On 12/01/2014 06:13 PM, Matt Arsenault wrote:
I think the test should also check for the function target attribute.
Not sure of this as Hal said that those are being phased out.
I added a test for the attributes that were there already anyways,
but didn't add a new attribute for the no-signed-zeros.
What about the other flags? I think this patch should handle (maybe just
test?) all of the CL fast math flags instead of just this one (
-cl-no-signed-zeros, -cl-unsafe-math-optimizations,
-cl-finite-math-only, and -cl-fast-relaxed-math)
Done. The OpenCL flags seem to be supersets of the
flags of LLVM, so there might be more optimization
opportunities to extract from those than these flags
enable.
For example:
"Allow optimizations for floating-point arithmetic that (a) assume that
arguments and results are valid, (b) may violate IEEE 754 standard and
(c) may violate the OpenCL numerical compliance requirements as defined
in section 7.4 for single-precision floating-point, section 9.3.9 for
double-precision floating-point, and edge case behavior in section 7.5.
This option includes the -cl-no-signed-zeros and -cl-mad-enable options."
https://www.khronos.org/registry/cl/sdk/1.0/docs/man/xhtml/clBuildProgram.html
Now it just sets the nnans flag even though (b) and (c) allow
pretty much anything (if read with "lawyer's eyes").
--
--Pekka
Index: include/clang/Driver/CC1Options.td
===================================================================
--- include/clang/Driver/CC1Options.td (revision 222892)
+++ include/clang/Driver/CC1Options.td (working copy)
@@ -575,6 +575,8 @@
HelpText<"OpenCL only. Allow floating-point optimizations that assume arguments and results are not NaNs or +-Inf.">;
def cl_kernel_arg_info : Flag<["-"], "cl-kernel-arg-info">,
HelpText<"OpenCL only. Generate kernel argument metadata.">;
+def cl_no_signed_zeros : Flag<["-"], "cl-no-signed-zeros">,
+ HelpText<"OpenCL only. Allow optimizations to ignore the signedness of the floating-point zero.">;
def cl_unsafe_math_optimizations : Flag<["-"], "cl-unsafe-math-optimizations">,
HelpText<"OpenCL only. Allow unsafe floating-point optimizations. Also implies -cl-no-signed-zeros and -cl-mad-enable">;
def cl_fast_relaxed_math : Flag<["-"], "cl-fast-relaxed-math">,
Index: include/clang/Frontend/CodeGenOptions.def
===================================================================
--- include/clang/Frontend/CodeGenOptions.def (revision 222892)
+++ include/clang/Frontend/CodeGenOptions.def (working copy)
@@ -78,6 +78,7 @@
CODEGENOPT(NoGlobalMerge , 1, 0) ///< Set when -mno-global-merge is enabled.
CODEGENOPT(NoImplicitFloat , 1, 0) ///< Set when -mno-implicit-float is enabled.
CODEGENOPT(NoInfsFPMath , 1, 0) ///< Assume FP arguments, results not +-Inf.
+CODEGENOPT(NoSignedZeros , 1, 0) ///< Allow ignoring the signedness of FP zero
CODEGENOPT(NoInline , 1, 0) ///< Set when -fno-inline is enabled.
///< Disables use of the inline keyword.
CODEGENOPT(NoNaNsFPMath , 1, 0) ///< Assume FP arguments, results not NaN.
Index: lib/CodeGen/CodeGenFunction.cpp
===================================================================
--- lib/CodeGen/CodeGenFunction.cpp (revision 222892)
+++ lib/CodeGen/CodeGenFunction.cpp (working copy)
@@ -63,6 +63,12 @@
FMF.setNoNaNs();
FMF.setNoInfs();
}
+ if (CGM.getCodeGenOpts().NoNaNsFPMath) {
+ FMF.setNoNaNs();
+ }
+ if (CGM.getCodeGenOpts().NoSignedZeros) {
+ FMF.setNoSignedZeros();
+ }
Builder.SetFastMathFlags(FMF);
}
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp (revision 222892)
+++ lib/Frontend/CompilerInvocation.cpp (working copy)
@@ -417,11 +417,13 @@
Opts.LessPreciseFPMAD = Args.hasArg(OPT_cl_mad_enable);
Opts.LimitFloatPrecision = Args.getLastArgValue(OPT_mlimit_float_precision);
Opts.NoInfsFPMath = (Args.hasArg(OPT_menable_no_infinities) ||
- Args.hasArg(OPT_cl_finite_math_only)||
+ Args.hasArg(OPT_cl_finite_math_only) ||
Args.hasArg(OPT_cl_fast_relaxed_math));
Opts.NoNaNsFPMath = (Args.hasArg(OPT_menable_no_nans) ||
- Args.hasArg(OPT_cl_finite_math_only)||
+ Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
+ Args.hasArg(OPT_cl_finite_math_only) ||
Args.hasArg(OPT_cl_fast_relaxed_math));
+ Opts.NoSignedZeros = Args.hasArg(OPT_cl_no_signed_zeros);
Opts.NoZeroInitializedInBSS = Args.hasArg(OPT_mno_zero_initialized_in_bss);
Opts.BackendOptions = Args.getAllArgValues(OPT_backend_option);
Opts.NumRegisterParameters = getLastArgIntValue(Args, OPT_mregparm, 0, Diags);
@@ -1596,8 +1598,11 @@
// inlining enabled.
Opts.NoInlineDefine = !Opt || Args.hasArg(OPT_fno_inline);
- Opts.FastMath = Args.hasArg(OPT_ffast_math);
- Opts.FiniteMathOnly = Args.hasArg(OPT_ffinite_math_only);
+ Opts.FastMath = Args.hasArg(OPT_ffast_math) ||
+ Args.hasArg(OPT_cl_fast_relaxed_math);
+ Opts.FiniteMathOnly = Args.hasArg(OPT_ffinite_math_only) ||
+ Args.hasArg(OPT_cl_finite_math_only) ||
+ Args.hasArg(OPT_cl_fast_relaxed_math);
Opts.RetainCommentsFromSystemHeaders =
Args.hasArg(OPT_fretain_comments_from_system_headers);
Index: test/CodeGenOpenCL/relaxed-fpmath.cl
===================================================================
--- test/CodeGenOpenCL/relaxed-fpmath.cl (revision 0)
+++ test/CodeGenOpenCL/relaxed-fpmath.cl (working copy)
@@ -0,0 +1,36 @@
+// RUN: %clang_cc1 %s -emit-llvm -o - | FileCheck %s -check-prefix=NORMAL
+// RUN: %clang_cc1 %s -emit-llvm -cl-fast-relaxed-math -o - | FileCheck %s -check-prefix=FAST
+// RUN: %clang_cc1 %s -emit-llvm -cl-finite-math-only -o - | FileCheck %s -check-prefix=FINITE
+// RUN: %clang_cc1 %s -emit-llvm -cl-unsafe-math-optimizations -o - | FileCheck %s -check-prefix=UNSAFE
+// RUN: %clang_cc1 %s -emit-llvm -cl-no-signed-zeros -o - | FileCheck %s -check-prefix=NOSZ
+
+typedef __attribute__(( ext_vector_type(4) )) float float4;
+
+float spscalardiv(float a, float b) {
+ // CHECK: @spscalardiv(
+
+ // NORMAL: fdiv float
+ // FAST: fdiv fast float
+ // FINITE: fdiv nnan ninf float
+ // UNSAFE: fdiv nnan float
+ // NOSZ: fdiv nsz float
+ return a / b;
+}
+// CHECK: attributes
+
+// NORMAL: "no-infs-fp-math"="false"
+// NORMAL: "no-nans-fp-math"="false"
+// NORMAL: "unsafe-fp-math"="false"
+
+// FAST: "no-infs-fp-math"="true"
+// FAST: "no-nans-fp-math"="true"
+// FAST: "unsafe-fp-math"="true"
+
+// FINITE: "no-infs-fp-math"="true"
+// FINITE: "no-nans-fp-math"="true"
+// FINITE: "unsafe-fp-math"="false"
+
+// UNSAFE: "no-infs-fp-math"="false"
+// UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "unsafe-fp-math"="true"
+
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/cfe-commits
