76333 Commits

Author SHA1 Message Date
foreman 42fcc19238 P4 to Git Change 1246830 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/13 04:00:10
SWDEV-2 - Change OpenCL version number from 2061 to 2062.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1808 edit
2016-03-13 04:10:50 -04:00
Ben Sander 5efb582db5 Remove ROCR_V2, assume=1
[ROCm/clr commit: 59f0ef2801]
2016-03-12 04:08:13 -06:00
Ben Sander 59f0ef2801 Remove ROCR_V2, assume=1 2016-03-12 04:08:13 -06:00
Ben Sander e08baf41d7 Remove ROCR_V2, assume=1
[ROCm/hip commit: b0dca6bd0c]
2016-03-12 04:08:13 -06:00
Ben Sander b0dca6bd0c Remove ROCR_V2, assume=1 2016-03-12 04:08:13 -06:00
Ben Sander a236942ca5 Remove USE_AM_TRACKER (assume 1)
[ROCm/clr commit: de4bb0ca0e]
2016-03-12 04:04:57 -06:00
Ben Sander de4bb0ca0e Remove USE_AM_TRACKER (assume 1) 2016-03-12 04:04:57 -06:00
Ben Sander 30fbe45694 Remove USE_AM_TRACKER (assume 1)
[ROCm/hip commit: a5a2c7f33c]
2016-03-12 04:04:57 -06:00
Ben Sander a5a2c7f33c Remove USE_AM_TRACKER (assume 1) 2016-03-12 04:04:57 -06:00
Ben Sander d6ad50c2e0 Improve error reporting.
use throw with error class.
fix bug when memcpyDefault resolved to D2D copy.


[ROCm/clr commit: ac272932f6]
2016-03-12 04:02:04 -06:00
Ben Sander ac272932f6 Improve error reporting.
use throw with error class.
fix bug when memcpyDefault resolved to D2D copy.
2016-03-12 04:02:04 -06:00
Ben Sander 4900ebb39f Improve error reporting.
use throw with error class.
fix bug when memcpyDefault resolved to D2D copy.


[ROCm/hip commit: 250739666d]
2016-03-12 04:02:04 -06:00
Ben Sander 250739666d Improve error reporting.
use throw with error class.
fix bug when memcpyDefault resolved to D2D copy.
2016-03-12 04:02:04 -06:00
foreman e38f50fee0 P4 to Git Change 1246786 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/12 03:00:10
SWDEV-2 - Change OpenCL version number from 2060 to 2061.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1807 edit


[ROCm/clr commit: e3b5848d6d]
2016-03-12 03:12:07 -05:00
foreman e3b5848d6d P4 to Git Change 1246786 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/12 03:00:10
SWDEV-2 - Change OpenCL version number from 2060 to 2061.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1807 edit
2016-03-12 03:12:07 -05:00
Harish Kasiviswanathan 1c1bc32477 Sync IOLINK defines to thunk spec
Current thunk spec v1.07 dated Feb 1, 2016

Change-Id: Ie1821f7f1903ac48b76cb68d452a6073d3a3c8d9
2016-03-11 18:59:57 -05:00
Harish Kasiviswanathan 2f015053b2 Sync IOLINK defines to thunk spec
Current thunk spec v1.07 dated Feb 1, 2016

Change-Id: Ie1821f7f1903ac48b76cb68d452a6073d3a3c8d9


[ROCm/ROCR-Runtime commit: 1c1bc32477]
2016-03-11 18:59:57 -05:00
Harish Kasiviswanathan 8ff2bcd48d Fix indirect io_links
Connect only (Peer-to-Peer) GPUs that belong to same NUMA node. Without
this additional check non direct GPUs would also get connected.

Change-Id: I9a5ed19b8f06cd0527854cbbdb51ede99eade28b
2016-03-11 18:54:32 -05:00
Harish Kasiviswanathan dbe8c8faba Fix indirect io_links
Connect only (Peer-to-Peer) GPUs that belong to same NUMA node. Without
this additional check non direct GPUs would also get connected.

Change-Id: I9a5ed19b8f06cd0527854cbbdb51ede99eade28b


[ROCm/ROCR-Runtime commit: 8ff2bcd48d]
2016-03-11 18:54:32 -05:00
Felix Kuehling cac0c08496 Fix lstopo
Lstopo doesn't have system memory mappings at low addresses. Make
sure we leave enough GPUVM address space for kernel allocations
(currently only CWSR) before the start of the user-managed SVM
aperture.

Change-Id: Ic197f7bd5a3cfb150a0da2bfdbc848664e7869be
2016-03-11 11:01:12 -05:00
Felix Kuehling 68f1b37518 Fix lstopo
Lstopo doesn't have system memory mappings at low addresses. Make
sure we leave enough GPUVM address space for kernel allocations
(currently only CWSR) before the start of the user-managed SVM
aperture.

Change-Id: Ic197f7bd5a3cfb150a0da2bfdbc848664e7869be


[ROCm/ROCR-Runtime commit: cac0c08496]
2016-03-11 11:01:12 -05:00
foreman dc64bc14ee P4 to Git Change 1246346 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/11 03:00:11
SWDEV-2 - Change OpenCL version number from 2059 to 2060.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1806 edit


[ROCm/clr commit: c7d5d06a84]
2016-03-11 03:07:50 -05:00
foreman c7d5d06a84 P4 to Git Change 1246346 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/11 03:00:11
SWDEV-2 - Change OpenCL version number from 2059 to 2060.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1806 edit
2016-03-11 03:07:50 -05:00
foreman 4c9bdf32a3 P4 to Git Change 1246105 by cpaquot@hog-ocl on 2016/03/10 15:13:37
SWDEV-89711 - Adding EGL interop capability:
	- Remove Context::Info::type_ and only use flags_, it's more accurate and type_ was just redundant
	- Plumbing work for EGL at the top of the API layer.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/9965/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl_amd.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.hpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#269 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#542 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#157 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#24 edit


[ROCm/clr commit: ca062c81b4]
2016-03-10 15:21:20 -05:00
foreman ca062c81b4 P4 to Git Change 1246105 by cpaquot@hog-ocl on 2016/03/10 15:13:37
SWDEV-89711 - Adding EGL interop capability:
	- Remove Context::Info::type_ and only use flags_, it's more accurate and type_ was just redundant
	- Plumbing work for EGL at the top of the API layer.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/9965/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl_amd.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.hpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#269 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#542 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#157 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#24 edit
2016-03-10 15:21:20 -05:00
foreman 42c2836e5a P4 to Git Change 1246105 by cpaquot@hog-ocl on 2016/03/10 15:13:37
SWDEV-89711 - Adding EGL interop capability:
	- Remove Context::Info::type_ and only use flags_, it's more accurate and type_ was just redundant
	- Plumbing work for EGL at the top of the API layer.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/9965/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl_amd.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.hpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#269 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#542 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#157 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#24 edit


[ROCm/clr commit: 269f599f85]
2016-03-10 15:21:20 -05:00
foreman 269f599f85 P4 to Git Change 1246105 by cpaquot@hog-ocl on 2016/03/10 15:13:37
SWDEV-89711 - Adding EGL interop capability:
	- Remove Context::Info::type_ and only use flags_, it's more accurate and type_ was just redundant
	- Plumbing work for EGL at the top of the API layer.

	ReviewBoardURL = http://ocltc.amd.com/reviews/r/9965/diff/

Affected files ...

... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d10.cpp#11 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d11.cpp#18 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_d3d9.cpp#28 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl.cpp#48 edit
... //depot/stg/opencl/drivers/opencl/api/opencl/amdocl/cl_gl_amd.hpp#18 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/cpu/cpudevice.hpp#94 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#269 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.cpp#542 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpudevice.hpp#157 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.cpp#56 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/hsa_foundation/hsadevice.hpp#25 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.cpp#40 edit
... //depot/stg/opencl/drivers/opencl/runtime/platform/context.hpp#24 edit
2016-03-10 15:21:20 -05:00
Harish Kasiviswanathan 7042292c60 Add indirect io_links
Connect (Peer-to-Peer) GPUs that belong to same NUMA node.
Connect all [GPU] <--> [Non Parent NUMA] node

Change-Id: Ib4b08a6545d28b7dce4c9b1a90378bfc51bed07e
2016-03-10 15:11:17 -05:00
Harish Kasiviswanathan 6409b00f8f Add indirect io_links
Connect (Peer-to-Peer) GPUs that belong to same NUMA node.
Connect all [GPU] <--> [Non Parent NUMA] node

Change-Id: Ib4b08a6545d28b7dce4c9b1a90378bfc51bed07e


[ROCm/ROCR-Runtime commit: 7042292c60]
2016-03-10 15:11:17 -05:00
Harish Kasiviswanathan 1e729510d2 Allocate memory for indirect io_links
To simplify, allocate maximum needed memory for node_t->link array.
No need for realloc when indirect links are added. Trade off - for some
nodes more memory than required will be allocated.

This means the loop to compute the number of direct (reverse) io_links
for a CPU node is not necessary.

Change-Id: I2b2559142cbec3b262d0b4ea5fdebfd8f36c28fc
2016-03-10 15:10:48 -05:00
Harish Kasiviswanathan 35e6692134 Allocate memory for indirect io_links
To simplify, allocate maximum needed memory for node_t->link array.
No need for realloc when indirect links are added. Trade off - for some
nodes more memory than required will be allocated.

This means the loop to compute the number of direct (reverse) io_links
for a CPU node is not necessary.

Change-Id: I2b2559142cbec3b262d0b4ea5fdebfd8f36c28fc


[ROCm/ROCR-Runtime commit: 1e729510d2]
2016-03-10 15:10:48 -05:00
Felix Kuehling 61ec3df2f9 Add support for hsaKmtRegisterGraphicsHandleToNodes
Change-Id: I6fd7154dea78188480d5cb89ac237bad572356c4
2016-03-10 11:16:02 -05:00
Felix Kuehling 029002d073 Add support for hsaKmtRegisterGraphicsHandleToNodes
Change-Id: I6fd7154dea78188480d5cb89ac237bad572356c4


[ROCm/ROCR-Runtime commit: 61ec3df2f9]
2016-03-10 11:16:02 -05:00
foreman 6d635edb3b P4 to Git Change 1245787 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/10 03:00:13
SWDEV-2 - Change OpenCL version number from 2058 to 2059.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1805 edit


[ROCm/clr commit: 3fe9bcaaff]
2016-03-10 03:08:48 -05:00
foreman 3fe9bcaaff P4 to Git Change 1245787 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/10 03:00:13
SWDEV-2 - Change OpenCL version number from 2058 to 2059.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1805 edit
2016-03-10 03:08:48 -05:00
Ben Goz b1393f8224 Support MapMemoryToGPUNodes on APU
Change-Id: Ie77a2eb23cd9fe6671ff9e0630977220218e55dd
Signed-off-by: Ben Goz <ben.goz@amd.com>
2016-03-09 21:31:52 -05:00
Ben Goz c32a504b59 Support MapMemoryToGPUNodes on APU
Change-Id: Ie77a2eb23cd9fe6671ff9e0630977220218e55dd
Signed-off-by: Ben Goz <ben.goz@amd.com>


[ROCm/ROCR-Runtime commit: b1393f8224]
2016-03-09 21:31:52 -05:00
Felix Kuehling cb0315d31d Update kfd_ioctl.h from kernel
Change-Id: I9852ef2e33e1f3b24343747e3c1c09b0050ffdc1
2016-03-09 10:55:12 -05:00
Felix Kuehling e2d2d6bd32 Update kfd_ioctl.h from kernel
Change-Id: I9852ef2e33e1f3b24343747e3c1c09b0050ffdc1


[ROCm/ROCR-Runtime commit: cb0315d31d]
2016-03-09 10:55:12 -05:00
Felix Kuehling b837c3e7b0 Clean up GPUVM aperture management
Non-canonical GPUVM aperture doesn't exist on dGPUs. Remove comments
and code that say otherwise.

Fix alignment of GPUVM aperture for gfx801. Requires the same workaround
as gfx802. It's not used for anything on gfx801 yet, but will be soon.

Change-Id: I88607fe7b340081cc0715b85f28fdbf5f1bb0ad7
2016-03-09 10:55:12 -05:00
Felix Kuehling f171fef754 Clean up GPUVM aperture management
Non-canonical GPUVM aperture doesn't exist on dGPUs. Remove comments
and code that say otherwise.

Fix alignment of GPUVM aperture for gfx801. Requires the same workaround
as gfx802. It's not used for anything on gfx801 yet, but will be soon.

Change-Id: I88607fe7b340081cc0715b85f28fdbf5f1bb0ad7


[ROCm/ROCR-Runtime commit: b837c3e7b0]
2016-03-09 10:55:12 -05:00
dfukalov 38d5bd4111 fixed bug with -debug switch
[ROCm/clr commit: f0c01ebd57]
2016-03-09 18:37:20 +03:00
dfukalov f0c01ebd57 fixed bug with -debug switch 2016-03-09 18:37:20 +03:00
dfukalov 88fdff7e55 fixed bug with -debug switch
[ROCm/hip commit: d30f103882]
2016-03-09 18:37:20 +03:00
dfukalov d30f103882 fixed bug with -debug switch 2016-03-09 18:37:20 +03:00
foreman 6175541596 P4 to Git Change 1245390 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/09 03:00:12
SWDEV-2 - Change OpenCL version number from 2057 to 2058.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1804 edit


[ROCm/clr commit: 0ed489ca5e]
2016-03-09 03:09:09 -05:00
foreman 0ed489ca5e P4 to Git Change 1245390 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/03/09 03:00:12
SWDEV-2 - Change OpenCL version number from 2057 to 2058.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1804 edit
2016-03-09 03:09:09 -05:00
foreman 8b95f29714 P4 to Git Change 1245012 by gandryey@gera-w8 on 2016/03/08 14:41:35
SWDEV-89511 - Enable F16 KHR extension

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#268 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#343 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#253 edit


[ROCm/clr commit: 08721493fa]
2016-03-08 14:51:18 -05:00
foreman 08721493fa P4 to Git Change 1245012 by gandryey@gera-w8 on 2016/03/08 14:41:35
SWDEV-89511 - Enable F16 KHR extension

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/device/device.hpp#268 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/gpu/gpusettings.cpp#343 edit
... //depot/stg/opencl/drivers/opencl/runtime/utils/flags.hpp#253 edit
2016-03-08 14:51:18 -05:00
Aditya Atluri 6162990f44 Added hipHostRegister for hip with tests and added copyright
[ROCm/clr commit: 3127969d97]
2016-03-08 12:57:22 -06:00