23 Star 30 Fork 165

src-openEuler/gcc
关闭

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
该仓库未声明开源许可证文件(LICENSE),使用请关注具体项目描述及其代码上游依赖。
克隆/下载
0242-Backport-SME-aarch64-Remove-redundant-builtins-code.patch 6.12 KB
一键复制 编辑 原始数据 按行查看 历史
huangzifeng 提交于 2024-11-21 11:35 +08:00 . Sync patches from branch openEuler-24.09
From 42bfa9a26205da222cebbe830168b6f0b5e668b4 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 12 Jul 2022 12:59:25 +0100
Subject: [PATCH 143/157] [Backport][SME] aarch64: Remove redundant builtins
code
Reference: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=e80daf04c8888f527d2fc7f6cbcd1b4c853dcd04
aarch64_builtin_vectorized_function handles some built-in functions
that already have equivalent internal functions. This seems to be
redundant now, since the target builtins that it chooses are mapped
to the same optab patterns as the internal functions.
gcc/
* config/aarch64/aarch64-builtins.cc
(aarch64_builtin_vectorized_function): Remove handling of
floor, ceil, trunc, round, nearbyint, sqrt, clz and ctz.
gcc/testsuite/
* gcc.target/aarch64/vect_unary_1.c: New test.
---
gcc/config/aarch64/aarch64-builtins.cc | 32 ---
.../gcc.target/aarch64/vect_unary_1.c | 186 ++++++++++++++++++
2 files changed, 186 insertions(+), 32 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/aarch64/vect_unary_1.c
diff --git a/gcc/config/aarch64/aarch64-builtins.cc b/gcc/config/aarch64/aarch64-builtins.cc
index 37bb3af48..23a84cd53 100644
--- a/gcc/config/aarch64/aarch64-builtins.cc
+++ b/gcc/config/aarch64/aarch64-builtins.cc
@@ -2653,38 +2653,6 @@ aarch64_builtin_vectorized_function (unsigned int fn, tree type_out,
switch (fn)
{
#undef AARCH64_CHECK_BUILTIN_MODE
-#define AARCH64_CHECK_BUILTIN_MODE(C, N) \
- (out_mode == V##C##N##Fmode && in_mode == V##C##N##Fmode)
- CASE_CFN_FLOOR:
- return AARCH64_FIND_FRINT_VARIANT (floor);
- CASE_CFN_CEIL:
- return AARCH64_FIND_FRINT_VARIANT (ceil);
- CASE_CFN_TRUNC:
- return AARCH64_FIND_FRINT_VARIANT (btrunc);
- CASE_CFN_ROUND:
- return AARCH64_FIND_FRINT_VARIANT (round);
- CASE_CFN_NEARBYINT:
- return AARCH64_FIND_FRINT_VARIANT (nearbyint);
- CASE_CFN_SQRT:
- return AARCH64_FIND_FRINT_VARIANT (sqrt);
-#undef AARCH64_CHECK_BUILTIN_MODE
-#define AARCH64_CHECK_BUILTIN_MODE(C, N) \
- (out_mode == V##C##SImode && in_mode == V##C##N##Imode)
- CASE_CFN_CLZ:
- {
- if (AARCH64_CHECK_BUILTIN_MODE (4, S))
- return aarch64_builtin_decls[AARCH64_SIMD_BUILTIN_UNOP_clzv4si];
- return NULL_TREE;
- }
- CASE_CFN_CTZ:
- {
- if (AARCH64_CHECK_BUILTIN_MODE (2, S))
- return aarch64_builtin_decls[AARCH64_SIMD_BUILTIN_UNOP_ctzv2si];
- else if (AARCH64_CHECK_BUILTIN_MODE (4, S))
- return aarch64_builtin_decls[AARCH64_SIMD_BUILTIN_UNOP_ctzv4si];
- return NULL_TREE;
- }
-#undef AARCH64_CHECK_BUILTIN_MODE
#define AARCH64_CHECK_BUILTIN_MODE(C, N) \
(out_mode == V##C##N##Imode && in_mode == V##C##N##Fmode)
CASE_CFN_IFLOOR:
diff --git a/gcc/testsuite/gcc.target/aarch64/vect_unary_1.c b/gcc/testsuite/gcc.target/aarch64/vect_unary_1.c
new file mode 100644
index 000000000..8516808be
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/vect_unary_1.c
@@ -0,0 +1,186 @@
+/* { dg-options "-O3 --save-temps" } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+
+#include <stdint.h>
+
+#define TEST2(OUT, NAME, IN) \
+OUT __attribute__((vector_size(sizeof(OUT) * 2))) \
+test2_##OUT##_##NAME##_##IN (float dummy, \
+ IN __attribute__((vector_size(sizeof(IN) * 2))) y) \
+{ \
+ OUT __attribute__((vector_size(sizeof(OUT) * 2))) x; \
+ x[0] = __builtin_##NAME (y[0]); \
+ x[1] = __builtin_##NAME (y[1]); \
+ return x; \
+} \
+
+#define TEST4(OUT, NAME, IN) \
+OUT __attribute__((vector_size(16))) \
+test4_##OUT##_##NAME##_##IN (float dummy, \
+ IN __attribute__((vector_size(16))) y) \
+{ \
+ OUT __attribute__((vector_size(16))) x; \
+ x[0] = __builtin_##NAME (y[0]); \
+ x[1] = __builtin_##NAME (y[1]); \
+ x[2] = __builtin_##NAME (y[2]); \
+ x[3] = __builtin_##NAME (y[3]); \
+ return x; \
+} \
+
+/*
+** test2_float_truncf_float:
+** frintz v0.2s, v1.2s
+** ret
+*/
+TEST2 (float, truncf, float)
+
+/*
+** test2_double_trunc_double:
+** frintz v0.2d, v1.2d
+** ret
+*/
+TEST2 (double, trunc, double)
+
+/*
+** test4_float_truncf_float:
+** frintz v0.4s, v1.4s
+** ret
+*/
+TEST4 (float, truncf, float)
+
+/*
+** test2_float_roundf_float:
+** frinta v0.2s, v1.2s
+** ret
+*/
+TEST2 (float, roundf, float)
+
+/*
+** test2_double_round_double:
+** frinta v0.2d, v1.2d
+** ret
+*/
+TEST2 (double, round, double)
+
+/*
+** test4_float_roundf_float:
+** frinta v0.4s, v1.4s
+** ret
+*/
+TEST4 (float, roundf, float)
+
+/*
+** test2_float_nearbyintf_float:
+** frinti v0.2s, v1.2s
+** ret
+*/
+TEST2 (float, nearbyintf, float)
+
+/*
+** test2_double_nearbyint_double:
+** frinti v0.2d, v1.2d
+** ret
+*/
+TEST2 (double, nearbyint, double)
+
+/*
+** test4_float_nearbyintf_float:
+** frinti v0.4s, v1.4s
+** ret
+*/
+TEST4 (float, nearbyintf, float)
+
+/*
+** test2_float_floorf_float:
+** frintm v0.2s, v1.2s
+** ret
+*/
+TEST2 (float, floorf, float)
+
+/*
+** test2_double_floor_double:
+** frintm v0.2d, v1.2d
+** ret
+*/
+TEST2 (double, floor, double)
+
+/*
+** test4_float_floorf_float:
+** frintm v0.4s, v1.4s
+** ret
+*/
+TEST4 (float, floorf, float)
+
+/*
+** test2_float_ceilf_float:
+** frintp v0.2s, v1.2s
+** ret
+*/
+TEST2 (float, ceilf, float)
+
+/*
+** test2_double_ceil_double:
+** frintp v0.2d, v1.2d
+** ret
+*/
+TEST2 (double, ceil, double)
+
+/*
+** test4_float_ceilf_float:
+** frintp v0.4s, v1.4s
+** ret
+*/
+TEST4 (float, ceilf, float)
+
+/*
+** test2_float_rintf_float:
+** frintx v0.2s, v1.2s
+** ret
+*/
+TEST2 (float, rintf, float)
+
+/*
+** test2_double_rint_double:
+** frintx v0.2d, v1.2d
+** ret
+*/
+TEST2 (double, rint, double)
+
+/*
+** test4_float_rintf_float:
+** frintx v0.4s, v1.4s
+** ret
+*/
+TEST4 (float, rintf, float)
+
+/*
+** test2_int_clz_int:
+** clz v0.2s, v1.2s
+** ret
+*/
+TEST2 (int, clz, int)
+
+/*
+** test4_int_clz_int:
+** clz v0.4s, v1.4s
+** ret
+*/
+TEST4 (int, clz, int)
+
+/*
+** test2_int_ctz_int:
+** rev32 (v[0-9]+).8b, v1.8b
+** rbit (v[0-9]+).8b, \1.8b
+** clz v0.2s, \2.2s
+** ret
+*/
+TEST2 (int, ctz, int)
+
+/*
+** test4_int_ctz_int:
+** rev32 (v[0-9]+).16b, v1.16b
+** rbit (v[0-9]+).16b, \1.16b
+** clz v0.4s, \2.4s
+** ret
+*/
+TEST4 (int, ctz, int)
--
2.33.0
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/src-openeuler/gcc.git
git@gitee.com:src-openeuler/gcc.git
src-openeuler
gcc
gcc
master

搜索帮助