This is the mail archive of the
gcc-patches@gcc.gnu.org
mailing list for the GCC project.
inhibit the sincos optimization when the target has sin and cos instructions
- From: Cesar Philippidis <cesar at codesourcery dot com>
- To: "gcc-patches at gcc dot gnu dot org" <gcc-patches at gcc dot gnu dot org>
- Date: Fri, 13 May 2016 12:18:57 -0700
- Subject: inhibit the sincos optimization when the target has sin and cos instructions
- Authentication-results: sourceware.org; auth=none
The cse_sincos pass tries to optimize sequences such as
sin (x);
cos (x);
into a single call to sincos, or cexpi, when available. However, the
nvptx target has sin and cos instructions, albeit with some loss of
precision (so it's only enabled with -ffast-math). This patch teaches
cse_sincos pass to ignore sin, cos and cexpi instructions when the
target can expand those calls. This yields a 6x speedup in 314.omriq
from spec accel when running on Nvidia accelerators.
Is this OK for trunk?
Cesar
2016-05-13 Cesar Philippidis <cesar@codesourcery.com>
gcc/
* tree-ssa-math-opts.c (pass_cse_sincos::execute): Don't optimize
sin and cos calls when the target has instructions for them.
gcc/testsuite/
* gcc.target/nvptx/sincos.c: New test.
diff --git a/gcc/testsuite/gcc.target/nvptx/sincos.c b/gcc/testsuite/gcc.target/nvptx/sincos.c
new file mode 100644
index 0000000..921ec41
--- /dev/null
+++ b/gcc/testsuite/gcc.target/nvptx/sincos.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -ffast-math" } */
+
+extern float sinf (float);
+extern float cosf (float);
+
+float
+sincos_add (float x)
+{
+ float s = sinf (x);
+ float c = cosf (x);
+
+ return s + c;
+}
+
+/* { dg-final { scan-assembler-times "sin.approx.f32" 1 } } */
+/* { dg-final { scan-assembler-times "cos.approx.f32" 1 } } */
diff --git a/gcc/tree-ssa-math-opts.c b/gcc/tree-ssa-math-opts.c
index 81688cd..38051e1 100644
--- a/gcc/tree-ssa-math-opts.c
+++ b/gcc/tree-ssa-math-opts.c
@@ -1806,6 +1806,11 @@ pass_cse_sincos::execute (function *fun)
CASE_CFN_COS:
CASE_CFN_SIN:
CASE_CFN_CEXPI:
+ /* Don't modify these calls if they can be translated
+ directly into hardware instructions. */
+ if (replacement_internal_fn (as_a <gcall *> (stmt))
+ != IFN_LAST)
+ break;
/* Make sure we have either sincos or cexp. */
if (!targetm.libc_has_function (function_c99_math_complex)
&& !targetm.libc_has_function (function_sincos))