[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[John McCall via Phabricator via cfe-commits]

rjmccall closed this revision.
rjmccall added a comment.

8a8d703be0986dd6785cba0b610c9c4708b83e89 



Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale added a comment.

Thanks John.

Would you be able to land this on my behalf?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[John McCall via Phabricator via cfe-commits]

rjmccall added a comment.

Per a private discussion, it seems like the right thing to do here would be 
stop recognizing `-ffast-math` flag in cc1 and just put the driver in charge of 
all these individual flags.  That may necessitate adding a `-fdefine-fast-math` 
cc1 option to control the `#define`, but the logic for that seems complex 
enough that it ought to be left to the driver.

Separately, we should consider making some more driver options imply 
`-ffp-contract=fast`.  Fast contraction is the default behavior in GCC, and 
while Clang has chosen not to follow that precedent, it seems to be in keeping 
with the spirit of options like `-funsafe-math-optimizations` that they should 
broadly enable contraction if that policy isn't otherwise specified.

Those sorts of changes should be kept separate from this kind of refactor, 
though.  This is still approved.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale updated this revision to Diff 267401.
michele.scandale added a comment.

Revert last change about `-ffast-math` imply "fast" contraction mode by default 
in CC1.
Rebase.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315

Files:
  clang/include/clang/Basic/CodeGenOptions.def
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/BackendUtil.cpp
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/lib/CodeGen/CodeGenFunction.cpp
  clang/lib/CodeGen/CodeGenFunction.h
  clang/lib/Frontend/CompilerInvocation.cpp
  clang/test/CodeGen/builtins-nvptx-ptx60.cu
  clang/test/CodeGen/complex-math.c
  clang/test/CodeGen/fp-options-to-fast-math-flags.c
  clang/test/CodeGen/libcalls.c
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/library-builtin.cu
  clang/test/CodeGenOpenCL/relaxed-fpmath.cl

Index: clang/test/CodeGenOpenCL/relaxed-fpmath.cl
===
--- clang/test/CodeGenOpenCL/relaxed-fpmath.cl
+++ clang/test/CodeGenOpenCL/relaxed-fpmath.cl
@@ -11,7 +11,7 @@
   // NORMAL: fdiv float
   // FAST: fdiv fast float
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float
   // NOSIGNED: fdiv nsz float
   return a / b;
@@ -38,7 +38,7 @@
 
 // UNSAFE: "less-precise-fpmad"="true"
 // UNSAFE: "no-infs-fp-math"="false"
-// UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "no-nans-fp-math"="false"
 // UNSAFE: "no-signed-zeros-fp-math"="true"
 // UNSAFE: "unsafe-fp-math"="true"
 
Index: clang/test/CodeGenCUDA/library-builtin.cu
===
--- clang/test/CodeGenCUDA/library-builtin.cu
+++ clang/test/CodeGenCUDA/library-builtin.cu
@@ -10,7 +10,7 @@
 
 // logf() should be calling itself recursively as we don't have any standard
 // library on device side.
-// DEVICE: call float @logf(float
+// DEVICE: call contract float @logf(float
 extern "C" __attribute__((device)) float logf(float __x) { return logf(__x); }
 
 // NOTE: this case is to illustrate the expected differences in behavior between
@@ -18,5 +18,5 @@
 // library.
 //
 // Host is assumed to have standard library, so logf() calls LLVM intrinsic.
-// HOST: call float @llvm.log.f32(float
+// HOST: call contract float @llvm.log.f32(float
 extern "C" float logf(float __x) { return logf(__x); }
Index: clang/test/CodeGenCUDA/builtins-amdgcn.cu
===
--- clang/test/CodeGenCUDA/builtins-amdgcn.cu
+++ clang/test/CodeGenCUDA/builtins-amdgcn.cu
@@ -10,7 +10,7 @@
 }
 
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__
 void test_ds_fmax(float src) {
   __shared__ float shared;
Index: clang/test/CodeGen/libcalls.c
===
--- clang/test/CodeGen/libcalls.c
+++ clang/test/CodeGen/libcalls.c
@@ -8,17 +8,17 @@
 void test_sqrt(float a0, double a1, long double a2) {
   // CHECK-YES: call float @sqrtf
   // CHECK-NO: call float @llvm.sqrt.f32(float
-  // CHECK-FAST: call float @llvm.sqrt.f32(float
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(float
   float l0 = sqrtf(a0);
 
   // CHECK-YES: call double @sqrt
   // CHECK-NO: call double @llvm.sqrt.f64(double
-  // CHECK-FAST: call double @llvm.sqrt.f64(double
+  // CHECK-FAST: call reassoc nsz arcp afn double @llvm.sqrt.f64(double
   double l1 = sqrt(a1);
 
   // CHECK-YES: call x86_fp80 @sqrtl
   // CHECK-NO: call x86_fp80 @llvm.sqrt.f80(x86_fp80
-  // CHECK-FAST: call x86_fp80 @llvm.sqrt.f80(x86_fp80
+  // CHECK-FAST: call reassoc nsz arcp afn x86_fp80 @llvm.sqrt.f80(x86_fp80
   long double l2 = sqrtl(a2);
 }
 
Index: clang/test/CodeGen/fp-options-to-fast-math-flags.c
===
--- /dev/null
+++ clang/test/CodeGen/fp-options-to-fast-math-flags.c
@@ -0,0 +1,42 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck -check-prefix CHECK-PRECISE %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -menable-no-nans -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-NANS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -menable-no-infs -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-INFS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -ffinite-math-only -emit-llvm -o - %s | FileCheck -check-prefix CHECK-FINITE %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fno-signed-zeros -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-SIGNED-ZEROS %s
+// RUN: %clang_cc1 -triple x86_64-unkno

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale requested review of this revision.
michele.scandale added a comment.

I've just realized it might be incorrect to have the CC1 option `-ffast-math` 
changing the default contraction mode. The clang driver generates `-ffast-math` 
based on conditions that do not involve the contraction mode state at all:

  // -ffast-math enables the __FAST_MATH__ preprocessor macro, but check for the
  // individual features enabled by -ffast-math instead of the option itself as
  // that's consistent with gcc's behaviour.
  if (!HonorINFs && !HonorNaNs && !MathErrno && AssociativeMath &&
  ReciprocalMath && !SignedZeros && !TrappingMath && !RoundingFPMath) {
CmdArgs.push_back("-ffast-math");
if (FPModel.equals("fast")) {
  if (FPContract.equals("fast"))
// All set, do nothing.
;
  else if (FPContract.empty())
// Enable -ffp-contract=fast
CmdArgs.push_back(Args.MakeArgString("-ffp-contract=fast"));
  else
D.Diag(clang::diag::warn_drv_overriding_flag_option)
  << "-ffp-model=fast"
  << Args.MakeArgString("-ffp-contract=" + FPContract);
}
  }

For example the running the following `clang -### -funsafe-math-optimizations 
-ffinite-math-only -x c -` lead to a CC1 command line without any 
`-ffp-contract=` option relying on the fact that the default value for the 
contraction mode in the compiler is OFF.

I will revert the modification on this aspect.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[John McCall via Phabricator via cfe-commits]

rjmccall accepted this revision.
rjmccall added a comment.
This revision is now accepted and ready to land.

>> I'm actually surprised it doesn't.  I can't imagine why someone enabling 
>> fast math would want contraction to be disabled.
> 
> Just to be clear the clang driver does the right thing.
>  If you run `clang -ffast-math` the CC1 invocation has both `-ffast-math` and 
> `-ffp-contract=fast` (and other options as well)
> 
> Here specifically I'm just considering the behavior of `clang -cc1 
> -ffast-math`.

Okay.  It is probably best for testing purposes if flags like this stay as 
close as possible to their driver behavior.  The driver can just canonicalize 
different spellings down to the interface that -cc1 wants.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale updated this revision to Diff 267124.
michele.scandale added a comment.
Herald added a reviewer: jdoerfert.
Herald added a subscriber: sstefan1.

Fixup more tests with now redundant `-ffp-contract=fast` option.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315

Files:
  clang/include/clang/Basic/CodeGenOptions.def
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/BackendUtil.cpp
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/lib/CodeGen/CodeGenFunction.cpp
  clang/lib/CodeGen/CodeGenFunction.h
  clang/lib/Frontend/CompilerInvocation.cpp
  clang/test/CodeGen/builtins-nvptx-ptx60.cu
  clang/test/CodeGen/fast-math.c
  clang/test/CodeGen/fp-floatcontrol-stack.cpp
  clang/test/CodeGen/fp-options-to-fast-math-flags.c
  clang/test/CodeGen/fpconstrained.c
  clang/test/CodeGen/fpconstrained.cpp
  clang/test/CodeGen/libcalls.c
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/library-builtin.cu
  clang/test/CodeGenOpenCL/relaxed-fpmath.cl
  clang/test/Headers/nvptx_device_math_sin.c
  clang/test/Headers/nvptx_device_math_sin.cpp
  clang/test/Parser/fp-floatcontrol-syntax.cpp

Index: clang/test/Parser/fp-floatcontrol-syntax.cpp
===
--- clang/test/Parser/fp-floatcontrol-syntax.cpp
+++ clang/test/Parser/fp-floatcontrol-syntax.cpp
@@ -22,7 +22,7 @@
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fdenormal-fp-math=preserve-sign,preserve-sign -ftrapping-math -fsyntax-only %s -DDEFAULT -verify
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fsyntax-only %s -ffp-contract=fast -DPRECISE -verify
 // RUN: %clang_cc1 -triple x86_64-linux-gnu -fsyntax-only %s -ftrapping-math -ffp-contract=off -frounding-math -ffp-exception-behavior=strict -DSTRICT -verify
-// RUN: %clang_cc1 -triple x86_64-linux-gnu -menable-no-infs -menable-no-nans -menable-unsafe-fp-math -fno-signed-zeros -mreassociate -freciprocal-math -ffp-contract=fast -ffast-math -ffinite-math-only -fsyntax-only %s -DFAST -verify
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -fsyntax-only %s -ffast-math -DFAST -verify
 double a = 0.0;
 double b = 1.0;
 
Index: clang/test/Headers/nvptx_device_math_sin.cpp
===
--- clang/test/Headers/nvptx_device_math_sin.cpp
+++ clang/test/Headers/nvptx_device_math_sin.cpp
@@ -1,8 +1,8 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
 // RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix=SLOW
-// RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -ffast-math -ffp-contract=fast
-// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math -ffp-contract=fast | FileCheck %s --check-prefix=FAST
+// RUN: %clang_cc1 -x c++ -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc -ffast-math
+// RUN: %clang_cc1 -x c++ -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -aux-triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - -ffast-math | FileCheck %s --check-prefix=FAST
 // expected-no-diagnostics
 
 #include 
Index: clang/test/Headers/nvptx_device_math_sin.c
===
--- clang/test/Headers/nvptx_device_math_sin.c
+++ clang/test/Headers/nvptx_device_math_sin.c
@@ -1,8 +1,8 @@
 // REQUIRES: nvptx-registered-target
 // RUN: %clang_cc1 -x c -internal-isystem %S/Inputs/include -fopenmp -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc
 // RUN: %clang_cc1 -x c -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -fopenmp -triple nvptx64-nvidia-cuda -au

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale updated this revision to Diff 267121.
michele.scandale added a comment.

Rebase + `-ffast-math` change the default contraction mode to fast.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315

Files:
  clang/include/clang/Basic/CodeGenOptions.def
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/BackendUtil.cpp
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/lib/CodeGen/CodeGenFunction.cpp
  clang/lib/CodeGen/CodeGenFunction.h
  clang/lib/Frontend/CompilerInvocation.cpp
  clang/test/CodeGen/builtins-nvptx-ptx60.cu
  clang/test/CodeGen/complex-math.c
  clang/test/CodeGen/fast-math.c
  clang/test/CodeGen/fp-options-to-fast-math-flags.c
  clang/test/CodeGen/fpconstrained.c
  clang/test/CodeGen/fpconstrained.cpp
  clang/test/CodeGen/libcalls.c
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/library-builtin.cu
  clang/test/CodeGenOpenCL/relaxed-fpmath.cl

Index: clang/test/CodeGenOpenCL/relaxed-fpmath.cl
===
--- clang/test/CodeGenOpenCL/relaxed-fpmath.cl
+++ clang/test/CodeGenOpenCL/relaxed-fpmath.cl
@@ -11,7 +11,7 @@
   // NORMAL: fdiv float
   // FAST: fdiv fast float
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float
   // NOSIGNED: fdiv nsz float
   return a / b;
@@ -38,7 +38,7 @@
 
 // UNSAFE: "less-precise-fpmad"="true"
 // UNSAFE: "no-infs-fp-math"="false"
-// UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "no-nans-fp-math"="false"
 // UNSAFE: "no-signed-zeros-fp-math"="true"
 // UNSAFE: "unsafe-fp-math"="true"
 
Index: clang/test/CodeGenCUDA/library-builtin.cu
===
--- clang/test/CodeGenCUDA/library-builtin.cu
+++ clang/test/CodeGenCUDA/library-builtin.cu
@@ -10,7 +10,7 @@
 
 // logf() should be calling itself recursively as we don't have any standard
 // library on device side.
-// DEVICE: call float @logf(float
+// DEVICE: call contract float @logf(float
 extern "C" __attribute__((device)) float logf(float __x) { return logf(__x); }
 
 // NOTE: this case is to illustrate the expected differences in behavior between
@@ -18,5 +18,5 @@
 // library.
 //
 // Host is assumed to have standard library, so logf() calls LLVM intrinsic.
-// HOST: call float @llvm.log.f32(float
+// HOST: call contract float @llvm.log.f32(float
 extern "C" float logf(float __x) { return logf(__x); }
Index: clang/test/CodeGenCUDA/builtins-amdgcn.cu
===
--- clang/test/CodeGenCUDA/builtins-amdgcn.cu
+++ clang/test/CodeGenCUDA/builtins-amdgcn.cu
@@ -10,7 +10,7 @@
 }
 
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__
 void test_ds_fmax(float src) {
   __shared__ float shared;
Index: clang/test/CodeGen/libcalls.c
===
--- clang/test/CodeGen/libcalls.c
+++ clang/test/CodeGen/libcalls.c
@@ -8,17 +8,17 @@
 void test_sqrt(float a0, double a1, long double a2) {
   // CHECK-YES: call float @sqrtf
   // CHECK-NO: call float @llvm.sqrt.f32(float
-  // CHECK-FAST: call float @llvm.sqrt.f32(float
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(float
   float l0 = sqrtf(a0);
 
   // CHECK-YES: call double @sqrt
   // CHECK-NO: call double @llvm.sqrt.f64(double
-  // CHECK-FAST: call double @llvm.sqrt.f64(double
+  // CHECK-FAST: call reassoc nsz arcp afn double @llvm.sqrt.f64(double
   double l1 = sqrt(a1);
 
   // CHECK-YES: call x86_fp80 @sqrtl
   // CHECK-NO: call x86_fp80 @llvm.sqrt.f80(x86_fp80
-  // CHECK-FAST: call x86_fp80 @llvm.sqrt.f80(x86_fp80
+  // CHECK-FAST: call reassoc nsz arcp afn x86_fp80 @llvm.sqrt.f80(x86_fp80
   long double l2 = sqrtl(a2);
 }
 
Index: clang/test/CodeGen/fpconstrained.cpp
===
--- clang/test/CodeGen/fpconstrained.cpp
+++ clang/test/CodeGen/fpconstrained.cpp
@@ -1,7 +1,7 @@
 // RUN: %clang_cc1 -x c++ -ftrapping-math -fexceptions -fcxx-exceptions -frounding-math -ffp-exception-behavior=strict -emit-llvm -o - %s | FileCheck %s -check-prefix=FPMODELSTRICT
 // RUN: %clang_cc1 -x c++ -ffp-contract=fast -fexceptions -fcxx-exceptions -emit-llvm -o - %s | FileCheck %s -check-prefix=PRECISE
 // RUN: %clang_cc1 -x c++ -ffast-math -fexceptions -fcxx-exceptions -ffp-contract=fast -emit-llvm -o - %s | FileCheck %s -check-prefix=FAST
-// RUN: %clang_cc1 -x c++ -ffast-math -fexceptions -fcxx-exceptions -emit-llvm -o - %s | FileCheck %s -check-prefix=FASTNOCONTRACT
+// RUN: %clang_cc

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale added a comment.

In D80315#2061164 , @rjmccall wrote:

> In D80315#2059160 , 
> @michele.scandale wrote:
>
> > In D80315#2058914 , @rjmccall 
> > wrote:
> >
> > > In D80315#2058735 , 
> > > @michele.scandale wrote:
> > >
> > > > In D80315#2058549 , @rjmccall 
> > > > wrote:
> > > >
> > > > > The code cleanups all seems reasonable.  The actual changes in 
> > > > > code-generation changes are because we were failing to set these 
> > > > > reliably?
> > > >
> > > >
> > > > Most of them yes.
> > > >
> > > > In the CUDA test we there is now `contract` because we honor the 
> > > > default contraction mode that for CUDA is set to fast.
> > >
> > >
> > > Right, and we weren't honoring that mode before?
> >
> >
> > Not in the setup of base fast-math flags inside `CodeGenFunction`. However 
> > when emitting code for expression with `FPOptions` stored in the AST nodes 
> > then `contract` was set correctly.
>
>
> Okay, that seems justifiable.
>
> >>> In `clang/test/CodeGen/complex-math.c` I've added `-ffp-contract=fast` to 
> >>> the command line option because `-ffast-math` at the CC1 level does not 
> >>> change the default contraction mode.
> >> 
> >> Oh, I see, makes sense.  So there was inconsistent treatment of the 
> >> options, where one thing observed it but others didn't, and that's been 
> >> fixed now.
> > 
> > Do you think we should handle `-ffast-math` as `-cl-fast-relaxed-math`, 
> > i.e. it implies the default contraction mode being "fast"?
>
> I'm actually surprised it doesn't.  I can't imagine why someone enabling fast 
> math would want contraction to be disabled.


Just to be clear the clang driver does the right thing.
If you run `clang -ffast-math` the CC1 invocation has both `-ffast-math` and 
`-ffp-contract=fast` (and other options as well)

Here specifically I'm just considering the behavior of `clang -cc1 -ffast-math`.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[John McCall via Phabricator via cfe-commits]

rjmccall added a comment.

In D80315#2059160 , @michele.scandale 
wrote:

> In D80315#2058914 , @rjmccall wrote:
>
> > In D80315#2058735 , 
> > @michele.scandale wrote:
> >
> > > In D80315#2058549 , @rjmccall 
> > > wrote:
> > >
> > > > The code cleanups all seems reasonable.  The actual changes in 
> > > > code-generation changes are because we were failing to set these 
> > > > reliably?
> > >
> > >
> > > Most of them yes.
> > >
> > > In the CUDA test we there is now `contract` because we honor the default 
> > > contraction mode that for CUDA is set to fast.
> >
> >
> > Right, and we weren't honoring that mode before?
>
>
> Not in the setup of base fast-math flags inside `CodeGenFunction`. However 
> when emitting code for expression with `FPOptions` stored in the AST nodes 
> then `contract` was set correctly.


Okay, that seems justifiable.

>>> In `clang/test/CodeGen/complex-math.c` I've added `-ffp-contract=fast` to 
>>> the command line option because `-ffast-math` at the CC1 level does not 
>>> change the default contraction mode.
>> 
>> Oh, I see, makes sense.  So there was inconsistent treatment of the options, 
>> where one thing observed it but others didn't, and that's been fixed now.
> 
> Do you think we should handle `-ffast-math` as `-cl-fast-relaxed-math`, i.e. 
> it implies the default contraction mode being "fast"?

I'm actually surprised it doesn't.  I can't imagine why someone enabling fast 
math would want contraction to be disabled.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale added a comment.

In D80315#2058914 , @rjmccall wrote:

> In D80315#2058735 , 
> @michele.scandale wrote:
>
> > In D80315#2058549 , @rjmccall 
> > wrote:
> >
> > > The code cleanups all seems reasonable.  The actual changes in 
> > > code-generation changes are because we were failing to set these reliably?
> >
> >
> > Most of them yes.
> >
> > In the CUDA test we there is now `contract` because we honor the default 
> > contraction mode that for CUDA is set to fast.
>
>
> Right, and we weren't honoring that mode before?


Not in the setup of base fast-math flags inside `CodeGenFunction`. However when 
emitting code for expression with `FPOptions` stored in the AST nodes then 
`contract` was set correctly.

> 
> 
>> In `clang/test/CodeGen/complex-math.c` I've added `-ffp-contract=fast` to 
>> the command line option because `-ffast-math` at the CC1 level does not 
>> change the default contraction mode.
> 
> Oh, I see, makes sense.  So there was inconsistent treatment of the options, 
> where one thing observed it but others didn't, and that's been fixed now.

Do you think we should handle `-ffast-math` as `-cl-fast-relaxed-math`, i.e. it 
implies the default contraction mode being "fast"?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[John McCall via Phabricator via cfe-commits]

rjmccall added a comment.

In D80315#2058735 , @michele.scandale 
wrote:

> In D80315#2058549 , @rjmccall wrote:
>
> > The code cleanups all seems reasonable.  The actual changes in 
> > code-generation changes are because we were failing to set these reliably?
>
>
> Most of them yes.
>
> In the CUDA test we there is now `contract` because we honor the default 
> contraction mode that for CUDA is set to fast.


Right, and we weren't honoring that mode before?

> In `clang/test/CodeGen/complex-math.c` I've added `-ffp-contract=fast` to the 
> command line option because `-ffast-math` at the CC1 level does not change 
> the default contraction mode.

Oh, I see, makes sense.  So there was inconsistent treatment of the options, 
where one thing observed it but others didn't, and that's been fixed now.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale added a comment.

In D80315#2058549 , @rjmccall wrote:

> The code cleanups all seems reasonable.  The actual changes in 
> code-generation changes are because we were failing to set these reliably?


Most of them yes.

In the CUDA test we there is now `contract` because we honor the default 
contraction mode that for CUDA is set to fast.

In `clang/test/CodeGen/complex-math.c` I've added `-ffp-contract=fast` to the 
command line option because `-ffast-math` at the CC1 level does not change the 
default contraction mode. We might want to treat `-ffast-math` similarly to 
`-cl-fast-relaxed-math`, i.e. it implies by default the "fast" contraction 
mode. Before this change there behavior was accidentally the same as 
"-ffast-math changes the default contraction mode" because there was:

  if (CGM.getLangOpts().FastMath)
FMF.setFast()

and so the bit for `AllowContract` was enabled in the fast-math flags.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[John McCall via Phabricator via cfe-commits]

rjmccall added a comment.

The code cleanups all seems reasonable.  The actual changes in code-generation 
changes are because we were failing to set these reliably?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Anastasia Stulova via Phabricator via cfe-commits]

Anastasia added inline comments.



Comment at: clang/test/CodeGenOpenCL/relaxed-fpmath.cl:14
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float

michele.scandale wrote:
> This change is based on the following:
> * `-cl-fast-relaxed-math` = `-cl-unsafe-math-optimizations` + 
> `-cl-finite-math-only` 
> * the GCC option `-funsafe-math-optimizations` and 
> `-cl-unsafe-math-optimizations` are described with very similar wording and 
> from the GCC description states explicitly mention that no signed zeros, 
> reassociation and reciprocals are enabled, but there is no mention to 
> assuming that NaNs do not exist.
> 
> See 
> https://www.khronos.org/registry/OpenCL/sdk/1.2/docs/man/xhtml/clBuildProgram.html
>  and https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html
Makes sense!


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale updated this revision to Diff 265405.
michele.scandale added a comment.

Fix formatting issues.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315

Files:
  clang/include/clang/Basic/CodeGenOptions.def
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/BackendUtil.cpp
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/lib/CodeGen/CodeGenFunction.cpp
  clang/lib/CodeGen/CodeGenFunction.h
  clang/lib/Frontend/CompilerInvocation.cpp
  clang/test/CodeGen/builtins-nvptx-ptx60.cu
  clang/test/CodeGen/complex-math.c
  clang/test/CodeGen/fp-options-to-fast-math-flags.c
  clang/test/CodeGen/libcalls.c
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/library-builtin.cu
  clang/test/CodeGenOpenCL/relaxed-fpmath.cl

Index: clang/test/CodeGenOpenCL/relaxed-fpmath.cl
===
--- clang/test/CodeGenOpenCL/relaxed-fpmath.cl
+++ clang/test/CodeGenOpenCL/relaxed-fpmath.cl
@@ -11,7 +11,7 @@
   // NORMAL: fdiv float
   // FAST: fdiv fast float
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float
   // NOSIGNED: fdiv nsz float
   return a / b;
@@ -38,7 +38,7 @@
 
 // UNSAFE: "less-precise-fpmad"="true"
 // UNSAFE: "no-infs-fp-math"="false"
-// UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "no-nans-fp-math"="false"
 // UNSAFE: "no-signed-zeros-fp-math"="true"
 // UNSAFE: "unsafe-fp-math"="true"
 
Index: clang/test/CodeGenCUDA/library-builtin.cu
===
--- clang/test/CodeGenCUDA/library-builtin.cu
+++ clang/test/CodeGenCUDA/library-builtin.cu
@@ -10,7 +10,7 @@
 
 // logf() should be calling itself recursively as we don't have any standard
 // library on device side.
-// DEVICE: call float @logf(float
+// DEVICE: call contract float @logf(float
 extern "C" __attribute__((device)) float logf(float __x) { return logf(__x); }
 
 // NOTE: this case is to illustrate the expected differences in behavior between
@@ -18,5 +18,5 @@
 // library.
 //
 // Host is assumed to have standard library, so logf() calls LLVM intrinsic.
-// HOST: call float @llvm.log.f32(float
+// HOST: call contract float @llvm.log.f32(float
 extern "C" float logf(float __x) { return logf(__x); }
Index: clang/test/CodeGenCUDA/builtins-amdgcn.cu
===
--- clang/test/CodeGenCUDA/builtins-amdgcn.cu
+++ clang/test/CodeGenCUDA/builtins-amdgcn.cu
@@ -10,7 +10,7 @@
 }
 
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__
 void test_ds_fmax(float src) {
   __shared__ float shared;
Index: clang/test/CodeGen/libcalls.c
===
--- clang/test/CodeGen/libcalls.c
+++ clang/test/CodeGen/libcalls.c
@@ -8,17 +8,17 @@
 void test_sqrt(float a0, double a1, long double a2) {
   // CHECK-YES: call float @sqrtf
   // CHECK-NO: call float @llvm.sqrt.f32(float
-  // CHECK-FAST: call float @llvm.sqrt.f32(float
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(float
   float l0 = sqrtf(a0);
 
   // CHECK-YES: call double @sqrt
   // CHECK-NO: call double @llvm.sqrt.f64(double
-  // CHECK-FAST: call double @llvm.sqrt.f64(double
+  // CHECK-FAST: call reassoc nsz arcp afn double @llvm.sqrt.f64(double
   double l1 = sqrt(a1);
 
   // CHECK-YES: call x86_fp80 @sqrtl
   // CHECK-NO: call x86_fp80 @llvm.sqrt.f80(x86_fp80
-  // CHECK-FAST: call x86_fp80 @llvm.sqrt.f80(x86_fp80
+  // CHECK-FAST: call reassoc nsz arcp afn x86_fp80 @llvm.sqrt.f80(x86_fp80
   long double l2 = sqrtl(a2);
 }
 
Index: clang/test/CodeGen/fp-options-to-fast-math-flags.c
===
--- /dev/null
+++ clang/test/CodeGen/fp-options-to-fast-math-flags.c
@@ -0,0 +1,42 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck -check-prefix CHECK-PRECISE %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -menable-no-nans -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-NANS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -menable-no-infs -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-INFS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -ffinite-math-only -emit-llvm -o - %s | FileCheck -check-prefix CHECK-FINITE %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fno-signed-zeros -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-SIGNED-ZEROS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -mreassociate -emit-llvm -o - %s | FileCheck -check-prefix CHEC

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Melanie Blower via Phabricator via cfe-commits]

mibintc added a comment.

Thanks for cleaning this up!


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale updated this revision to Diff 265333.
michele.scandale added a comment.

Fix 'clang/test/CodeGenCUDA/library-builtin.cu'


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315

Files:
  clang/include/clang/Basic/CodeGenOptions.def
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/BackendUtil.cpp
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/lib/CodeGen/CodeGenFunction.cpp
  clang/lib/CodeGen/CodeGenFunction.h
  clang/lib/Frontend/CompilerInvocation.cpp
  clang/test/CodeGen/builtins-nvptx-ptx60.cu
  clang/test/CodeGen/complex-math.c
  clang/test/CodeGen/fp-options-to-fast-math-flags.c
  clang/test/CodeGen/libcalls.c
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenCUDA/library-builtin.cu
  clang/test/CodeGenOpenCL/relaxed-fpmath.cl

Index: clang/test/CodeGenOpenCL/relaxed-fpmath.cl
===
--- clang/test/CodeGenOpenCL/relaxed-fpmath.cl
+++ clang/test/CodeGenOpenCL/relaxed-fpmath.cl
@@ -11,7 +11,7 @@
   // NORMAL: fdiv float
   // FAST: fdiv fast float
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float
   // NOSIGNED: fdiv nsz float
   return a / b;
@@ -38,7 +38,7 @@
 
 // UNSAFE: "less-precise-fpmad"="true"
 // UNSAFE: "no-infs-fp-math"="false"
-// UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "no-nans-fp-math"="false"
 // UNSAFE: "no-signed-zeros-fp-math"="true"
 // UNSAFE: "unsafe-fp-math"="true"
 
Index: clang/test/CodeGenCUDA/library-builtin.cu
===
--- clang/test/CodeGenCUDA/library-builtin.cu
+++ clang/test/CodeGenCUDA/library-builtin.cu
@@ -10,7 +10,7 @@
 
 // logf() should be calling itself recursively as we don't have any standard
 // library on device side.
-// DEVICE: call float @logf(float
+// DEVICE: call contract float @logf(float
 extern "C" __attribute__((device)) float logf(float __x) { return logf(__x); }
 
 // NOTE: this case is to illustrate the expected differences in behavior between
@@ -18,5 +18,5 @@
 // library.
 //
 // Host is assumed to have standard library, so logf() calls LLVM intrinsic.
-// HOST: call float @llvm.log.f32(float
+// HOST: call contract float @llvm.log.f32(float
 extern "C" float logf(float __x) { return logf(__x); }
Index: clang/test/CodeGenCUDA/builtins-amdgcn.cu
===
--- clang/test/CodeGenCUDA/builtins-amdgcn.cu
+++ clang/test/CodeGenCUDA/builtins-amdgcn.cu
@@ -10,7 +10,7 @@
 }
 
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__
 void test_ds_fmax(float src) {
   __shared__ float shared;
Index: clang/test/CodeGen/libcalls.c
===
--- clang/test/CodeGen/libcalls.c
+++ clang/test/CodeGen/libcalls.c
@@ -8,17 +8,17 @@
 void test_sqrt(float a0, double a1, long double a2) {
   // CHECK-YES: call float @sqrtf
   // CHECK-NO: call float @llvm.sqrt.f32(float
-  // CHECK-FAST: call float @llvm.sqrt.f32(float
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(float
   float l0 = sqrtf(a0);
 
   // CHECK-YES: call double @sqrt
   // CHECK-NO: call double @llvm.sqrt.f64(double
-  // CHECK-FAST: call double @llvm.sqrt.f64(double
+  // CHECK-FAST: call reassoc nsz arcp afn double @llvm.sqrt.f64(double
   double l1 = sqrt(a1);
 
   // CHECK-YES: call x86_fp80 @sqrtl
   // CHECK-NO: call x86_fp80 @llvm.sqrt.f80(x86_fp80
-  // CHECK-FAST: call x86_fp80 @llvm.sqrt.f80(x86_fp80
+  // CHECK-FAST: call reassoc nsz arcp afn x86_fp80 @llvm.sqrt.f80(x86_fp80
   long double l2 = sqrtl(a2);
 }
 
Index: clang/test/CodeGen/fp-options-to-fast-math-flags.c
===
--- /dev/null
+++ clang/test/CodeGen/fp-options-to-fast-math-flags.c
@@ -0,0 +1,42 @@
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck -check-prefix CHECK-PRECISE %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -menable-no-nans -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-NANS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -menable-no-infs -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-INFS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -ffinite-math-only -emit-llvm -o - %s | FileCheck -check-prefix CHECK-FINITE %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -fno-signed-zeros -emit-llvm -o - %s | FileCheck -check-prefix CHECK-NO-SIGNED-ZEROS %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -mreassociate -emit-llvm -o - %s | Fil

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale marked an inline comment as done.
michele.scandale added inline comments.



Comment at: clang/test/CodeGenOpenCL/relaxed-fpmath.cl:14
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float

This change is based on the following:
* `-cl-fast-relaxed-math` = `-cl-unsafe-math-optimizations` + 
`-cl-finite-math-only` 
* the GCC option `-funsafe-math-optimizations` and 
`-cl-unsafe-math-optimizations` are described with very similar wording and 
from the GCC description states explicitly mention that no signed zeros, 
reassociation and reciprocals are enabled, but there is no mention to assuming 
that NaNs do not exist.

See 
https://www.khronos.org/registry/OpenCL/sdk/1.2/docs/man/xhtml/clBuildProgram.html
 and https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale marked 2 inline comments as done.
michele.scandale added inline comments.



Comment at: clang/test/CodeGen/libcalls.c:11-21
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(float
   float l0 = sqrtf(a0);
 
   // CHECK-YES: call double @sqrt
   // CHECK-NO: call double @llvm.sqrt.f64(double
-  // CHECK-FAST: call double @llvm.sqrt.f64(double
+  // CHECK-FAST: call reassoc nsz arcp afn double @llvm.sqrt.f64(double
   double l1 = sqrt(a1);

For CUDA the default FP contract mode is `fast`, therefore the `contract` FMF 
is emitted.



Comment at: clang/test/CodeGenCUDA/builtins-amdgcn.cu:13
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* 
@_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* 
@_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__

For CUDA the default FP contract mode is `fast`, therefore the `contract` FMF 
is emitted.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80315/new/

https://reviews.llvm.org/D80315



___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D80315: Fix CC1 command line options mapping into fast-math flags.

[Michele Scandale via Phabricator via cfe-commits]

michele.scandale created this revision.
michele.scandale added reviewers: rjmccall, mibintc, Anastasia.
Herald added subscribers: cfe-commits, jvesely.
Herald added a project: clang.
michele.scandale marked an inline comment as done.
michele.scandale added inline comments.
michele.scandale marked 2 inline comments as done.



Comment at: clang/test/CodeGen/libcalls.c:11-21
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(float
   float l0 = sqrtf(a0);
 
   // CHECK-YES: call double @sqrt
   // CHECK-NO: call double @llvm.sqrt.f64(double
-  // CHECK-FAST: call double @llvm.sqrt.f64(double
+  // CHECK-FAST: call reassoc nsz arcp afn double @llvm.sqrt.f64(double
   double l1 = sqrt(a1);

For CUDA the default FP contract mode is `fast`, therefore the `contract` FMF 
is emitted.



Comment at: clang/test/CodeGenCUDA/builtins-amdgcn.cu:13
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* 
@_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* 
@_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__

For CUDA the default FP contract mode is `fast`, therefore the `contract` FMF 
is emitted.



Comment at: clang/test/CodeGenOpenCL/relaxed-fpmath.cl:14
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float

This change is based on the following:
* `-cl-fast-relaxed-math` = `-cl-unsafe-math-optimizations` + 
`-cl-finite-math-only` 
* the GCC option `-funsafe-math-optimizations` and 
`-cl-unsafe-math-optimizations` are described with very similar wording and 
from the GCC description states explicitly mention that no signed zeros, 
reassociation and reciprocals are enabled, but there is no mention to assuming 
that NaNs do not exist.

See 
https://www.khronos.org/registry/OpenCL/sdk/1.2/docs/man/xhtml/clBuildProgram.html
 and https://gcc.gnu.org/onlinedocs/gcc/Optimize-Options.html


This fixes the mapping between CC1 command line options to the
properties in `LangOptions` describing the floating point optimizations
configuration.
The default fast-math flags for the IR builder are now derived from such
properties to avoid inconsistencies.
Finally some of the `CodeGenOptions` floating point optimizations
properties have been removed since they are now exist in `LangOptions`.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D80315

Files:
  clang/include/clang/Basic/CodeGenOptions.def
  clang/include/clang/Basic/LangOptions.h
  clang/lib/CodeGen/BackendUtil.cpp
  clang/lib/CodeGen/CGCall.cpp
  clang/lib/CodeGen/CGExprScalar.cpp
  clang/lib/CodeGen/CodeGenFunction.cpp
  clang/lib/CodeGen/CodeGenFunction.h
  clang/lib/Frontend/CompilerInvocation.cpp
  clang/test/CodeGen/builtins-nvptx-ptx60.cu
  clang/test/CodeGen/complex-math.c
  clang/test/CodeGen/fp-options-to-fast-math-flags.c
  clang/test/CodeGen/libcalls.c
  clang/test/CodeGenCUDA/builtins-amdgcn.cu
  clang/test/CodeGenOpenCL/relaxed-fpmath.cl

Index: clang/test/CodeGenOpenCL/relaxed-fpmath.cl
===
--- clang/test/CodeGenOpenCL/relaxed-fpmath.cl
+++ clang/test/CodeGenOpenCL/relaxed-fpmath.cl
@@ -11,7 +11,7 @@
   // NORMAL: fdiv float
   // FAST: fdiv fast float
   // FINITE: fdiv nnan ninf float
-  // UNSAFE: fdiv nnan nsz float
+  // UNSAFE: fdiv reassoc nsz arcp afn float
   // MAD: fdiv float
   // NOSIGNED: fdiv nsz float
   return a / b;
@@ -38,7 +38,7 @@
 
 // UNSAFE: "less-precise-fpmad"="true"
 // UNSAFE: "no-infs-fp-math"="false"
-// UNSAFE: "no-nans-fp-math"="true"
+// UNSAFE: "no-nans-fp-math"="false"
 // UNSAFE: "no-signed-zeros-fp-math"="true"
 // UNSAFE: "unsafe-fp-math"="true"
 
Index: clang/test/CodeGenCUDA/builtins-amdgcn.cu
===
--- clang/test/CodeGenCUDA/builtins-amdgcn.cu
+++ clang/test/CodeGenCUDA/builtins-amdgcn.cu
@@ -10,7 +10,7 @@
 }
 
 // CHECK-LABEL: @_Z12test_ds_fmaxf(
-// CHECK: call float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
+// CHECK: call contract float @llvm.amdgcn.ds.fmax(float addrspace(3)* @_ZZ12test_ds_fmaxfE6shared, float %{{[^,]*}}, i32 0, i32 0, i1 false)
 __global__
 void test_ds_fmax(float src) {
   __shared__ float shared;
Index: clang/test/CodeGen/libcalls.c
===
--- clang/test/CodeGen/libcalls.c
+++ clang/test/CodeGen/libcalls.c
@@ -8,17 +8,17 @@
 void test_sqrt(float a0, double a1, long double a2) {
   // CHECK-YES: call float @sqrtf
   // CHECK-NO: call float @llvm.sqrt.f32(float
-  // CHECK-FAST: call float @llvm.sqrt.f32(float
+  // CHECK-FAST: call reassoc nsz arcp afn float @llvm.sqrt.f32(f