On 04/22/2014 02:35 PM, Tom Stellard wrote:
On Mon, Apr 21, 2014 at 10:02:27PM -0400, Jan Vesely wrote:
Hi,
I ran into a problem caused by this part of the OCL specs (6.1.5
Alignment of Types):
"For 3-component vector data types, the size of the data type is 4 *
sizeof(component)."
and the corresponding part of Khronos cl_platform.h (with all types, not
just float):
/* cl_float3 is identical in size, alignment and behavior to cl_float4.
See section 6.1.5. */
typedef cl_float4 cl_float3;
So when I try to run kernel that takes 3 element vectors as arguments I
get 'invalid arg size' error.
Not sure whether this is best solved in clang, libclc or clover. I tried
changing float3 to have 4 elements in libclc, it caused clang to
complain in thousand places. I don't think this can be handled cleanly
in clang, unless we add something like __attribute__((padding)).
I have attached a workaround that I use now.
You may want to ask this question on the pocl mailing list as they
have likely solved this issue already. Ideally, TD.getTypeStoreSize
would return the correct value. Also, maybe look at the DataLayout
description for R600 and see if there is a way to specify the
correct type size.
-Tom
I think this is what v96:128 is for
any advice welcome,
Jan
--
Jan Vesely <jan.ves...@rutgers.edu>
diff --git a/src/gallium/state_trackers/clover/llvm/invocation.cpp
b/src/gallium/state_trackers/clover/llvm/invocation.cpp
index a81bdf8..71ee01f 100644
--- a/src/gallium/state_trackers/clover/llvm/invocation.cpp
+++ b/src/gallium/state_trackers/clover/llvm/invocation.cpp
@@ -62,6 +62,8 @@
#include <llvm/IR/DataLayout.h>
#endif
+#include <llvm/Support/Debug.h>
+
#include "pipe/p_state.h"
#include "util/u_memory.h"
@@ -309,6 +311,13 @@ namespace {
llvm::Type *arg_type = arg.getType();
unsigned arg_size = TD.getTypeStoreSize(arg_type);
+ if (arg_type->isVectorTy() &&
+ ::llvm::cast<::llvm::VectorType>(arg_type)->getNumElements() ==
3) {
+ ::llvm::dbgs() << "Fixing argument type: " << *arg_type
+ << " size: " << arg_size << "->"
+ << (arg_size / 3) * 4 << "\n";
+ arg_size = (arg_size / 3) * 4;
+ }
llvm::Type *target_type = arg_type->isIntegerTy() ?
TD.getSmallestLegalIntType(mod->getContext(), arg_size * 8) :
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
_______________________________________________
cfe-dev mailing list
cfe-...@cs.uiuc.edu
http://lists.cs.uiuc.edu/mailman/listinfo/cfe-dev
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
