From: Pan Li <[email protected]>
Add asm dump check and for vec_duplicate + vadd.vv combine case 1 to vadd.vx.
The late-combine will take action when GR2VR cost is 0, because the vmv
and the vadd.vx will consume the same cost of GR2VR. Aka:
Before:
L1:
vmv.v.x
vadd.vv
J L1
After:
L1:
vadd.vx
J L1
The below test suites are passed for this patch.
* The rv64gcv fully regression test.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/vx_vf/vx_binary.h: Add test
helper macros.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i16.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i32.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i64.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i8.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u16.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u32.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u64.c: New test.
* gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u8.c: New test.
Signed-off-by: Pan Li <[email protected]>
---
.../riscv/rvv/autovec/vx_vf/vx_binary.h | 44 +++++++++++++++++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-i16.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-i32.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-i64.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-i8.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-u16.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-u32.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-u64.c | 8 ++++
.../riscv/rvv/autovec/vx_vf/vx_vadd-4-u8.c | 8 ++++
9 files changed, 108 insertions(+)
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i16.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i32.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i64.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i8.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u16.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u32.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u64.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u8.c
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_binary.h
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_binary.h
index de5b70dd04b..db802bdefd7 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_binary.h
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_binary.h
@@ -14,4 +14,48 @@ test_vx_binary_case_0 (T * restrict out, T * restrict in, T
x, unsigned n) \
#define RUN_VX_BINARY_CASE_0(out, in, x, n) test_vx_binary_case_0(out,
in, x, n)
#define RUN_VX_BINARY_CASE_0_WRAP(out, in, x, n) RUN_VX_BINARY_CASE_0(out, in,
x, n)
+#define VX_BINARY_BODY(op) \
+ out[k + 0] = in[k + 0] op tmp; \
+ out[k + 1] = in[k + 1] op tmp; \
+ k += 2;
+
+#define VX_BINARY_BODY_X4(op) \
+ VX_BINARY_BODY(op) \
+ VX_BINARY_BODY(op)
+
+#define VX_BINARY_BODY_X8(op) \
+ VX_BINARY_BODY_X4(op) \
+ VX_BINARY_BODY_X4(op)
+
+#define VX_BINARY_BODY_X16(op) \
+ VX_BINARY_BODY_X8(op) \
+ VX_BINARY_BODY_X8(op)
+
+#define VX_BINARY_BODY_X32(op) \
+ VX_BINARY_BODY_X16(op) \
+ VX_BINARY_BODY_X16(op)
+
+#define VX_BINARY_BODY_X64(op) \
+ VX_BINARY_BODY_X32(op) \
+ VX_BINARY_BODY_X32(op)
+
+#define VX_BINARY_BODY_X128(op) \
+ VX_BINARY_BODY_X64(op) \
+ VX_BINARY_BODY_X64(op)
+
+#define DEF_VX_BINARY_CASE_1(T, OP, BODY) \
+void \
+test_vx_binary_case_1 (T * restrict out, T * restrict in, T x, unsigned n) \
+{ \
+ unsigned k = 0; \
+ T tmp = x + 3; \
+ \
+ while (k < n) \
+ { \
+ tmp = tmp ^ 0x3f; \
+ BODY(OP) \
+ } \
+}
+#define DEF_VX_BINARY_CASE_1_WRAP(T, OP, BODY) DEF_VX_BINARY_CASE_1(T, OP,
BODY)
+
#endif
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i16.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i16.c
new file mode 100644
index 00000000000..9a26601165e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i16.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(int16_t, +, VX_BINARY_BODY_X16)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i32.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i32.c
new file mode 100644
index 00000000000..55b51fc0ec7
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i32.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(int32_t, +, VX_BINARY_BODY_X4)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i64.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i64.c
new file mode 100644
index 00000000000..8ad60982ff6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i64.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(int64_t, +, VX_BINARY_BODY)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i8.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i8.c
new file mode 100644
index 00000000000..193e0205b53
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-i8.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(int8_t, +, VX_BINARY_BODY_X16)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u16.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u16.c
new file mode 100644
index 00000000000..a093fca9637
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u16.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(uint16_t, +, VX_BINARY_BODY_X16)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u32.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u32.c
new file mode 100644
index 00000000000..9f5843b12aa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u32.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(uint32_t, +, VX_BINARY_BODY_X4)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u64.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u64.c
new file mode 100644
index 00000000000..0f00688ae93
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u64.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(uint64_t, +, VX_BINARY_BODY)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u8.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u8.c
new file mode 100644
index 00000000000..47707e87ae2
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vx_vf/vx_vadd-4-u8.c
@@ -0,0 +1,8 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl128b -mabi=lp64d --param=gpr2vr-cost=0" } */
+
+#include "vx_binary.h"
+
+DEF_VX_BINARY_CASE_1(uint8_t, +, VX_BINARY_BODY_X16)
+
+/* { dg-final { scan-assembler {vadd.vx} } } */
--
2.43.0
