[PATCH] D31324: [OpenCL] Extended mapping of parcing CodeGen arguments

[Egor Churaev via Phabricator via cfe-commits]

echuraev created this revision.
Herald added a subscriber: yaxunl.

Enable cl_mad_enamle and cl_no_signed_zeros options when user turns on cl_unsafe_math_optimizations or cl_fast_relaxed_math options.


https://reviews.llvm.org/D31324

Files:
  lib/Frontend/CompilerInvocation.cpp
  test/CodeGenOpenCL/relaxed-fpmath.cl


Index: test/CodeGenOpenCL/relaxed-fpmath.cl
===================================================================
--- test/CodeGenOpenCL/relaxed-fpmath.cl
+++ test/CodeGenOpenCL/relaxed-fpmath.cl
@@ -2,33 +2,54 @@
 // 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
-
-typedef __attribute__(( ext_vector_type(4) )) float float4;
+// RUN: %clang_cc1 %s -emit-llvm -cl-mad-enable -o - | FileCheck %s -check-prefix=MAD
+// RUN: %clang_cc1 %s -emit-llvm -cl-no-signed-zeros -o - | FileCheck %s -check-prefix=NOSIGNED
 
 float spscalardiv(float a, float b) {
   // CHECK: @spscalardiv(
 
-  // NORMAL: fdiv float    
+  // NORMAL: fdiv float
   // FAST: fdiv fast float
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan float
+  // UNSAFE: fdiv nnan nsz float
+  // MAD: fdiv float
+  // NOSIGNED: fdiv nsz float
   return a / b;
 }
 // CHECK: attributes
 
+// NORMAL: "less-precise-fpmad"="false"
 // NORMAL: "no-infs-fp-math"="false"
 // NORMAL: "no-nans-fp-math"="false"
+// NORMAL: "no-signed-zeros-fp-math"="false"
 // NORMAL: "unsafe-fp-math"="false"
 
+// FAST: "less-precise-fpmad"="true"
 // FAST: "no-infs-fp-math"="true"
 // FAST: "no-nans-fp-math"="true"
+// FAST: "no-signed-zeros-fp-math"="true"
 // FAST: "unsafe-fp-math"="true"
 
+// FINITE: "less-precise-fpmad"="false"
 // FINITE: "no-infs-fp-math"="true"
 // FINITE: "no-nans-fp-math"="true"
+// FINITE: "no-signed-zeros-fp-math"="false"
 // FINITE: "unsafe-fp-math"="false"
 
+// UNSAFE: "less-precise-fpmad"="true"
 // UNSAFE: "no-infs-fp-math"="false"
 // UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "no-signed-zeros-fp-math"="true"
 // UNSAFE: "unsafe-fp-math"="true"
 
+// MAD: "less-precise-fpmad"="true"
+// MAD: "no-infs-fp-math"="false"
+// MAD: "no-nans-fp-math"="false"
+// MAD: "no-signed-zeros-fp-math"="false"
+// MAD: "unsafe-fp-math"="false"
+
+// NOSIGNED: "less-precise-fpmad"="false"
+// NOSIGNED: "no-infs-fp-math"="false"
+// NOSIGNED: "no-nans-fp-math"="false"
+// NOSIGNED: "no-signed-zeros-fp-math"="true"
+// NOSIGNED: "unsafe-fp-math"="false"
Index: lib/Frontend/CompilerInvocation.cpp
===================================================================
--- lib/Frontend/CompilerInvocation.cpp
+++ lib/Frontend/CompilerInvocation.cpp
@@ -573,7 +573,9 @@
   Opts.DiscardValueNames = Args.hasArg(OPT_discard_value_names);
   Opts.DisableTailCalls = Args.hasArg(OPT_mdisable_tail_calls);
   Opts.FloatABI = Args.getLastArgValue(OPT_mfloat_abi);
-  Opts.LessPreciseFPMAD = Args.hasArg(OPT_cl_mad_enable);
+  Opts.LessPreciseFPMAD = Args.hasArg(OPT_cl_mad_enable) ||
+                          Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
+                          Args.hasArg(OPT_cl_fast_relaxed_math);
   Opts.LimitFloatPrecision = Args.getLastArgValue(OPT_mlimit_float_precision);
   Opts.NoInfsFPMath = (Args.hasArg(OPT_menable_no_infinities) ||
                        Args.hasArg(OPT_cl_finite_math_only) ||
@@ -583,7 +585,9 @@
                        Args.hasArg(OPT_cl_finite_math_only) ||
                        Args.hasArg(OPT_cl_fast_relaxed_math));
   Opts.NoSignedZeros = (Args.hasArg(OPT_fno_signed_zeros) ||
-                        Args.hasArg(OPT_cl_no_signed_zeros));
+                        Args.hasArg(OPT_cl_no_signed_zeros) ||
+                        Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
+                        Args.hasArg(OPT_cl_fast_relaxed_math));
   Opts.FlushDenorm = Args.hasArg(OPT_cl_denorms_are_zero);
   Opts.CorrectlyRoundedDivSqrt =
       Args.hasArg(OPT_cl_fp32_correctly_rounded_divide_sqrt);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D31324.92914.patch
Type: text/x-patch
Size: 3789 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20170324/04d2b70f/attachment.bin>