LGTM
juzhe.zh...@rivai.ai
From: pan2.li
Date: 2023-10-12 11:28
To: gcc-patches
CC: juzhe.zhong; pan2.li; yanzhang.wang; kito.cheng
Subject: [PATCH v1] RISC-V: Support FP llrint auto vectorization
From: Pan Li <pan2...@intel.com>
This patch would like to support the FP llrint auto vectorization.
* long long llrint (double)
This will be the CVT from DF => DI from the standard name's perpsective,
which has been covered in previous PATCH(es). Thus, this patch only add
some test cases.
gcc/testsuite/ChangeLog:
* gcc.target/riscv/rvv/autovec/unop/test-math.h: Add type int64_t.
* gcc.target/riscv/rvv/autovec/unop/math-llrint-0.c: New test.
* gcc.target/riscv/rvv/autovec/unop/math-llrint-run-0.c: New test.
* gcc.target/riscv/rvv/autovec/vls/math-llrint-0.c: New test.
Signed-off-by: Pan Li <pan2...@intel.com>
---
.../riscv/rvv/autovec/unop/math-llrint-0.c | 14 +++++
.../rvv/autovec/unop/math-llrint-run-0.c | 63 +++++++++++++++++++
.../riscv/rvv/autovec/unop/test-math.h | 2 +
.../riscv/rvv/autovec/vls/math-llrint-0.c | 30 +++++++++
4 files changed, 109 insertions(+)
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-0.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-run-0.c
create mode 100644
gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llrint-0.c
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-0.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-0.c
new file mode 100644
index 00000000000..2d90d232ba1
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-0.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv -mabi=lp64d -O3 -ftree-vectorize
-fno-vect-cost-model -ffast-math -fno-schedule-insns -fno-schedule-insns2" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+#include "test-math.h"
+
+/*
+** test_double_int64_t___builtin_llrint:
+** ...
+** vsetvli\s+[atx][0-9]+,\s*zero,\s*e64,\s*m1,\s*ta,\s*ma
+** vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+
+** ...
+*/
+TEST_UNARY_CALL_CVT (double, int64_t, __builtin_llrint)
diff --git
a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-run-0.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-run-0.c
new file mode 100644
index 00000000000..6b69f5568e9
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/math-llrint-run-0.c
@@ -0,0 +1,63 @@
+/* { dg-do run { target { riscv_v && rv64 } } } */
+/* { dg-additional-options "-std=c99 -O3 -ftree-vectorize -fno-vect-cost-model
-ffast-math" } */
+
+#include "test-math.h"
+
+#define ARRAY_SIZE 128
+
+double in[ARRAY_SIZE];
+int64_t out[ARRAY_SIZE];
+int64_t ref[ARRAY_SIZE];
+
+TEST_UNARY_CALL_CVT (double, int64_t, __builtin_llrint)
+TEST_ASSERT (int64_t)
+
+TEST_INIT_CVT (double, 1.2, int64_t, __builtin_llrint (1.2), 1)
+TEST_INIT_CVT (double, -1.2, int64_t, __builtin_llrint (-1.2), 2)
+TEST_INIT_CVT (double, 0.5, int64_t, __builtin_llrint (0.5), 3)
+TEST_INIT_CVT (double, -0.5, int64_t, __builtin_llrint (-0.5), 4)
+TEST_INIT_CVT (double, 0.1, int64_t, __builtin_llrint (0.1), 5)
+TEST_INIT_CVT (double, -0.1, int64_t, __builtin_llrint (-0.1), 6)
+TEST_INIT_CVT (double, 3.0, int64_t, __builtin_llrint (3.0), 7)
+TEST_INIT_CVT (double, -3.0, int64_t, __builtin_llrint (-3.0), 8)
+TEST_INIT_CVT (double, 4503599627370495.5, int64_t, __builtin_llrint
(4503599627370495.5), 9)
+TEST_INIT_CVT (double, 4503599627370497.0, int64_t, __builtin_llrint
(4503599627370497.0), 10)
+TEST_INIT_CVT (double, -4503599627370495.5, int64_t, __builtin_llrint
(-4503599627370495.5), 11)
+TEST_INIT_CVT (double, -4503599627370496.0, int64_t, __builtin_llrint
(-4503599627370496.0), 12)
+TEST_INIT_CVT (double, 0.0, int64_t, __builtin_llrint (-0.0), 13)
+TEST_INIT_CVT (double, -0.0, int64_t, __builtin_llrint (-0.0), 14)
+TEST_INIT_CVT (double, 9223372036854774784.0, int64_t, __builtin_llrint
(9223372036854774784.0), 15)
+TEST_INIT_CVT (double, 9223372036854775808.0, int64_t, __builtin_llrint
(9223372036854775808.0), 16)
+TEST_INIT_CVT (double, -9223372036854775808.0, int64_t, __builtin_llrint
(-9223372036854775808.0), 17)
+TEST_INIT_CVT (double, -9223372036854777856.0, int64_t, __builtin_llrint
(-9223372036854777856.0), 18)
+TEST_INIT_CVT (double, __builtin_inf (), int64_t, __builtin_llrint
(__builtin_inf ()), 19)
+TEST_INIT_CVT (double, -__builtin_inf (), int64_t, __builtin_llrint
(-__builtin_inf ()), 20)
+TEST_INIT_CVT (double, __builtin_nan (""), int64_t, 0x7fffffffffffffff, 21)
+
+int
+main ()
+{
+ RUN_TEST_CVT (double, int64_t, 1, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 2, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 3, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 4, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 5, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 6, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 7, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 8, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 9, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 10, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 11, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 12, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 13, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 14, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 15, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 16, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 17, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 18, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 19, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 20, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+ RUN_TEST_CVT (double, int64_t, 21, __builtin_llrint, in, out, ref,
ARRAY_SIZE);
+
+ return 0;
+}
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h
index a1c9d55bd48..3867bc50a14 100644
--- a/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/unop/test-math.h
@@ -68,6 +68,8 @@
#define FRM_RMM 4
#define FRM_DYN 7
+typedef long long int64_t;
+
static inline void
set_rm (unsigned rm)
{
diff --git a/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llrint-0.c
b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llrint-0.c
new file mode 100644
index 00000000000..b0bf422f685
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/rvv/autovec/vls/math-llrint-0.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gcv_zvl4096b -mabi=lp64d -O3
--param=riscv-autovec-lmul=m8 -ffast-math -fdump-tree-optimized" } */
+
+#include "def.h"
+
+DEF_OP_V_CVT (llrint, 1, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 2, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 4, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 8, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 16, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 32, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 64, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 128, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 256, double, int64_t, __builtin_llrint)
+DEF_OP_V_CVT (llrint, 512, double, int64_t, __builtin_llrint)
+
+/* { dg-final { scan-assembler-not {csrr} } } */
+/* { dg-final { scan-tree-dump-not "1,1" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "2,2" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "4,4" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "16,16" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "32,32" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "64,64" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "128,128" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "256,256" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "512,512" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "1024,1024" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "2048,2048" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "4096,4096" "optimized" } } */
+/* { dg-final { scan-assembler-times {vfcvt\.x\.f\.v\s+v[0-9]+,\s*v[0-9]+} 9 }
} */
--
2.34.1
