-
Notifications
You must be signed in to change notification settings - Fork 288
235B H20 configs #1132
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
235B H20 configs #1132
Changes from 1 commit
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,110 @@ | ||
| { | ||
| "1024": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "128": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "16384": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 16, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "2048": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "256": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "32768": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 16, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "512": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "64": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "65536": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 32, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "8": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "800": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "8192": { | ||
| "BLOCK_SIZE_K": 32, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 128, | ||
| "GROUP_SIZE_M": 16, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| } | ||
| } | ||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,110 @@ | ||
| { | ||
| "1": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "100": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "1024": { | ||
| "BLOCK_SIZE_K": 64, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 64, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "128": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "16": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 32, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "2048": { | ||
| "BLOCK_SIZE_K": 64, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 64, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "256": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 64, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "32": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "4096": { | ||
| "BLOCK_SIZE_K": 64, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 64, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| }, | ||
| "64": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 1, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "8": { | ||
| "BLOCK_SIZE_K": 128, | ||
| "BLOCK_SIZE_M": 16, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 32, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 3, | ||
| "num_warps": 4 | ||
| }, | ||
| "8192": { | ||
| "BLOCK_SIZE_K": 64, | ||
| "BLOCK_SIZE_M": 64, | ||
| "BLOCK_SIZE_N": 64, | ||
| "GROUP_SIZE_M": 64, | ||
| "NEED_TRANS": false, | ||
| "num_stages": 4, | ||
| "num_warps": 4 | ||
| } | ||
| } | ||
|
Comment on lines
+1
to
+110
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The keys in this JSON file are sorted alphabetically, which makes it hard to read as they represent numerical values. For better readability and maintainability, please sort the keys numerically. {
"1": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"NEED_TRANS": false,
"num_stages": 4,
"num_warps": 4
},
"8": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 32,
"NEED_TRANS": false,
"num_stages": 3,
"num_warps": 4
},
"16": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 32,
"GROUP_SIZE_M": 1,
"NEED_TRANS": false,
"num_stages": 3,
"num_warps": 4
},
"32": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"NEED_TRANS": false,
"num_stages": 4,
"num_warps": 4
},
"64": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"NEED_TRANS": false,
"num_stages": 3,
"num_warps": 4
},
"100": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"NEED_TRANS": false,
"num_stages": 3,
"num_warps": 4
},
"128": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 1,
"NEED_TRANS": false,
"num_stages": 3,
"num_warps": 4
},
"256": {
"BLOCK_SIZE_K": 128,
"BLOCK_SIZE_M": 16,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 64,
"NEED_TRANS": false,
"num_stages": 3,
"num_warps": 4
},
"1024": {
"BLOCK_SIZE_K": 64,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 64,
"NEED_TRANS": false,
"num_stages": 4,
"num_warps": 4
},
"2048": {
"BLOCK_SIZE_K": 64,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 64,
"NEED_TRANS": false,
"num_stages": 4,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE_K": 64,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 64,
"NEED_TRANS": false,
"num_stages": 4,
"num_warps": 4
},
"8192": {
"BLOCK_SIZE_K": 64,
"BLOCK_SIZE_M": 64,
"BLOCK_SIZE_N": 64,
"GROUP_SIZE_M": 64,
"NEED_TRANS": false,
"num_stages": 4,
"num_warps": 4
}
} |
||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,50 @@ | ||
| { | ||
| "1": { | ||
| "BLOCK_SIZE": 256, | ||
| "num_warps": 8 | ||
| }, | ||
| "100": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| }, | ||
| "1024": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| }, | ||
| "128": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| }, | ||
| "16": { | ||
| "BLOCK_SIZE": 256, | ||
| "num_warps": 8 | ||
| }, | ||
| "2048": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 4 | ||
| }, | ||
| "256": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| }, | ||
| "32": { | ||
| "BLOCK_SIZE": 512, | ||
| "num_warps": 8 | ||
| }, | ||
| "4096": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| }, | ||
| "64": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| }, | ||
| "8": { | ||
| "BLOCK_SIZE": 256, | ||
| "num_warps": 8 | ||
| }, | ||
| "8192": { | ||
| "BLOCK_SIZE": 128, | ||
| "num_warps": 8 | ||
| } | ||
| } | ||
|
Comment on lines
+1
to
+50
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The keys in this JSON file are sorted alphabetically, which makes it hard to read as they represent numerical values. For better readability and maintainability, please sort the keys numerically. {
"1": {
"BLOCK_SIZE": 256,
"num_warps": 8
},
"8": {
"BLOCK_SIZE": 256,
"num_warps": 8
},
"16": {
"BLOCK_SIZE": 256,
"num_warps": 8
},
"32": {
"BLOCK_SIZE": 512,
"num_warps": 8
},
"64": {
"BLOCK_SIZE": 128,
"num_warps": 8
},
"100": {
"BLOCK_SIZE": 128,
"num_warps": 8
},
"128": {
"BLOCK_SIZE": 128,
"num_warps": 8
},
"256": {
"BLOCK_SIZE": 128,
"num_warps": 8
},
"1024": {
"BLOCK_SIZE": 128,
"num_warps": 8
},
"2048": {
"BLOCK_SIZE": 128,
"num_warps": 4
},
"4096": {
"BLOCK_SIZE": 128,
"num_warps": 8
},
"8192": {
"BLOCK_SIZE": 128,
"num_warps": 8
}
} |
||
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,74 @@ | ||
| { | ||
| "1": { | ||
| "BLOCK_DIM": 64, | ||
| "BLOCK_M": 4, | ||
| "NUM_STAGE": 2, | ||
| "num_warps": 8 | ||
| }, | ||
| "100": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 8 | ||
| }, | ||
| "1024": { | ||
| "BLOCK_DIM": 256, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 2 | ||
| }, | ||
| "128": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 8 | ||
| }, | ||
| "16": { | ||
| "BLOCK_DIM": 512, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 8 | ||
| }, | ||
| "2048": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 4, | ||
| "num_warps": 2 | ||
| }, | ||
| "256": { | ||
| "BLOCK_DIM": 512, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 2 | ||
| }, | ||
| "32": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 8 | ||
| }, | ||
| "4096": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 4, | ||
| "num_warps": 2 | ||
| }, | ||
| "64": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 1, | ||
| "num_warps": 8 | ||
| }, | ||
| "8": { | ||
| "BLOCK_DIM": 512, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 4, | ||
| "num_warps": 16 | ||
| }, | ||
| "8192": { | ||
| "BLOCK_DIM": 1024, | ||
| "BLOCK_M": 1, | ||
| "NUM_STAGE": 4, | ||
| "num_warps": 1 | ||
| } | ||
| } | ||
|
Comment on lines
+1
to
+74
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. The keys in this JSON file are sorted alphabetically, which makes it hard to read as they represent numerical values. For better readability and maintainability, please sort the keys numerically. {
"1": {
"BLOCK_DIM": 64,
"BLOCK_M": 4,
"NUM_STAGE": 2,
"num_warps": 8
},
"8": {
"BLOCK_DIM": 512,
"BLOCK_M": 1,
"NUM_STAGE": 4,
"num_warps": 16
},
"16": {
"BLOCK_DIM": 512,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 8
},
"32": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 8
},
"64": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 8
},
"100": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 8
},
"128": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 8
},
"256": {
"BLOCK_DIM": 512,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 2
},
"1024": {
"BLOCK_DIM": 256,
"BLOCK_M": 1,
"NUM_STAGE": 1,
"num_warps": 2
},
"2048": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 4,
"num_warps": 2
},
"4096": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 4,
"num_warps": 2
},
"8192": {
"BLOCK_DIM": 1024,
"BLOCK_M": 1,
"NUM_STAGE": 4,
"num_warps": 1
}
} |
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The keys in this JSON file are sorted alphabetically, which makes it hard to read as they represent numerical values. For better readability and maintainability, please sort the keys numerically.
{ "8": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 3, "num_warps": 4 }, "64": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 3, "num_warps": 4 }, "128": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 4, "num_warps": 4 }, "256": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 4, "num_warps": 4 }, "512": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 4, "num_warps": 4 }, "800": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 4, "num_warps": 4 }, "1024": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 4, "num_warps": 4 }, "2048": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 16, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 1, "NEED_TRANS": false, "num_stages": 4, "num_warps": 4 }, "8192": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 16, "NEED_TRANS": false, "num_stages": 3, "num_warps": 4 }, "16384": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 16, "NEED_TRANS": false, "num_stages": 3, "num_warps": 4 }, "32768": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 16, "NEED_TRANS": false, "num_stages": 3, "num_warps": 4 }, "65536": { "BLOCK_SIZE_K": 32, "BLOCK_SIZE_M": 64, "BLOCK_SIZE_N": 128, "GROUP_SIZE_M": 32, "NEED_TRANS": false, "num_stages": 3, "num_warps": 4 } }