This test only try to allocate buffer with size large than
CL_DEVICE_MAX_MEM_ALLOC_SIZE, and
assert if return status if not CL_INVALID_BUFFER_SIZE. But in openCL spec:
Implementations may return CL_INVALID_BUFFER_SIZE if size is greater than
CL_DEVICE_MAX_MEM_ALLOC_SIZE value specified in table 4.
According to spec, we need to support CL_PROGRAM_BUILD_LOG which is
used to get the build log of a cl kernel. And we also need to check
whether a build failure is a generic build fail or a build option
error. This commit also fix the piglit case:
API/clBuildProgram.
Another change in this commit i
I agree. This test case is useless now. Will push this patch latter, thanks.
On Wed, Nov 27, 2013 at 04:40:30PM +0800, Yang Rong wrote:
> This test only try to allocate buffer with size large than
> CL_DEVICE_MAX_MEM_ALLOC_SIZE, and
> assert if return status if not CL_INVALID_BUFFER_SIZE. But in
LGTM, thanks.
-Original Message-
From: beignet-boun...@lists.freedesktop.org
[mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Zhigang Gong
Sent: Wednesday, November 27, 2013 4:05 PM
To: beignet@lists.freedesktop.org
Cc: Gong, Zhigang
Subject: [Beignet] [PATCH v2] Runtime: imple
LGTM, thanks.
-Original Message-
From: beignet-boun...@lists.freedesktop.org
[mailto:beignet-boun...@lists.freedesktop.org] On Behalf Of Zhigang Gong
Sent: Wednesday, November 27, 2013 10:47 AM
To: beignet@lists.freedesktop.org
Cc: Gong, Zhigang
Subject: [Beignet] [PATCH 1/2] Fix a build
LGTM, will push latter, thanks.
On Tue, Nov 26, 2013 at 05:59:54PM +0800, junyan...@inbox.com wrote:
> From: Junyan He
>
> Add the support when the DRM lib is not in the system standard location.
> In some cases, we want to debug the libdrm but not want to influence the
> whole system.
>
> Sign
Yi,
This is really an efficient way to test the builtin math functions.
Two minor comments here:
1. Could you put all the generated unit test cases to sub-directory of the
utests?
2. It's better to delete all the generated files when do a make clean.
3. On the auto-generated test cases. It's bett
summary:
pass: 1478
fail: 5
crash: 0
skip: 1 (This case should be skipped)
warn: 10
dmesg-warn: 0
dmesg-fail: 0
total: 1494
Only 5 failed cases (9 in last test circle), 10 warn cases (22 in last test
circle).
Following are the improved test cases:
API/clBui
Great job! But I have two comments to share:
1. seems that you use FLT_ULP(0.01) as the ulp unit. In fact, 1 ulp
means the 'last bit of fraction part' in ieee754 representation. In radix b, if
x has exponent E, then ULP(x) = (2^-23) * (b^E). see
http://en.wikipedia.org/wiki/Unit_in_the_
Signed-off-by: Yang Rong
---
backend/src/backend/program.cpp | 2 ++
1 file changed, 2 insertions(+)
diff --git a/backend/src/backend/program.cpp b/backend/src/backend/program.cpp
index 8e80bbb..751c11d 100644
--- a/backend/src/backend/program.cpp
+++ b/backend/src/backend/program.cpp
@@ -503,6
As the unsupported argument may trigger unexpected compilation
error, we just remove them from the arglist.
If latter clang's cl frontend supports these arguments, we need
to revisit here.
This patch also add a new environment variable
OCL_OUTPUT_BUILD_LOG.
If this variable is set to 1, GBE will
LGTM, pushed, thanks.
On Thu, Nov 28, 2013 at 11:00:43AM +0800, Yang Rong wrote:
>
> Signed-off-by: Yang Rong
> ---
> backend/src/backend/program.cpp | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/backend/src/backend/program.cpp b/backend/src/backend/program.cpp
> index 8e80bbb..75
From: Junyan He
The profiling feature is now all supported. We use
drm_intel_reg_read to get the current time of GPU
when the event is queued and submitted, and use
PIPI_CONTROL cmd to get the executing time of the
GPU for kernel start and end.
One trivial problem is that:
The GPU timer counter i
13 matches
Mail list logo