Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / rocm/hipblaslt issues and pull requests

#1366 - Skip the very first cold iteration from gpu time measurement

Pull Request - State: closed - Opened by TomokoKurotobi 3 months ago - 2 comments

#1365 - Library Logic Format Simplification

Pull Request - State: open - Opened by b-shi 3 months ago - 6 comments

#1365 - Library Logic Format Simplification

Pull Request - State: open - Opened by b-shi 3 months ago - 6 comments

#1364 - Add setOccupancyLimit

Pull Request - State: closed - Opened by KKyang 3 months ago - 2 comments

#1364 - Add setOccupancyLimit

Pull Request - State: closed - Opened by KKyang 3 months ago - 2 comments

#1363 - Bump rocm-docs-core from 1.8.3 to 1.8.5 in /docs/sphinx

Pull Request - State: open - Opened by dependabot[bot] 3 months ago
Labels: documentation, dependencies, ci:docs-only

#1363 - Bump rocm-docs-core from 1.8.3 to 1.8.5 in /docs/sphinx

Pull Request - State: open - Opened by dependabot[bot] 3 months ago
Labels: documentation, dependencies, ci:docs-only

#1362 - gridbased search for batched gemm

Pull Request - State: closed - Opened by aazz44ss 3 months ago - 1 comment

#1362 - gridbased search for batched gemm

Pull Request - State: closed - Opened by aazz44ss 3 months ago - 1 comment

#1361 - Remove alias for MirrorDims in logic yaml

Pull Request - State: closed - Opened by alex391a 3 months ago

#1360 - F32 MAC Bug Fix for gfx11/12

Pull Request - State: closed - Opened by wenchuanchen 3 months ago - 2 comments

#1360 - Fix F32 FMAC Perf Bugs for gfx11/12

Pull Request - State: open - Opened by wenchuanchen 3 months ago

#1359 - Fix invalid stream-k test case, make dynamic grid the default

Pull Request - State: closed - Opened by AlexBrownAMD 3 months ago - 4 comments

#1359 - Fix invalid stream-k test case, make dynamic grid the default

Pull Request - State: closed - Opened by AlexBrownAMD 3 months ago - 4 comments

#1358 - Refactoy the pack scheduling for scheduleIterAlg = 3.

Pull Request - State: open - Opened by vin-huang 3 months ago
Labels: gfx94x

#1358 - Refactoy the pack scheduling for scheduleIterAlg = 3.

Pull Request - State: open - Opened by vin-huang 3 months ago
Labels: gfx94x

#1357 - Bump rocm-docs-core from 1.8.3 to 1.8.4 in /docs/sphinx

Pull Request - State: closed - Opened by dependabot[bot] 3 months ago - 1 comment
Labels: documentation, dependencies, ci:docs-only

#1356 - Modify to check if alpha is in host memory.

Pull Request - State: closed - Opened by geotseng-amd 3 months ago - 1 comment

#1355 - Remove Min/Max/TotalVgprNumber in Common.py

Pull Request - State: closed - Opened by KKyang 3 months ago - 2 comments

#1355 - Remove Min/Max/TotalVgprNumber in Common.py

Pull Request - State: closed - Opened by KKyang 3 months ago - 2 comments

#1354 - Regression Tree for ranking solutions

Pull Request - State: closed - Opened by yenong-amd 3 months ago

#1354 - Regression Tree for ranking solutions

Pull Request - State: open - Opened by yenong-amd 3 months ago

#1353 - [OPT] Optimize tail loop

Pull Request - State: closed - Opened by briannwu 3 months ago - 6 comments
Labels: gfx94x

#1353 - [OPT] Optimize tail loop

Pull Request - State: closed - Opened by briannwu 3 months ago - 6 comments
Labels: gfx94x

#1352 - [BB] fix build break with ROCM build# < 14361

Pull Request - State: closed - Opened by cmingch 3 months ago

#1352 - [BB] fix build break with ROCM build# < 14361

Pull Request - State: closed - Opened by cmingch 3 months ago

#1351 - Update gfx942 BBS/S NT/TN/TT GridBased yamls for 1105 MRS Training

Pull Request - State: closed - Opened by AndySu12 3 months ago - 1 comment
Labels: gfx94x

#1351 - Update gfx942 BBS/S NT/TN/TT GridBased yamls for 1105 MRS Training

Pull Request - State: closed - Opened by AndySu12 3 months ago - 1 comment
Labels: gfx94x

#1350 - Fix CI errors: no DeviceMaxFreq in GroupedGemm test

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1350 - Fix CI errors: no DeviceMaxFreq in GroupedGemm test

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1349 - Add sgpr occupancy

Pull Request - State: closed - Opened by KKyang 3 months ago

#1349 - Add sgpr occupancy

Pull Request - State: closed - Opened by KKyang 3 months ago

#1348 - Revert "Use stream-k dynamic grid size model by default"

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1348 - Revert "Use stream-k dynamic grid size model by default"

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1347 - Add initial optional stream-k libraries

Pull Request - State: closed - Opened by AlexBrownAMD 3 months ago - 2 comments

#1347 - Add initial optional stream-k libraries

Pull Request - State: closed - Opened by AlexBrownAMD 3 months ago - 2 comments

#1346 - Change syntax of Union for earlier python versions

Pull Request - State: closed - Opened by daineAMD 3 months ago - 1 comment

#1346 - Change syntax of Union for earlier python versions

Pull Request - State: closed - Opened by daineAMD 3 months ago - 1 comment

#1345 - gfx942 38cu F8BS NN TN NT grid tune

Pull Request - State: closed - Opened by m-kim 3 months ago - 1 comment

#1344 - Set Python_ROOT virtual.env

Pull Request - State: closed - Opened by ellosel 3 months ago

#1342 - update lib version as 0.12

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1342 - update lib version as 0.12

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1341 - Fix dependency check in unrolled loop with numItersPLR == 0

Pull Request - State: closed - Opened by Serge45 3 months ago - 1 comment
Labels: gfx94x

#1340 - Remove out-of-date descriptions

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1338 - Added multiple devices support for matrix transform

Pull Request - State: closed - Opened by Serge45 3 months ago - 2 comments
Labels: gfx94x

#1338 - Added multiple devices support for matrix transform

Pull Request - State: closed - Opened by Serge45 3 months ago - 2 comments
Labels: gfx94x

#1337 - Fix cpuThreads == 0 not working properly

Pull Request - State: open - Opened by KKyang 3 months ago

#1337 - Fix cpuThreads == 0 not working properly

Pull Request - State: closed - Opened by KKyang 3 months ago

#1336 - adding bpl64 support to addLdsLoad (for Bias and scaleAlphaVector)

Pull Request - State: closed - Opened by smalekta 3 months ago - 2 comments

#1336 - adding bpl64 support to addLdsLoad (for Bias and scaleAlphaVector)

Pull Request - State: closed - Opened by smalekta 3 months ago - 2 comments

#1335 - use correct data type 'rocblaslt_pointer_mode' for pointer mode

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1335 - use correct data type 'rocblaslt_pointer_mode' for pointer mode

Pull Request - State: closed - Opened by jichangjichang 3 months ago - 1 comment

#1333 - Fix F8/BF8 failed cases for GWVW=8 and Beta != 0

Pull Request - State: closed - Opened by geotseng-amd 3 months ago - 1 comment

#1331 - gfx942 38cu HHS BBS NN TN NT grid tune

Pull Request - State: closed - Opened by m-kim 3 months ago - 1 comment

#1329 - Add profiling to TensileCreateLibrary

Pull Request - State: closed - Opened by bstefanuk 3 months ago

#1329 - Add profiling to TensileCreateLibrary

Pull Request - State: closed - Opened by bstefanuk 3 months ago

#1328 - Add --experimental flag to TensileCreateLibrary

Pull Request - State: open - Opened by bstefanuk 3 months ago - 2 comments

#1328 - Add --experimental flag to TensileCreateLibrary

Pull Request - State: open - Opened by bstefanuk 3 months ago - 2 comments

#1327 - Add device IDs to gfx942 logic files

Pull Request - State: open - Opened by bstefanuk 3 months ago
Labels: gfx94x

#1327 - Add device IDs to gfx942 logic files

Pull Request - State: open - Opened by bstefanuk 3 months ago
Labels: gfx94x

#1326 - Modify to check if alpha is in host memory.

Pull Request - State: closed - Opened by geotseng-amd 3 months ago - 2 comments

#1326 - Modify to check if alpha is in host memory.

Pull Request - State: closed - Opened by geotseng-amd 3 months ago - 2 comments

#1325 - Fix F8/BF8 failed cases for GWVW=8 and Beta != 0

Pull Request - State: closed - Opened by geotseng-amd 3 months ago

#1325 - Fix F8/BF8 failed cases for GWVW=8 and Beta != 0

Pull Request - State: closed - Opened by geotseng-amd 3 months ago

#1324 - gfx942 bbs tn equality tuning

Pull Request - State: closed - Opened by aazz44ss 3 months ago - 1 comment

#1324 - gfx942 bbs tn equality tuning

Pull Request - State: closed - Opened by aazz44ss 3 months ago - 1 comment

#1323 - Tune Aldebaran BF16 NN TN NT GEMM sizes

Pull Request - State: closed - Opened by aferoz21 3 months ago - 3 comments

#1322 - Use find_package Python

Pull Request - State: closed - Opened by ellosel 4 months ago - 1 comment

#1321 - GEMM Perfromance when M/N == 1 is mutch slower than theorectial.

Issue - State: closed - Opened by IMbackK 4 months ago - 2 comments
Labels: Under Investigation

#1319 - Use stream-k dynamic grid size model by default

Pull Request - State: closed - Opened by AlexBrownAMD 4 months ago

#1318 - reduce default gfx targets (#1311)

Pull Request - State: closed - Opened by TorreZuk 4 months ago - 5 comments

#1317 - add 942 NN/NT/TN Equality sizes

Pull Request - State: closed - Opened by Jinp800125 4 months ago - 1 comment
Labels: gfx94x

#1316 - FP8 TN Compute for Grouped GEMMs

Pull Request - State: closed - Opened by ssuyuanchang 4 months ago - 4 comments
Labels: gfx94x

#1315 - Fix F8/BF8 failed cases for GWVW=8 and Beta != 0

Pull Request - State: closed - Opened by geotseng-amd 4 months ago - 4 comments
Labels: gfx94x

#1314 - Fix metadata accvgpr offset and next_free_vgpr usage

Pull Request - State: closed - Opened by KKyang 4 months ago - 2 comments
Labels: gfx94x

#1313 - Is the OOM issue addressed?

Issue - State: closed - Opened by SKPsanjeevi 4 months ago - 3 comments
Labels: Under Investigation

#1312 - Fix stream-k dynamic grid model

Pull Request - State: closed - Opened by AlexBrownAMD 4 months ago - 1 comment

#1311 - reduce default gfx targets

Pull Request - State: closed - Opened by TorreZuk 4 months ago
Labels: gfx94x

#1310 - Remove Duplicate 7900XTX from Issue Report

Pull Request - State: closed - Opened by darren-amd 4 months ago
Labels: documentation, ci:docs-only

#1309 - Fix occupancy does not calculate correctly

Pull Request - State: closed - Opened by KKyang 4 months ago - 2 comments

#1306 - code-gen: Fixed DTVA code-gen and validation failures

Pull Request - State: closed - Opened by solaslin 4 months ago
Labels: bug, gfx94x

#1305 - Add user offline tuning doc

Pull Request - State: closed - Opened by Jay0521 4 months ago
Labels: ci:docs-only

#1304 - Modify the condition to check resource.

Pull Request - State: closed - Opened by hcman2 4 months ago - 6 comments
Labels: gfx94x

#1303 - Fixing and adding test for DepthU=48

Pull Request - State: closed - Opened by mahmoodw 4 months ago

#1302 - GFX942 equality tuning for F8HS and F8B8HS for TN,NT,NN

Pull Request - State: closed - Opened by smalekta 4 months ago - 4 comments
Labels: gfx94x

#1301 - Fix clang compilation error

Pull Request - State: closed - Opened by KKyang 4 months ago

#1300 - Update ROCm versions on issue template

Pull Request - State: closed - Opened by darren-amd 4 months ago
Labels: documentation, ci:docs-only

#1299 - [Issue]: [Documentation] Document gfx908 support

Issue - State: closed - Opened by IMbackK 4 months ago - 6 comments
Labels: Under Investigation