[PATCH] RISC-V: Allow dest operand and accumulator operand overlap of widen reduction instruction[PR112327]

[Juzhe-Zhong <juzhe.zhong@rivai.ai>]

Consider this following intrinsic code:

void rvv_dot_prod(int16_t *pSrcA, int16_t *pSrcB, uint32_t n, int64_t *result)
{
    size_t vl;
    vint16m4_t vSrcA, vSrcB;
    vint64m1_t vSum = __riscv_vmv_s_x_i64m1(0, 1);
    while (n > 0) {
        vl = __riscv_vsetvl_e16m4(n);
        vSrcA = __riscv_vle16_v_i16m4(pSrcA, vl);
        vSrcB = __riscv_vle16_v_i16m4(pSrcB, vl);
        vSum = __riscv_vwredsum_vs_i32m8_i64m1(__riscv_vwmul_vv_i32m8(vSrcA, vSrcB, vl), vSum, vl);
        pSrcA += vl;
        pSrcB += vl;
        n -= vl;
    }
    *result = __riscv_vmv_x_s_i64m1_i64(vSum);
}

https://godbolt.org/z/vWd35W7G6

Before this patch:

...
Loop:
...
vmv1r.v v2,v1
...
vwredsum.vs     v1,v8,v2
...

After this patch:

...
Loop:
...
vwredsum.vs	v1,v8,v1
...

	PR target/112327

gcc/ChangeLog:

	* config/riscv/vector.md: Add '0'.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/rvv/base/pr112327-1.c: New test.
	* gcc.target/riscv/rvv/base/pr112327-2.c: New test.

---
 gcc/config/riscv/vector.md                    |  4 +--
 .../gcc.target/riscv/rvv/base/pr112327-1.c    | 27 +++++++++++++++++++
 .../gcc.target/riscv/rvv/base/pr112327-2.c    | 27 +++++++++++++++++++
 3 files changed, 56 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-1.c
 create mode 100644 gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-2.c

diff --git a/gcc/config/riscv/vector.md b/gcc/config/riscv/vector.md
index 0297e4f0227..3577971fa33 100644
--- a/gcc/config/riscv/vector.md
+++ b/gcc/config/riscv/vector.md
@@ -7765,7 +7765,7 @@
 	     (reg:SI VTYPE_REGNUM)] UNSPEC_VPREDICATE)
            (unspec:<V_EXT_LMUL1> [
 	     (match_operand:VI_QHS         3 "register_operand"      "   vr,   vr")
-	     (match_operand:<V_EXT_LMUL1>  4 "register_operand"      "   vr,   vr")
+	     (match_operand:<V_EXT_LMUL1>  4 "register_operand"      "  vr0,  vr0")
            ] ANY_WREDUC)
 	   (match_operand:<V_EXT_LMUL1>    2 "vector_merge_operand"  "   vu,    0")] UNSPEC_REDUC))]
   "TARGET_VECTOR"
@@ -7834,7 +7834,7 @@
 	     (reg:SI FRM_REGNUM)] UNSPEC_VPREDICATE)
            (unspec:<V_EXT_LMUL1> [
 	     (match_operand:VF_HS          3 "register_operand"      "   vr,   vr")
-	     (match_operand:<V_EXT_LMUL1>  4 "register_operand"      "   vr,   vr")
+	     (match_operand:<V_EXT_LMUL1>  4 "register_operand"      "  vr0,  vr0")
            ] ANY_FWREDUC_SUM)
 	   (match_operand:<V_EXT_LMUL1>    2 "vector_merge_operand"  "   vu,    0")] UNSPEC_REDUC))]
   "TARGET_VECTOR"
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-1.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-1.c
new file mode 100644
index 00000000000..20da23976f3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-1.c
@@ -0,0 +1,27 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+void
+foo (int16_t *pSrcA, int16_t *pSrcB, uint32_t n, int64_t *result)
+{
+  size_t vl;
+  vint16m4_t vSrcA, vSrcB;
+  vint64m1_t vSum = __riscv_vmv_s_x_i64m1 (0, 1);
+  while (n > 0)
+    {
+      vl = __riscv_vsetvl_e16m4 (n);
+      vSrcA = __riscv_vle16_v_i16m4 (pSrcA, vl);
+      vSrcB = __riscv_vle16_v_i16m4 (pSrcB, vl);
+      vSum = __riscv_vwredsum_vs_i32m8_i64m1 (
+	__riscv_vwmul_vv_i32m8 (vSrcA, vSrcB, vl), vSum, vl);
+      pSrcA += vl;
+      pSrcB += vl;
+      n -= vl;
+    }
+  *result = __riscv_vmv_x_s_i64m1_i64 (vSum);
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv\.v\.v} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-2.c b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-2.c
new file mode 100644
index 00000000000..5ffde000fbd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/base/pr112327-2.c
@@ -0,0 +1,27 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvfh_zfh -mabi=lp64d -O3" } */
+
+#include "riscv_vector.h"
+
+void
+foo (_Float16 *pSrcA, _Float16 *pSrcB, uint32_t n, double *result)
+{
+  size_t vl;
+  vfloat16m4_t vSrcA, vSrcB;
+  vfloat64m1_t vSum = __riscv_vfmv_s_f_f64m1 (0, 1);
+  while (n > 0)
+    {
+      vl = __riscv_vsetvl_e16m4 (n);
+      vSrcA = __riscv_vle16_v_f16m4 (pSrcA, vl);
+      vSrcB = __riscv_vle16_v_f16m4 (pSrcB, vl);
+      vSum = __riscv_vfwredusum_vs_f32m8_f64m1 (
+	__riscv_vfwmul_vv_f32m8 (vSrcA, vSrcB, vl), vSum, vl);
+      pSrcA += vl;
+      pSrcB += vl;
+      n -= vl;
+    }
+  *result = __riscv_vfmv_f_s_f64m1_f64 (vSum);
+}
+
+/* { dg-final { scan-assembler-not {vmv1r} } } */
+/* { dg-final { scan-assembler-not {vmv\.v\.v} } } */
-- 
2.36.3