RE: [PATCH v1] RISC-V: Add xfail test case for widening register overlap of vf4/vf8

["Li, Pan2" <pan2.li@intel.com>]

[-- Attachment #1: Type: text/plain, Size: 8841 bytes --]

Committed, thanks Juzhe.

Pan

From: juzhe.zhong@rivai.ai <juzhe.zhong@rivai.ai>
Sent: Monday, April 22, 2024 11:49 AM
To: Li, Pan2 <pan2.li@intel.com>; gcc-patches <gcc-patches@gcc.gnu.org>
Cc: kito.cheng <kito.cheng@gmail.com>; Robin Dapp <rdapp.gcc@gmail.com>; Li, Pan2 <pan2.li@intel.com>
Subject: Re: [PATCH v1] RISC-V: Add xfail test case for widening register overlap of vf4/vf8

LGTM.

________________________________
juzhe.zhong@rivai.ai<mailto:juzhe.zhong@rivai.ai>

From: pan2.li<mailto:pan2.li@intel.com>
Date: 2024-04-22 11:19
To: gcc-patches<mailto:gcc-patches@gcc.gnu.org>
CC: juzhe.zhong<mailto:juzhe.zhong@rivai.ai>; kito.cheng<mailto:kito.cheng@gmail.com>; rdapp.gcc<mailto:rdapp.gcc@gmail.com>; Pan Li<mailto:pan2.li@intel.com>
Subject: [PATCH v1] RISC-V: Add xfail test case for widening register overlap of vf4/vf8
From: Pan Li <pan2.li@intel.com<mailto: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.

303195e2a6b RISC-V: Support widening register overlap for vf4/vf8

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

gcc/testsuite/ChangeLog:

* gcc.target/riscv/rvv/base/pr112431-16.c: New test.
* gcc.target/riscv/rvv/base/pr112431-17.c: New test.
* gcc.target/riscv/rvv/base/pr112431-18.c: New test.

Signed-off-by: Pan Li <pan2.li@intel.com<mailto:pan2.li@intel.com>>
---
.../gcc.target/riscv/rvv/base/pr112431-16.c   | 68 +++++++++++++++++++
.../gcc.target/riscv/rvv/base/pr112431-17.c   | 51 ++++++++++++++
.../gcc.target/riscv/rvv/base/pr112431-18.c   | 51 ++++++++++++++
3 files changed, 170 insertions(+)
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-16.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-17.c
create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-18.c

diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-16.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-16.c
new file mode 100644
index 00000000000..42d11611d98
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-16.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;)
+    {
+      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;
+
+      asm volatile("nop" ::: "memory");
+      vint32m4_t vw0 = __riscv_vsext_vf4_i32m4 (v0, vl);
+      vint32m4_t vw1 = __riscv_vsext_vf4_i32m4 (v1, vl);
+      vint32m4_t vw2 = __riscv_vsext_vf4_i32m4 (v2, vl);
+      vint32m4_t vw3 = __riscv_vsext_vf4_i32m4 (v3, vl);
+      vint32m4_t vw4 = __riscv_vsext_vf4_i32m4 (v4, vl);
+      vint32m4_t vw5 = __riscv_vsext_vf4_i32m4 (v5, vl);
+      vint32m4_t vw6 = __riscv_vsext_vf4_i32m4 (v6, vl);
+      vint32m4_t vw7 = __riscv_vsext_vf4_i32m4 (v7, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i32m4_i32 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i32m4_i32 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i32m4_i32 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i32m4_i32 (vw3);
+      size_t sum4 = __riscv_vmv_x_s_i32m4_i32 (vw4);
+      size_t sum5 = __riscv_vmv_x_s_i32m4_i32 (vw5);
+      size_t sum6 = __riscv_vmv_x_s_i32m4_i32 (vw6);
+      size_t sum7 = __riscv_vmv_x_s_i32m4_i32 (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/pr112431-17.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-17.c
new file mode 100644
index 00000000000..9ecc62e234b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-17.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;)
+    {
+      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;
+
+      asm volatile("nop" ::: "memory");
+      vint32m8_t vw0 = __riscv_vsext_vf4_i32m8 (v0, vl);
+      vint32m8_t vw1 = __riscv_vsext_vf4_i32m8 (v1, vl);
+      vint32m8_t vw2 = __riscv_vsext_vf4_i32m8 (v2, vl);
+      vint32m8_t vw3 = __riscv_vsext_vf4_i32m8 (v3, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i32m8_i32 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i32m8_i32 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i32m8_i32 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i32m8_i32 (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/pr112431-18.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-18.c
new file mode 100644
index 00000000000..4365fe0af54
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112431-18.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;)
+    {
+      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;
+
+      asm volatile("nop" ::: "memory");
+      vint64m8_t vw0 = __riscv_vsext_vf8_i64m8 (v0, vl);
+      vint64m8_t vw1 = __riscv_vsext_vf8_i64m8 (v1, vl);
+      vint64m8_t vw2 = __riscv_vsext_vf8_i64m8 (v2, vl);
+      vint64m8_t vw3 = __riscv_vsext_vf8_i64m8 (v3, vl);
+
+      asm volatile("nop" ::: "memory");
+      size_t sum0 = __riscv_vmv_x_s_i64m8_i64 (vw0);
+      size_t sum1 = __riscv_vmv_x_s_i64m8_i64 (vw1);
+      size_t sum2 = __riscv_vmv_x_s_i64m8_i64 (vw2);
+      size_t sum3 = __riscv_vmv_x_s_i64m8_i64 (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*-*-* } } } */
--
2.34.1