kmx git

Commit	Date	Message
4fbe5bed	2012-08-23T23:25:32	OpenCL 1.0 does not have native atomic_add and extremely slow support with atom_add so detect opencl1.0 and use a non-atomic workaround.
482322a4	2012-08-23T12:47:28	Pick worksize 256 with Cypress if none is specified.
be06cf70	2012-08-23T12:44:42	Give warning with sdk2.7 and phatk as well.
cce19d90	2012-08-23T12:42:10	Whitelist sdk2.7 for diablo kernel as well.
fc44b6d7	2012-08-05T15:32:44	Use different variables for command line specified lookup gap and thread concurrency to differentiate user defined versus auto chosen values.
97aa6ea4	2012-07-29T19:13:45	Fix build error without scrypt enabled.
43752ee5	2012-07-26T16:12:45	Limit thread concurrency for scrypt to 5xshaders if shaders is specified.
da1b996a	2012-07-26T16:10:21	Simplify repeated use of gpus[gpu]. in ocl.c
ea10b08d	2012-07-25T22:02:14	Find the nearest power of 2 maximum alloc size for the scrypt buffer that can successfully be allocated and is large enough to accomodate the thread concurrency chosen, thus mapping it to an intensity.
9a6c082a	2012-07-24T20:27:37	Make the thread concurrency and lookup gap options hidden on the command line and autotune parameters with a newly parsed --shaders option.
3a0d60cf	2012-07-23T21:30:30	Always create the largest possible padbuffer for scrypt kernels even if not needed for thread_concurrency, giving us some headroom for intensity levels.
d8f81c18	2012-07-23T17:51:57	Use the detected maximum allocable memory on a GPU to determine the optimal scrypt settings when lookup_gap and thread_concurrency parameters are not given.
89eb1fa3	2012-07-23T17:41:31	Check the maximum allocable memory size per opencl device.
5087ff90	2012-07-23T16:37:13	Add debugging output if buffer allocation fails for scrypt and round up bufsize to a multiple of 256.
1711b4eb	2012-07-22T00:58:09	Display size of scrypt buffer used in debug.
39f7d2fa	2012-07-21T17:31:06	Allow lookup gap and thread concurrency to be passed per device and store details in kernel binary filename.
7d53fba1	2012-07-21T02:49:50	Reinstate GPU only opencl device detection.
d13a3f1d	2012-07-21T02:47:27	Decrease lookup gap to 1. Does not seem to help in any way being 2.
d72add9a	2012-07-20T16:16:18	Send correct values to scrypt kernel to get it finally working.
3e61db10	2012-07-18T21:58:27	Create command queue before compiling program in opencl.
471daecb	2012-07-16T17:05:08	Initialise mdplatform.
07292f73	2012-07-16T17:05:08	Initialise mdplatform.
ffd21f8d	2012-07-15T13:40:11	Find the gpu platform with the most devices and use that if no platform option is passed.
f99ac0ca	2012-07-15T13:31:03	Allow more platforms to be probed if first does not return GPUs.
428d5e5d	2012-07-16T13:22:35	Limit scrypt to 1 vector.
a9a0bba1	2012-07-16T11:53:18	Set the correct data for cldata and prepare for pad8 fixes.
04edf4bf	2012-07-15T13:40:56	Temporarily set opencl to use all devices to allow debugging of scrypt kernel rapidly.
53e9c61c	2012-07-15T13:40:11	Find the gpu platform with the most devices and use that if no platform option is passed.
884f83f3	2012-07-15T13:31:03	Allow more platforms to be probed if first does not return GPUs.
243d005b	2012-07-14T16:21:27	Set scrypt settings and buffer size in ocl.c code to be future modifiable.
aabc7233	2012-07-14T00:30:25	Make sure goffset is set for scrypt and drop padbuffer8 to something manageable for now.
e0296c41	2012-07-13T21:35:25	Set up buffer8 for scrypt.
0f43eb5e	2012-07-13T20:35:44	Don't test nonce with sha and various fixes for scrypt.
b085c338	2012-07-13T20:28:36	Make scrypt buffers and midstate compatible with cgminer.
dd740caa	2012-07-13T19:02:43	Provide initial support for the scrypt kernel to compile with and mine scrypt with the --scrypt option.
f479be07	2012-04-27T08:29:56	add goffset support for diakgcn with -v 1 and update kernel version
9a3ae266	2012-04-27T10:22:53	Add support for latest ATI SDK on windows.
bb319883	2012-04-25T11:41:35	Detect poorly performing combination of SDK and phatk kernel and add verbose warning at startup.
9175e4f2	2012-04-23T17:56:31	Display all OpenCL devices when -n is called as well to allow debugging of differential mapping of OpenCL to ADL.
6274fbe7	2012-03-30T09:32:42	Change the preferred vector width to 1 for Tahiti only, not all poclbm kernels.
621bcca7	2012-03-27T22:10:17	Use global offset parameter to diablo and poclbm kernel ONLY for 1 vector kernels.
39395eb1	2012-03-27T19:58:51	Use poclbm preferentially on Tahiti now regardless of SDK.
edb070c8	2012-02-24T13:31:29	Fixes.
fb077c6d	2012-02-24T13:27:15	Pass vectors * worksize to kernel to avoid one op.
709c4cd8	2012-02-23T20:24:32	Use diablo kernel on all future SDKs for Tahiti and set preferred vector width to 1 on poclbm kernel only.
dfcb98de	2012-02-23T00:45:40	Use the SDK and hardware information to choose good performing default kernels.
d3ad87f5	2012-02-22T20:13:23	Allow writing of multiple worksizes to the configuration file.
1b1fa5cd	2012-02-22T20:08:29	Allow writing of multiple vector sizes to the configuration file.
994cd775	2012-02-22T20:01:09	Allow writing of multiple kernels to the configuration file.
93efb726	2012-02-22T19:38:01	Allow multiple different kernels to be chosen per device.
a54f7606	2012-02-22T19:00:44	Fix multiple work size entry.
26c59fbf	2012-02-22T16:59:28	Allow the worksize to be set per-device.
deff55c6	2012-02-22T16:54:06	Allow different vectors to be set per device.
bf3a9f94	2012-02-22T14:42:20	Unintentionally dropped the device name from the binary filenames. Reinstate.
5d23d70f	2012-02-22T14:14:26	As all kernels will be new versions it's an opportunity to change the .bin format and make it simpler. Specifying bitalign is redundant and long can be l.
d1cddf8b	2012-02-21T22:23:07	Update licensing to GPL V3.
00290a3e	2012-02-21T21:31:31	Select diablo kernel on all but GCN+SDK 2.6.
e9c3d730	2012-02-19T18:32:56	Tahiti prefers worksize 64 with poclbm.
30936f17	2012-02-18T23:28:41	No need to expressly retain the opencl program now that the zero binary issue is fixed.
810ad045	2012-02-18T23:16:08	More copyright updates.
22d3034e	2012-02-18T23:13:45	Show error code on any opencl failure status.
be9db9ce	2012-02-18T23:00:21	Copyright updates.
0b6e35cd	2012-02-18T22:49:49	Add detection for version 898.1 SDK as well but only give SDK 2.6 warning once on startup instead of with each device initialisation.
67c4ada1	2012-02-16T01:10:11	Provide warning on each startup about sdk 2.6 and decrease poclbm kernel selection to LOG_INFO.
b4c86ba6	2012-02-16T00:48:34	Give SDK 2.6 warning only on building a kernel for !GCN bitalign devices.
728e3d43	2012-02-16T00:43:05	Revert "Automatically choose phatk kernel for bitalign non-gcn ATI cards, and then only select poclbm if SDK2.6 is detected." This reverts commit e7fdadfc8fc388f68772d5a4c2740da60287c889. Broke kernel loading.
e7fdadfc	2012-02-15T14:52:29	Automatically choose phatk kernel for bitalign non-gcn ATI cards, and then only select poclbm if SDK2.6 is detected.
6a785946	2012-02-15T14:47:02	Make SDK 2.6 warning and advice big and bold.
23c01bc7	2012-02-13T13:19:04	Make output buffer write only as per Diapolo's suggestion.
b2b5083b	2012-02-13T12:22:35	Microoptimise phatk kernel on return code.
fd05341a	2012-02-13T10:39:26	Do not loop indefinitely setting poclbm kernel to load a binary.
d689cfbd	2012-02-13T10:06:26	Try to load a binary if we've defaulted to the poclbm kernel on SDK2.6
3057b701	2012-02-13T09:59:29	Use the poclbm kernel on SDK2.6 with bitalign devices only if there is no binary available.
2c33f122	2012-02-13T08:34:44	Whitelist ATI SDK 2.6 to use the poclbm kernel by default.
fb99c8d5	2012-02-12T21:38:45	The longstanding generation of a zero sized binary appears to be due to the OpenCL library putting the binary in a RANDOM SLOT amongst 4 possible binary locations. Iterate over each of them after building from source till the real binary is found and use that.
56907db2	2012-02-12T18:21:30	Fix harmless warnings with -Wsign-compare to allow cgminer to build with -W.
405a2120	2012-02-11T20:11:18	Remove unnecessary check for opt_debug on every invocation of applog at LOG_DEBUG and place the check in applog().
60c70145	2012-02-11T16:41:41	Retain cl program after successfully loading a binary image.
55bd031d	2012-02-11T16:38:55	Variable unused after this so remove setting it.
1c1b8bec	2012-02-11T15:58:07	BFI INT patching is not necessarily true on binary loading of files and not true on ATI SDK2.6+. Report bitalign instead.
f2d5db0c	2012-02-10T16:45:35	Use only working kernels by default.
59d3d011	2012-02-10T14:33:40	Implement diablo kernel support and try to make it work.
95a989da	2012-02-10T13:18:16	Conflicting entries of cl_kernel may have been causing problems, and automatically chosen kernel type was not being passed on. Rename the enum to cl_kernels and store the chosen kernel in each clState.
e6cf96ad	2012-02-10T10:28:45	ALlow much longer filenames for kernels to load properly.
cb7145b1	2012-02-08T13:45:56	Add basic build ability with diakgcn and put all kernel names in configure.ac to avoid changing them in mutliple places.
4822cca7	2012-02-10T10:23:06	Allow different kernels to be used by different devices and fix the logic fail of overcorrecting on last commit with !strstr.
196e8a0f	2012-02-10T09:10:57	Fix kernel selection process and build error.
47a09cea	2012-02-09T15:15:03	added OpenCL >= 1.1 detection code, in preparation of OpenCL 1.1 global offset parameter support
6776b0ea	2012-02-10T16:45:35	Use only working kernels by default.
2270b4e0	2012-02-10T14:33:40	Implement diablo kernel support and try to make it work.
02c94272	2012-02-10T13:18:16	Conflicting entries of cl_kernel may have been causing problems, and automatically chosen kernel type was not being passed on. Rename the enum to cl_kernels and store the chosen kernel in each clState.
35ea31b1	2012-02-10T10:28:45	ALlow much longer filenames for kernels to load properly.
8af2365e	2012-02-10T10:23:06	Allow different kernels to be used by different devices and fix the logic fail of overcorrecting on last commit with !strstr.
2b23805e	2012-02-10T09:10:57	Fix kernel selection process and build error.
ed7210af	2012-02-09T15:15:03	added OpenCL >= 1.1 detection code, in preparation of OpenCL 1.1 global offset parameter support
a6c6866a	2012-02-08T13:45:56	Add basic build ability with diakgcn and put all kernel names in configure.ac to avoid changing them in mutliple places.
53c1e9ae	2012-02-04T15:15:57	Allow the OpenCL platform ID to be chosen with --gpu-platform.
a4f47812	2012-02-04T14:47:23	Iterate over all platforms displaying their information and number of devices when --ndevs is called.
ebaa2be1	2012-02-03T18:19:39	Update poclbm kernel for better performance on GCN and new SDKs with bitalign support when not BFI INT patching. Update phatk kernel to work properly for non BFI INT patched kernels, providing support for phatk to run on GCN and non-ATI cards.
82af288e	2012-01-29T22:57:29	Revert "Fix various harmless warnings." This reverts commit a4b67f030fc0c7e2b18e79114a441c1e1617d5f8.

4fbe5bed

2012-08-23T23:25:32

OpenCL 1.0 does not have native atomic_add and extremely slow support with atom_add so detect opencl1.0 and use a non-atomic workaround.

482322a4

2012-08-23T12:47:28

Pick worksize 256 with Cypress if none is specified.

be06cf70

2012-08-23T12:44:42

Give warning with sdk2.7 and phatk as well.

cce19d90

2012-08-23T12:42:10

Whitelist sdk2.7 for diablo kernel as well.

fc44b6d7

2012-08-05T15:32:44

Use different variables for command line specified lookup gap and thread concurrency to differentiate user defined versus auto chosen values.

97aa6ea4

2012-07-29T19:13:45

Fix build error without scrypt enabled.

43752ee5

2012-07-26T16:12:45

Limit thread concurrency for scrypt to 5xshaders if shaders is specified.

da1b996a

2012-07-26T16:10:21

Simplify repeated use of gpus[gpu]. in ocl.c

ea10b08d

2012-07-25T22:02:14

Find the nearest power of 2 maximum alloc size for the scrypt buffer that can successfully be allocated and is large enough to accomodate the thread concurrency chosen, thus mapping it to an intensity.

9a6c082a

2012-07-24T20:27:37

Make the thread concurrency and lookup gap options hidden on the command line and autotune parameters with a newly parsed --shaders option.

3a0d60cf

2012-07-23T21:30:30

Always create the largest possible padbuffer for scrypt kernels even if not needed for thread_concurrency, giving us some headroom for intensity levels.

d8f81c18

2012-07-23T17:51:57

Use the detected maximum allocable memory on a GPU to determine the optimal scrypt settings when lookup_gap and thread_concurrency parameters are not given.

89eb1fa3

2012-07-23T17:41:31

Check the maximum allocable memory size per opencl device.

5087ff90

2012-07-23T16:37:13

Add debugging output if buffer allocation fails for scrypt and round up bufsize to a multiple of 256.

1711b4eb

2012-07-22T00:58:09

Display size of scrypt buffer used in debug.

39f7d2fa

2012-07-21T17:31:06

Allow lookup gap and thread concurrency to be passed per device and store details in kernel binary filename.

7d53fba1

2012-07-21T02:49:50

Reinstate GPU only opencl device detection.

d13a3f1d

2012-07-21T02:47:27

Decrease lookup gap to 1. Does not seem to help in any way being 2.

d72add9a

2012-07-20T16:16:18

Send correct values to scrypt kernel to get it finally working.

3e61db10

2012-07-18T21:58:27

Create command queue before compiling program in opencl.

471daecb

2012-07-16T17:05:08

Initialise mdplatform.

07292f73

2012-07-16T17:05:08

Initialise mdplatform.

ffd21f8d

2012-07-15T13:40:11

Find the gpu platform with the most devices and use that if no platform option is passed.

f99ac0ca

2012-07-15T13:31:03

Allow more platforms to be probed if first does not return GPUs.

428d5e5d

2012-07-16T13:22:35

Limit scrypt to 1 vector.

a9a0bba1

2012-07-16T11:53:18

Set the correct data for cldata and prepare for pad8 fixes.

04edf4bf

2012-07-15T13:40:56

Temporarily set opencl to use all devices to allow debugging of scrypt kernel rapidly.

53e9c61c

2012-07-15T13:40:11

Find the gpu platform with the most devices and use that if no platform option is passed.

884f83f3

2012-07-15T13:31:03

Allow more platforms to be probed if first does not return GPUs.

243d005b

2012-07-14T16:21:27

Set scrypt settings and buffer size in ocl.c code to be future modifiable.

aabc7233

2012-07-14T00:30:25

Make sure goffset is set for scrypt and drop padbuffer8 to something manageable for now.

e0296c41

2012-07-13T21:35:25

Set up buffer8 for scrypt.

0f43eb5e

2012-07-13T20:35:44

Don't test nonce with sha and various fixes for scrypt.

b085c338

2012-07-13T20:28:36

Make scrypt buffers and midstate compatible with cgminer.

dd740caa

2012-07-13T19:02:43

Provide initial support for the scrypt kernel to compile with and mine scrypt with the --scrypt option.

f479be07

2012-04-27T08:29:56

add goffset support for diakgcn with -v 1 and update kernel version

9a3ae266

2012-04-27T10:22:53

Add support for latest ATI SDK on windows.

bb319883

2012-04-25T11:41:35

Detect poorly performing combination of SDK and phatk kernel and add verbose warning at startup.

9175e4f2

2012-04-23T17:56:31

Display all OpenCL devices when -n is called as well to allow debugging of differential mapping of OpenCL to ADL.

6274fbe7

2012-03-30T09:32:42

Change the preferred vector width to 1 for Tahiti only, not all poclbm kernels.

621bcca7

2012-03-27T22:10:17

Use global offset parameter to diablo and poclbm kernel ONLY for 1 vector kernels.

39395eb1

2012-03-27T19:58:51

Use poclbm preferentially on Tahiti now regardless of SDK.

edb070c8

2012-02-24T13:31:29

Fixes.

fb077c6d

2012-02-24T13:27:15

Pass vectors * worksize to kernel to avoid one op.

709c4cd8

2012-02-23T20:24:32

Use diablo kernel on all future SDKs for Tahiti and set preferred vector width to 1 on poclbm kernel only.

dfcb98de

2012-02-23T00:45:40

Use the SDK and hardware information to choose good performing default kernels.

d3ad87f5

2012-02-22T20:13:23

Allow writing of multiple worksizes to the configuration file.

1b1fa5cd

2012-02-22T20:08:29

Allow writing of multiple vector sizes to the configuration file.

994cd775

2012-02-22T20:01:09

Allow writing of multiple kernels to the configuration file.

93efb726

2012-02-22T19:38:01

Allow multiple different kernels to be chosen per device.

a54f7606

2012-02-22T19:00:44

Fix multiple work size entry.

26c59fbf

2012-02-22T16:59:28

Allow the worksize to be set per-device.

deff55c6

2012-02-22T16:54:06

Allow different vectors to be set per device.

bf3a9f94

2012-02-22T14:42:20

Unintentionally dropped the device name from the binary filenames. Reinstate.

5d23d70f

2012-02-22T14:14:26

As all kernels will be new versions it's an opportunity to change the .bin format and make it simpler. Specifying bitalign is redundant and long can be l.

d1cddf8b

2012-02-21T22:23:07

Update licensing to GPL V3.

00290a3e

2012-02-21T21:31:31

Select diablo kernel on all but GCN+SDK 2.6.

e9c3d730

2012-02-19T18:32:56

Tahiti prefers worksize 64 with poclbm.

30936f17

2012-02-18T23:28:41

No need to expressly retain the opencl program now that the zero binary issue is fixed.

810ad045

2012-02-18T23:16:08

More copyright updates.

22d3034e

2012-02-18T23:13:45

Show error code on any opencl failure status.

be9db9ce

2012-02-18T23:00:21

Copyright updates.

0b6e35cd

2012-02-18T22:49:49

Add detection for version 898.1 SDK as well but only give SDK 2.6 warning once on startup instead of with each device initialisation.

67c4ada1

2012-02-16T01:10:11

Provide warning on each startup about sdk 2.6 and decrease poclbm kernel selection to LOG_INFO.

b4c86ba6

2012-02-16T00:48:34

Give SDK 2.6 warning only on building a kernel for !GCN bitalign devices.

728e3d43

2012-02-16T00:43:05

Revert "Automatically choose phatk kernel for bitalign non-gcn ATI cards, and then only select poclbm if SDK2.6 is detected." This reverts commit e7fdadfc8fc388f68772d5a4c2740da60287c889. Broke kernel loading.

e7fdadfc

2012-02-15T14:52:29

Automatically choose phatk kernel for bitalign non-gcn ATI cards, and then only select poclbm if SDK2.6 is detected.

6a785946

2012-02-15T14:47:02

Make SDK 2.6 warning and advice big and bold.

23c01bc7

2012-02-13T13:19:04

Make output buffer write only as per Diapolo's suggestion.

b2b5083b

2012-02-13T12:22:35

Microoptimise phatk kernel on return code.

fd05341a

2012-02-13T10:39:26

Do not loop indefinitely setting poclbm kernel to load a binary.

d689cfbd

2012-02-13T10:06:26

Try to load a binary if we've defaulted to the poclbm kernel on SDK2.6

3057b701

2012-02-13T09:59:29

Use the poclbm kernel on SDK2.6 with bitalign devices only if there is no binary available.

2c33f122

2012-02-13T08:34:44

Whitelist ATI SDK 2.6 to use the poclbm kernel by default.

fb99c8d5

2012-02-12T21:38:45

The longstanding generation of a zero sized binary appears to be due to the OpenCL library putting the binary in a RANDOM SLOT amongst 4 possible binary locations. Iterate over each of them after building from source till the real binary is found and use that.

56907db2

2012-02-12T18:21:30

Fix harmless warnings with -Wsign-compare to allow cgminer to build with -W.

405a2120

2012-02-11T20:11:18

Remove unnecessary check for opt_debug on every invocation of applog at LOG_DEBUG and place the check in applog().

60c70145

2012-02-11T16:41:41

Retain cl program after successfully loading a binary image.

55bd031d

2012-02-11T16:38:55

Variable unused after this so remove setting it.

1c1b8bec

2012-02-11T15:58:07

BFI INT patching is not necessarily true on binary loading of files and not true on ATI SDK2.6+. Report bitalign instead.

f2d5db0c

2012-02-10T16:45:35

Use only working kernels by default.

59d3d011

2012-02-10T14:33:40

Implement diablo kernel support and try to make it work.

95a989da

2012-02-10T13:18:16

Conflicting entries of cl_kernel may have been causing problems, and automatically chosen kernel type was not being passed on. Rename the enum to cl_kernels and store the chosen kernel in each clState.

e6cf96ad

2012-02-10T10:28:45

ALlow much longer filenames for kernels to load properly.

cb7145b1

2012-02-08T13:45:56

Add basic build ability with diakgcn and put all kernel names in configure.ac to avoid changing them in mutliple places.

4822cca7

2012-02-10T10:23:06

Allow different kernels to be used by different devices and fix the logic fail of overcorrecting on last commit with !strstr.

196e8a0f

2012-02-10T09:10:57

Fix kernel selection process and build error.

47a09cea

2012-02-09T15:15:03

added OpenCL >= 1.1 detection code, in preparation of OpenCL 1.1 global offset parameter support

6776b0ea

2012-02-10T16:45:35

Use only working kernels by default.

2270b4e0

2012-02-10T14:33:40

Implement diablo kernel support and try to make it work.

02c94272

2012-02-10T13:18:16

Conflicting entries of cl_kernel may have been causing problems, and automatically chosen kernel type was not being passed on. Rename the enum to cl_kernels and store the chosen kernel in each clState.

35ea31b1

2012-02-10T10:28:45

ALlow much longer filenames for kernels to load properly.

8af2365e

2012-02-10T10:23:06

Allow different kernels to be used by different devices and fix the logic fail of overcorrecting on last commit with !strstr.

2b23805e

2012-02-10T09:10:57

Fix kernel selection process and build error.

ed7210af

2012-02-09T15:15:03

added OpenCL >= 1.1 detection code, in preparation of OpenCL 1.1 global offset parameter support

a6c6866a

2012-02-08T13:45:56

Add basic build ability with diakgcn and put all kernel names in configure.ac to avoid changing them in mutliple places.

53c1e9ae

2012-02-04T15:15:57

Allow the OpenCL platform ID to be chosen with --gpu-platform.

a4f47812

2012-02-04T14:47:23

Iterate over all platforms displaying their information and number of devices when --ndevs is called.

ebaa2be1

2012-02-03T18:19:39

Update poclbm kernel for better performance on GCN and new SDKs with bitalign support when not BFI INT patching. Update phatk kernel to work properly for non BFI INT patched kernels, providing support for phatk to run on GCN and non-ATI cards.

82af288e

2012-01-29T22:57:29

Revert "Fix various harmless warnings." This reverts commit a4b67f030fc0c7e2b18e79114a441c1e1617d5f8.

thodg/cgminer/ocl.c

ocl.c

Log