2016-07-14 05:21:05 +08:00
|
|
|
// RUN: %clang -S -### -cl-std=CL %s 2>&1 | FileCheck --check-prefix=CHECK-CL %s
|
|
|
|
// RUN: %clang -S -### -cl-std=CL1.1 %s 2>&1 | FileCheck --check-prefix=CHECK-CL11 %s
|
|
|
|
// RUN: %clang -S -### -cl-std=CL1.2 %s 2>&1 | FileCheck --check-prefix=CHECK-CL12 %s
|
|
|
|
// RUN: %clang -S -### -cl-std=CL2.0 %s 2>&1 | FileCheck --check-prefix=CHECK-CL20 %s
|
2018-04-12 22:17:04 +08:00
|
|
|
// RUN: %clang -S -### -cl-std=c++ %s 2>&1 | FileCheck --check-prefix=CHECK-CLCPP %s
|
2016-07-14 05:21:05 +08:00
|
|
|
// RUN: %clang -S -### -cl-opt-disable %s 2>&1 | FileCheck --check-prefix=CHECK-OPT-DISABLE %s
|
|
|
|
// RUN: %clang -S -### -cl-strict-aliasing %s 2>&1 | FileCheck --check-prefix=CHECK-STRICT-ALIASING %s
|
|
|
|
// RUN: %clang -S -### -cl-single-precision-constant %s 2>&1 | FileCheck --check-prefix=CHECK-SINGLE-PRECISION-CONST %s
|
|
|
|
// RUN: %clang -S -### -cl-finite-math-only %s 2>&1 | FileCheck --check-prefix=CHECK-FINITE-MATH-ONLY %s
|
|
|
|
// RUN: %clang -S -### -cl-kernel-arg-info %s 2>&1 | FileCheck --check-prefix=CHECK-KERNEL-ARG-INFO %s
|
|
|
|
// RUN: %clang -S -### -cl-unsafe-math-optimizations %s 2>&1 | FileCheck --check-prefix=CHECK-UNSAFE-MATH-OPT %s
|
|
|
|
// RUN: %clang -S -### -cl-fast-relaxed-math %s 2>&1 | FileCheck --check-prefix=CHECK-FAST-RELAXED-MATH %s
|
|
|
|
// RUN: %clang -S -### -cl-mad-enable %s 2>&1 | FileCheck --check-prefix=CHECK-MAD-ENABLE %s
|
|
|
|
// RUN: %clang -S -### -cl-no-signed-zeros %s 2>&1 | FileCheck --check-prefix=CHECK-NO-SIGNED-ZEROS %s
|
|
|
|
// RUN: %clang -S -### -cl-denorms-are-zero %s 2>&1 | FileCheck --check-prefix=CHECK-DENORMS-ARE-ZERO %s
|
2016-08-10 04:10:18 +08:00
|
|
|
// RUN: %clang -S -### -cl-fp32-correctly-rounded-divide-sqrt %s 2>&1 | FileCheck --check-prefix=CHECK-ROUND-DIV %s
|
[OpenCL] Add '-cl-uniform-work-group-size' compile option
Summary:
OpenCL 2.0 specification defines '-cl-uniform-work-group-size' option,
which requires that the global work-size be a multiple of the work-group
size specified to clEnqueueNDRangeKernel and allows optimizations that
are made possible by this restriction.
The patch introduces the support of this option.
To keep information about whether an OpenCL kernel has uniform work
group size or not, clang generates 'uniform-work-group-size' function
attribute for every kernel:
- "uniform-work-group-size"="true" for OpenCL 1.2 and lower,
- "uniform-work-group-size"="true" for OpenCL 2.0 and higher if
'-cl-uniform-work-group-size' option was specified,
- "uniform-work-group-size"="false" for OpenCL 2.0 and higher if no
'-cl-uniform-work-group-size' options was specified.
If the function is not an OpenCL kernel, 'uniform-work-group-size'
attribute isn't generated.
Patch by: krisb
Reviewers: yaxunl, Anastasia, b-sumner
Reviewed By: yaxunl, Anastasia
Subscribers: nhaehnle, yaxunl, Anastasia, cfe-commits
Differential Revision: https://reviews.llvm.org/D43570
llvm-svn: 325771
2018-02-22 19:54:14 +08:00
|
|
|
// RUN: %clang -S -### -cl-uniform-work-group-size %s 2>&1 | FileCheck --check-prefix=CHECK-UNIFORM-WG %s
|
2016-07-14 05:21:05 +08:00
|
|
|
// RUN: not %clang -cl-std=c99 -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-C99 %s
|
|
|
|
// RUN: not %clang -cl-std=invalid -DOPENCL %s 2>&1 | FileCheck --check-prefix=CHECK-INVALID %s
|
2016-06-30 03:39:32 +08:00
|
|
|
|
2016-07-14 23:06:57 +08:00
|
|
|
// CHECK-CL: "-cc1" {{.*}} "-cl-std=CL"
|
|
|
|
// CHECK-CL11: "-cc1" {{.*}} "-cl-std=CL1.1"
|
|
|
|
// CHECK-CL12: "-cc1" {{.*}} "-cl-std=CL1.2"
|
|
|
|
// CHECK-CL20: "-cc1" {{.*}} "-cl-std=CL2.0"
|
2018-04-12 22:17:04 +08:00
|
|
|
// CHECK-CLCPP: "-cc1" {{.*}} "-cl-std=c++"
|
2016-07-14 23:06:57 +08:00
|
|
|
// CHECK-OPT-DISABLE: "-cc1" {{.*}} "-cl-opt-disable"
|
|
|
|
// CHECK-STRICT-ALIASING: "-cc1" {{.*}} "-cl-strict-aliasing"
|
|
|
|
// CHECK-SINGLE-PRECISION-CONST: "-cc1" {{.*}} "-cl-single-precision-constant"
|
|
|
|
// CHECK-FINITE-MATH-ONLY: "-cc1" {{.*}} "-cl-finite-math-only"
|
|
|
|
// CHECK-KERNEL-ARG-INFO: "-cc1" {{.*}} "-cl-kernel-arg-info"
|
|
|
|
// CHECK-UNSAFE-MATH-OPT: "-cc1" {{.*}} "-cl-unsafe-math-optimizations"
|
|
|
|
// CHECK-FAST-RELAXED-MATH: "-cc1" {{.*}} "-cl-fast-relaxed-math"
|
|
|
|
// CHECK-MAD-ENABLE: "-cc1" {{.*}} "-cl-mad-enable"
|
|
|
|
// CHECK-NO-SIGNED-ZEROS: "-cc1" {{.*}} "-cl-no-signed-zeros"
|
|
|
|
// CHECK-DENORMS-ARE-ZERO: "-cc1" {{.*}} "-cl-denorms-are-zero"
|
2016-08-10 04:10:18 +08:00
|
|
|
// CHECK-ROUND-DIV: "-cc1" {{.*}} "-cl-fp32-correctly-rounded-divide-sqrt"
|
[OpenCL] Add '-cl-uniform-work-group-size' compile option
Summary:
OpenCL 2.0 specification defines '-cl-uniform-work-group-size' option,
which requires that the global work-size be a multiple of the work-group
size specified to clEnqueueNDRangeKernel and allows optimizations that
are made possible by this restriction.
The patch introduces the support of this option.
To keep information about whether an OpenCL kernel has uniform work
group size or not, clang generates 'uniform-work-group-size' function
attribute for every kernel:
- "uniform-work-group-size"="true" for OpenCL 1.2 and lower,
- "uniform-work-group-size"="true" for OpenCL 2.0 and higher if
'-cl-uniform-work-group-size' option was specified,
- "uniform-work-group-size"="false" for OpenCL 2.0 and higher if no
'-cl-uniform-work-group-size' options was specified.
If the function is not an OpenCL kernel, 'uniform-work-group-size'
attribute isn't generated.
Patch by: krisb
Reviewers: yaxunl, Anastasia, b-sumner
Reviewed By: yaxunl, Anastasia
Subscribers: nhaehnle, yaxunl, Anastasia, cfe-commits
Differential Revision: https://reviews.llvm.org/D43570
llvm-svn: 325771
2018-02-22 19:54:14 +08:00
|
|
|
// CHECK-UNIFORM-WG: "-cc1" {{.*}} "-cl-uniform-work-group-size"
|
2016-07-14 05:21:05 +08:00
|
|
|
// CHECK-C99: error: invalid value 'c99' in '-cl-std=c99'
|
|
|
|
// CHECK-INVALID: error: invalid value 'invalid' in '-cl-std=invalid'
|
2016-06-18 01:19:28 +08:00
|
|
|
|
|
|
|
kernel void func(void);
|