+
+size_t
+foo2 (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vint8m4_t v0 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+      vint8m4_t v1 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+      vint8m4_t v2 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+      vint8m4_t v3 = __riscv_vle8_v_i8m4 ((void *) it, vl);
+      it += vl;
+
+      asm volatile("nop" ::: "memory");
+      vint16m8_t vw0 = __riscv_vwmulsu_vx_i16m8 (v0, 66, vl);
+      vint16m8_t vw1 = __riscv_vwmulsu_vx_i16m8 (v1, 66, vl);
+      vint16m8_t vw2 = __riscv_vwmulsu_vx_i16m8 (v2, 66, vl);
+      vint16m8_t vw3 = __riscv_vwmulsu_vx_i16m8 (v3, 66, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i16m8_i16 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i16m8_i16 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i16m8_i16 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i16m8_i16 (vw3);
+
+      sum += sumation (sum0, sum1, sum2, sum3);
+    }
+  return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} { xfail riscv*-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-25.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-25.c
new file mode 100644
index 00000000000..57a8ef28486
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-25.c
@@ -0,0 +1,104 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+   size_t sum5, size_t sum6, size_t sum7, size_t sum8, size_t sum9,
+   size_t sum10, size_t sum11, size_t sum12, size_t sum13, size_t sum14,
+   size_t sum15)
+{
+  return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7 + sum8 + sum9
+ + sum10 + sum11 + sum12 + sum13 + sum14 + sum15;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vfloat32m1_t v0 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v1 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v2 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v3 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v4 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v5 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v6 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v7 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v8 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v9 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v10 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v11 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v12 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v13 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v14 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      vfloat32m1_t v15 = __riscv_vle32_v_f32m1 ((void *) it, vl);
+      it += vl;
+      
+      asm volatile("nop" ::: "memory");
+      vfloat64m2_t vw0 = __riscv_vfwadd_vf_f64m2 (v0, 33, vl);
+      vfloat64m2_t vw1 = __riscv_vfwadd_vf_f64m2 (v1, 33, vl);
+      vfloat64m2_t vw2 = __riscv_vfwadd_vf_f64m2 (v2, 33, vl);
+      vfloat64m2_t vw3 = __riscv_vfwadd_vf_f64m2 (v3, 33, vl);
+      vfloat64m2_t vw4 = __riscv_vfwadd_vf_f64m2 (v4, 33, vl);
+      vfloat64m2_t vw5 = __riscv_vfwadd_vf_f64m2 (v5, 33, vl);
+      vfloat64m2_t vw6 = __riscv_vfwadd_vf_f64m2 (v6, 33, vl);
+      vfloat64m2_t vw7 = __riscv_vfwadd_vf_f64m2 (v7, 33, vl);
+      vfloat64m2_t vw8 = __riscv_vfwadd_vf_f64m2 (v8, 33, vl);
+      vfloat64m2_t vw9 = __riscv_vfwadd_vf_f64m2 (v9, 33, vl);
+      vfloat64m2_t vw10 = __riscv_vfwadd_vf_f64m2 (v10, 33, vl);
+      vfloat64m2_t vw11 = __riscv_vfwadd_vf_f64m2 (v11, 33, vl);
+      vfloat64m2_t vw12 = __riscv_vfwadd_vf_f64m2 (v12, 33, vl);
+      vfloat64m2_t vw13 = __riscv_vfwadd_vf_f64m2 (v13, 33, vl);
+      vfloat64m2_t vw14 = __riscv_vfwadd_vf_f64m2 (v14, 33, vl);
+      vfloat64m2_t vw15 = __riscv_vfwadd_vf_f64m2 (v15, 33, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vfmv_f_s_f64m2_f64 (vw0);
+      size_t sum1 = __riscv_vfmv_f_s_f64m2_f64 (vw1);
+      size_t sum2 = __riscv_vfmv_f_s_f64m2_f64 (vw2);
+      size_t sum3 = __riscv_vfmv_f_s_f64m2_f64 (vw3);
+      size_t sum4 = __riscv_vfmv_f_s_f64m2_f64 (vw4);
+      size_t sum5 = __riscv_vfmv_f_s_f64m2_f64 (vw5);
+      size_t sum6 = __riscv_vfmv_f_s_f64m2_f64 (vw6);
+      size_t sum7 = __riscv_vfmv_f_s_f64m2_f64 (vw7);
+      size_t sum8 = __riscv_vfmv_f_s_f64m2_f64 (vw8);
+      size_t sum9 = __riscv_vfmv_f_s_f64m2_f64 (vw9);
+      size_t sum10 = __riscv_vfmv_f_s_f64m2_f64 (vw10);
+      size_t sum11 = __riscv_vfmv_f_s_f64m2_f64 (vw11);
+      size_t sum12 = __riscv_vfmv_f_s_f64m2_f64 (vw12);
+      size_t sum13 = __riscv_vfmv_f_s_f64m2_f64 (vw13);
+      size_t sum14 = __riscv_vfmv_f_s_f64m2_f64 (vw14);
+      size_t sum15 = __riscv_vfmv_f_s_f64m2_f64 (vw15);
+
+      sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7, sum8,
+        sum9, sum10, sum11, sum12, sum13, sum14, sum15);
+    }
+  return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} { xfail riscv*-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-26.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-26.c
new file mode 100644
index 00000000000..0f05e2b2e1d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-26.c
@@ -0,0 +1,68 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3, size_t sum4,
+   size_t sum5, size_t sum6, size_t sum7)
+{
+  return sum0 + sum1 + sum2 + sum3 + sum4 + sum5 + sum6 + sum7;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vfloat32m2_t v0 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v1 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v2 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v3 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v4 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v5 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v6 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      vfloat32m2_t v7 = __riscv_vle32_v_f32m2 ((void *) it, vl);
+      it += vl;
+      
+      asm volatile("nop" ::: "memory");
+      vfloat64m4_t vw0 = __riscv_vfwadd_vf_f64m4 (v0, 33, vl);
+      vfloat64m4_t vw1 = __riscv_vfwadd_vf_f64m4 (v1, 33, vl);
+      vfloat64m4_t vw2 = __riscv_vfwadd_vf_f64m4 (v2, 33, vl);
+      vfloat64m4_t vw3 = __riscv_vfwadd_vf_f64m4 (v3, 33, vl);
+      vfloat64m4_t vw4 = __riscv_vfwadd_vf_f64m4 (v4, 33, vl);
+      vfloat64m4_t vw5 = __riscv_vfwadd_vf_f64m4 (v5, 33, vl);
+      vfloat64m4_t vw6 = __riscv_vfwadd_vf_f64m4 (v6, 33, vl);
+      vfloat64m4_t vw7 = __riscv_vfwadd_vf_f64m4 (v7, 33, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vfmv_f_s_f64m4_f64 (vw0);
+      size_t sum1 = __riscv_vfmv_f_s_f64m4_f64 (vw1);
+      size_t sum2 = __riscv_vfmv_f_s_f64m4_f64 (vw2);
+      size_t sum3 = __riscv_vfmv_f_s_f64m4_f64 (vw3);
+      size_t sum4 = __riscv_vfmv_f_s_f64m4_f64 (vw4);
+      size_t sum5 = __riscv_vfmv_f_s_f64m4_f64 (vw5);
+      size_t sum6 = __riscv_vfmv_f_s_f64m4_f64 (vw6);
+      size_t sum7 = __riscv_vfmv_f_s_f64m4_f64 (vw7);
+
+      sum += sumation (sum0, sum1, sum2, sum3, sum4, sum5, sum6, sum7);
+    }
+  return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} { xfail riscv*-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-27.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-27.c
new file mode 100644
index 00000000000..d640bcf74ba
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-27.c
@@ -0,0 +1,51 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+size_t __attribute__ ((noinline))
+sumation (size_t sum0, size_t sum1, size_t sum2, size_t sum3)
+{
+  return sum0 + sum1 + sum2 + sum3;
+}
+
+size_t
+foo (char const *buf, size_t len)
+{
+  size_t sum = 0;
+  size_t vl = __riscv_vsetvlmax_e8m8 ();
+  size_t step = vl * 4;
+  const char *it = buf, *end = buf + len;
+  for (; it + step <= end;)
+    {
+      vfloat32m4_t v0 = __riscv_vle32_v_f32m4 ((void *) it, vl);
+      it += vl;
+      vfloat32m4_t v1 = __riscv_vle32_v_f32m4 ((void *) it, vl);
+      it += vl;
+      vfloat32m4_t v2 = __riscv_vle32_v_f32m4 ((void *) it, vl);
+      it += vl;
+      vfloat32m4_t v3 = __riscv_vle32_v_f32m4 ((void *) it, vl);
+      it += vl;
+      
+      asm volatile("nop" ::: "memory");
+      vfloat64m8_t vw0 = __riscv_vfwadd_vf_f64m8 (v0, 33, vl);
+      vfloat64m8_t vw1 = __riscv_vfwadd_vf_f64m8 (v1, 33, vl);
+      vfloat64m8_t vw2 = __riscv_vfwadd_vf_f64m8 (v2, 33, vl);
+      vfloat64m8_t vw3 = __riscv_vfwadd_vf_f64m8 (v3, 33, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vfmv_f_s_f64m8_f64 (vw0);
+      size_t sum1 = __riscv_vfmv_f_s_f64m8_f64 (vw1);
+      size_t sum2 = __riscv_vfmv_f_s_f64m8_f64 (vw2);
+      size_t sum3 = __riscv_vfmv_f_s_f64m8_f64 (vw3);
+
+      sum += sumation (sum0, sum1, sum2, sum3);
+    }
+  return sum;
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv2r} } } */
+/* { dg-final { scan-assembler-not {vmv4r} } } */
+/* { dg-final { scan-assembler-not {vmv8r} } } */
+/* { dg-final { scan-assembler-not {csrr} { xfail riscv*-*-* } } } */

Committed, thanks Juzhe.

Pan

From: 钟居哲 <juzhe.zhong@rivai.ai>
Sent: Monday, April 22, 2024 6:38 AM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: kito.cheng <kito.cheng@gmail.com>; rdapp.gcc <rdapp.gcc@gmail.com>; Li, Pan2 <pan2.li@intel.com>
Subject: Re: [PATCH v1] RISC-V: Add xfail test case for highpart register overlap of vx/vf widen

LGTM