Fixup the problem of CL_PROGRAM_BINARIES in clGetProgramInfo API

clGetProgramInfo using CL_PROGRAM_BINARIES to get the binary will
not be right because the binary got is not the serilization one.
Add the serilization there to fix this bug.

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

fix builtin function "fmax"

if an parameter is nan, then returns another parameter.

v2: no need to test nan for integer
Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

GBE: Fix alignment for private variables

Private variables allocated on the stack should be aligned according to OCL spec.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Tested-by: Zhigang Gong <zhigang.gong@linux.intel.com>

GBE: Fix alignment according to OCL spec

The patch simply store a 'align' for each kernel argument.
Then the runtime could align the kernel argument address to 'align'.
This patch works for constant and local address space.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Tested-by: Zhigang Gong <zhigang.gong@linux.intel.com>

GBE: Remove max_limit for struct alignment

a struct may have vector field (like int8/16), max_limit is meaningless.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Tested-by: Zhigang Gong <zhigang.gong@linux.intel.com>

release context in runtime_createcontextfromtype

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Move the gpgpu struct from cl_command_queue to thread specific context

We find some cases will use multi-threads to run on the same queue,
executing the same kernel. This will cause the gpgpu struct which
is very important for GPU context setting be destroyed because we
do not implement any sync protect on it now.
Move the gpgpu struct into thread specific space will fix this problem
because the lib_drm will do the GPU command serialization for us.

Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Zou, Nanhai" <nanhai.zou@intel.com>

Add the clGetMemObjectInfo options for sub-buffer and update the utest case

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Add the test case for sub buffer check

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Implement the clCreateSubBuffer API

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Add the bo's internal offset support when do drm_intel_bo_emit_reloc

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

GBE: fix a 64bit scalar register issue.

For scalar register, should use stride 0.
also change the unit test to hit the point.

v2: fix h2()

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

improve multithread calling of llvm

call llvm multithread function instead of using a semaphore.
also exit llvm multithread mode at the end of life.

v2: not call llvm::shutdown() if llvm is older than 3.4
Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>
Tested-by: Zhigang Gong <zhigang.gong@linux.intel.com>

fix builtin function "fract"

v2: return nan for nan, +zero for +inf, -zero for -inf.
Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

fix builtin function "copysign"

using better algorithm

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

fix builtin function 'frexp'

returns correct value for nan or inf.
also returns correct value for very small float value.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

release previous program in cl_kernel_init

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

release previous kernel in cl_kernel_init

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: fix some max/alignment values.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: fix one bug in clGetProgramInfo.

The CL_PROGRAM_BINARIES forget to return the param value size.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: Don't modify argument 0 of the get image information instruction.

When the first round compilation fail, GBE will turn to recompile the
sample program by using another profile. If we changed the argument
0 of the get image information instruction, then it will fail the second
round compilation. But the argument 1 is ok to change, as we never change
the first instruction's argument, and all the subsequent instruction's
argument 1 is free to change.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: fix the length of properties.

The last zero should also be counted.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: implement clGetSamplerInfo.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: fix some max values.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: fix the incorrect device info string size.

sizeof(str) already includes the '\0', we don't need to add
1 to it.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: disable MulAdd pattern in instruction selection temporarily.

The story starts from 'FP_CONTRACT'. In c99 spec, it describes constract
expression as:
"A floating expression may be contracted, that is, evaluated as though it
were an atomic operation, thereby omitting rounding errors implied by the
source code and the expression evaluation method."

But user can use 'pragma FP_CONTRACT OFF' to disable float contraction,
in which condition, we should not do contraction like mad optimization.
In SPIR 1.2, named metadata 'opencl.enable.FP_CONTRACT' will be used to do this.
When Clang is ready, we need refine the backend logic.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: Homer Hsing <homer.xing@intel.com>

utests: add test case for structure argument

Signed-off-by: Lu Guanqun <guanqun.lu@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

fix the error that structure would be pushed twice

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Tested-by: Lu Guanqun <guanqun.lu@intel.com>
Reviewed-by: Lu Guanqun <guanqun.lu@intel.com>

GBE: use ISA mad for mad() builtin function.

directly map mad() to ISA mad. so mad will have better performance and
less precision loss.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

utests: use mad which will get better precision.

Normal mul/add could not met the precision requirement of this case.
Previously it passed because we will do mad optimization in backend.
Use mad directly, so the test case does not depend on backend optimization.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Add a necessary include path for building with mesa.

Reported by Lv Meng.

Signed-off-by: Zhigang Gong <zhigang.gong@intel.com>

fix operators for 64 bit integer

if operand is signed 64 bit integer, emit -1 for SExt casting

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

fix pointer bugs in linked list

change the header of linked list if the header was deleted

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

fix ill-coded utest_run::main

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

add same type converting

converting a data type to same type ...

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Song, Ruiling" <ruiling.song@intel.com>

runtime: Fix a dangling pointer issue

ctx->events points to the head of 'event list' under the ctx.
When deleting an event from the list, we should also update
the head pointer besides updating its neighbour's next & prev,

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewedy-by: "Xing, Homer" <homer.xing@intel.com>

GBE: fixed one bug for vector relational builtin functions.

For most vector relational builtin functions, we need to
return -1 if the element result is true, return 0 if the element
result is 0. So we can simply put a - in front of the scalar
version of function for each element.

Reported by Yang Rong.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: Yang Rong <rong.r.yang@intel.com>

fix built-in function "normalize"

divide the parameter by its length

ver 2: scalar typed function returns NaN if parameter is NaN.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

fix built-in function "fast_normalize"

if the parameter is zero, then return zero
if the parameter is positive, then return 1.
for other cases, return -1.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Lu, Guanqun" <guanqun.lu@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

GBE: Give a zero-initialized register for Undef value.

For instructions that reference an undef value, we simply
allocate a register to the undef operand and set as 0.

v2:
handle float and double type. also fix some typos about double type.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

Refine the build option checking.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: "Song, Ruiling" <ruiling.song@intel.com>

Fix a event segment fault.

If event type is CL_COMMAND_USER, event->queue is NULL, cause segment fault.
Change the order to fix it.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

GBE: enable bitselect vector builtin functions.

Now we have the scalar version of bitselect, so we
enable the vector version in the def file. Also remove
some comments.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: fixed an incorrect error checking for CL_INVALID_GLOBAL_OFFSET.

According to OpenCL spec:

CL_INVALID_GLOBAL_OFFSET if the value specified in global_work_size + the
corresponding values in global_work_offset for any dimensions is greater than the
sizeof(size t) for the device on which the kernel execution will be enqueued.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

GBE: fix 3-component vector's astype macros.

According to OpenCL spec,

For 3-component vector data types, the size of the data type is 4 * sizeof(component). This
means that a 3-component vector data type will be aligned to a 4 * sizeof(component)
boundary. The vload3 and vstore3 built-in functions can be used to read and write, respectively,
3-component vector data types from an array of packed scalar data type.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

GBE: fix a bug for the cast(FPToUI) instruction.

We need to choose unsigned dst type for this case.

v2:
fix a typo.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

fix built-in function "length"

if vector is zero, then returns zero.
if vector is very large, then do a scaling first.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

delete vec-8 or vec-16 typed geometric built-in

per OpenCL spec (ver 1.1 or 1.2), geometric built-in
should not have vec-8 type or vec-16 type versions.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

not use "mad" in vector type "dot"

the purpose is just to make code more readable, for float16 case

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Per openCL spec, set p->is_built to 1 when build fail.

Also correct the err code when build fail.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Song, Ruiling" <ruiling.song@intel.com>

Re-build the program when build option changed.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Song, Ruiling" <ruiling.song@intel.com>

Remove CL_FP_DENORM in clGetDeviceInfo.

IVB don't support single float denorm, so compiler option -cl-denorms-are-zero should ingore.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Song, Ruiling" <ruiling.song@intel.com>

Add preprocessor #define that match the extension name string.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

utest: add test case for builtin function exp/exp2/exp10/expm1.

Signed-off-by: Yi Sun <yi.sun@intel.com>
Signed-off-by: Yangwei Shui <yangweix.shui@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

utest: Add test case for built-in function pow.

Signed-off-by: Yi Sun <yi.sun@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

support saturated-rounding converting

passed piglit test case:
  piglit/bin/cl-program-tester tests/cl/program/execute/vector-conversion.cl

version 2:
  contains updating of ocl_convert.h

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

support converting with rounding mode

support built-in functions of converting with rounding mode,
such as "convert_DSTTYPE_rtz, rte, rtp, rtn".

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

initialize GenRegister::subphysical

GenRegister::subphysical should have same init value as GenRegister::physical
Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

add scalar type builtin function "dot"

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Song, Ruiling" <ruiling.song@intel.com>
Reviewed-by: "Lu, Guanqun" <guanqun.lu@intel.com>

implement __builtin_* functions

backend does not support __builtin_* functions,
so they are implemented in ocl_stdlib.tmpl.h

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Bump to version 0.3.

Also update some documents accordingly.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>

add a semaphore for clang lib

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Disable instrucion schedule temp.

If enable schedule, will cause fails. Will enable it after fix these fails.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

Fix two memory leak.

Signed-off-by: Chuanbo Weng <chuanbo.weng@intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

GBE: Fix a bo->offset assert

scratchSize was missed in the binary, which will cause a random value
when kernel is loaded from binary. add it in the binary format.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: He Junyan <junyan.he@inbox.com>

Fix zeroinitializer load/store vector assert.

After move the newValueProxy of vector load/store to genWriter pass, genWriter will
get ConstantAggregateZero of load/store vector with zeroinitializer. In function processConstant,
don't handle correct type of ConstantAggregateZero, cause assert. Add the types handle.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: "Xing, Homer" <homer.xing@intel.com>

Add a test for vector argument deallocate assert.

V2: Add result compare.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Ruiling Song <ruiling.song@intel.com>

Change -O3 to -O2 again because my previous change's typo.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Ruiling Song <ruiling.song@intel.com>

Refine vector register deallocate.

Split vector registers block, so can free them seperate.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Ruiling Song <ruiling.song@intel.com>

Fix a vector argument deallocate assert.

Vector argument will allocate together but deallocate sepelate, when deallocate
will assert. Split the each allocatedBlock in register partitioner to fix it.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>

Add more type for async copy test case.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

use int64_t to express "long" in a test case

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

runtime: Simply return success in clUnloadCompiler.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: Handle all-zero constant.

Also refine Undef value support.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

support vectorized saturated converting builtin functions

version 2: skip convert_float_sat(*)

version 3:
  scalar converting is moved from "ocl_stdlib.tmpl.h" to "gen_convert.sh",
  because scalar converting should be before vectorized version.

  "ocl_convert.h" is updated.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

support saturated converting from narrower type to wider type

This patch supports saturated converting from narrower type to wider type.
It simply returns the parameter.

version 2: not need convert_float_sat(*)

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

support saturated converting from 64-bit int

This patch supports saturated converting from 64-bit int to shorter int,
and from 32-bit float to 64-bit int.

This patch also contains test case.

version 2: ulong had been declared in some platform

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Runtime: correct some image related maximum values for IVB.

Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Add test case for newValueProxy of InsertElementInst.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Remove newValueProxy from scalarize pass to genWriter pass.

If call newValueProxy in scalarize pass, the realValue maybe been deleted by
the following pass, cause assert. Move to genWriter pass, can fix this bug and
make code more clean.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

add clCreateImageFromLibvaIntel() api

We can pass in libva's buffer object with other info and then create an image
in our CL code.

Signed-off-by: Lu Guanqun <guanqun.lu@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

add clCreateBufferFromLibvaIntel() api

We can pass in libva's buffer object name and then create the cl buffer from
it, thus we can share the buffer between libva and our opencl.

Signed-off-by: Lu Guanqun <guanqun.lu@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Implement the CL api for clGetEventProfilingInfo

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Using the PIPE_CONTROL to implement get time stamp in gen backend

We use PIPE_CONTROL to get the time stamps from GPU just after batch
start and before batch flush. Using the first one the caculate the
CL_PROFILING_COMMAND_START time and uing the second one to caculate
the CL_PROFILING_COMMAND_END time.
There are 2 limitations here:
1. Then end time stamp is just before the FLUSH, so the Flush time
   is not included, which will cause to lose the accuracy. Because
   the we do not know which event will be used to do the profling
   when it is created, adding another flush for end time stamp may
   add some overload.
2. The time of CPU and GPU can not be sync correctly now. So the
   time of CL_PROFILING_COMMAND_QUEUED and CL_PROFILING_COMMAND_SUBMIT
   which happens on CPU side can not be caculated correctly with the
   same base time of GPU. So we just simplely set them to
   CL_PROFILING_COMMAND_START now. For the Event not involving GPU
   operations such as ReadBuffer, all the times are 0 now.

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: Yang Rong <rong.r.yang@intel.com>

utests: add test cases for function call.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: Skip non-kernel functions in backend passes.

As non-kernel functions hit many assert in the backend, simply
skip them as we already inline all function calls.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: Inline all function calls.

use an extra large value for llvm flag -inline-threshold to inline all functions.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Add type long/ulong/double's async copy.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Fix a read64/write64 schedule bug.

Set the read64/write64 correct data type, otherwise, the dependency will wrong.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

Delete the redundant intel_batchbuffer_t init in intel_gpgpu_new

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: Update program binary format.

1. Remove useless 'reg' field of constant.
2. Add slmSize for local variables defined in kernel function.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

GBE: Support local variable inside kernel function.

As Clang treat local variable in similar way like global constant,
(they are treated as Global variable in each own address space)
we refine the previous constant implementation in order to
share same code between local variable and global constant.

We will allocate an address register for each GlobalVariable
(constant or local) through calling newRegister().
In later step, through getRegister() we will get a proper
register derived from the allocated address register.

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

support LLVM 3.4

LLVM 3.3 or earlier version don't support unary addition of vectors,
such as "++ int2". This patch supports LLVM 3.4.
Tested by PIGLIT, no regression.

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Add the test case for clEnqueueCopyBuffer

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Implement the clEnqueueCopyBuffer API using internal binary kernel

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Add the internal used kernels for buffer copy

Add internal used kernels for buffer copy. The align
1 4 16 is seperated into three kernels to improve
performance. The CMakeList is also updated.

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Add the string format support for gbe_bin_generater

The string format of kernel serializaion will be useful for
generating the code for internal kernel binary load in.

Signed-off-by: Junyan He <junyan.he@linux.intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>

Implement api clCreateKernelsInProgram.

Signed-off-by: Yang Rong <rong.r.yang@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

utests: put compiler_vector_inc into known issue list.

because ++/-- need LLVM3.4

Signed-off-by: Ruiling Song <ruiling.song@intel.com>
Reviewed-by: Zhigang Gong <zhigang.gong@linux.intel.com>

saturated conversion of native GPU data type, larger to narrower

This patch supports saturated conversion of
native GPU data type (char/short/int/float),
from a larger-range data type to a narrower-range data type.
For instance,  convert_uchar_sat(int)

Several test cases are in this patch.

v2: add uint->int, int->uint

Signed-off-by: Homer Hsing <homer.xing@intel.com>
Reviewed-by: "Yang, Rong R" <rong.r.yang@intel.com>