Code

Use MKL for verification#63

Code

Closed

AD2605 wants to merge 58 commits intocodeplaysoftware:sycl-developcodeplaysoftware/cutlass-fork:sycl-developfrom AD2605:atharva/add_mklAD2605/cutlass-fork:atharva/add_mklCopy head branch name to clipboard

+6,649-514

Commits

Commits on Mar 21, 2024

• Migrate cute sgemm_nt_1 to SYCLX

  

  aacostadiaz

  authored and

  mehdi-goli

  committed
  27b550e

  Copy full SHA for 27b550e

• "Migrate cute example to sycl"

  mehdi-goli

  committed
  35f0f25

  Copy full SHA for 35f0f25

• Migrate cute sgemm_nt_1 to SYCL"

  mehdi-goli

  committed
  d986eff

  Copy full SHA for d986eff

• fix sycl header

  

  AD2605

  authored and

  mehdi-goli

  committed
  3f5f86d

  Copy full SHA for 3f5f86d

• Initial README for SYCL support

  

  Ruyk

  authored and

  mehdi-goli

  committed
  14cf978

  Copy full SHA for 14cf978

• Update README-sycl.md

  Show description for c67ed0f
  

  Ruyk

  and

  mehdi-goli

  committed
  c67ed0f

  Copy full SHA for c67ed0f

• Update README-sycl.md

  Show description for ca2cc24
  

  Ruyk

  and

  mehdi-goli

  committed
  ca2cc24

  Copy full SHA for ca2cc24

Commits on Apr 2, 2024

• Merge branch 'NVIDIA:main' into sycl-develop

  aacostadiaz

  authored
  82c44d2

  Copy full SHA for 82c44d2

Commits on Apr 4, 2024

• Add cutlass example (codeplaysoftware#13)

  Show description for 696397f
  

  aacostadiaz

  and

  mehdi-goli

  authored
  696397f

  Copy full SHA for 696397f

• Remove the sgemm_nt_1_sycl PoC (codeplaysoftware#15)

  Show description for a00e437
  

  aacostadiaz

  and

  mehdi-goli

  authored
  a00e437

  Copy full SHA for a00e437

• Updating README-sycl.md to capture the 3.5 modifications (codeplaysoftware#16)

  Show description for a726bd3
  

  mehdi-goli

  and

  aacostadiaz

  authored
  a726bd3

  Copy full SHA for a726bd3

• Revert "Updating README-sycl.md to capture the 3.5 modifications (codeplaysoftware#16)" (codeplaysoftware#17)

  Show description for 84e730f
  mehdi-goli

  authored
  84e730f

  Copy full SHA for 84e730f

• Updating the readme-sycl.md (codeplaysoftware#18)

  mehdi-goli

  authored
  3c0f4bd

  Copy full SHA for 3c0f4bd

• Merge remote-tracking branch 'upstream/sycl-develop' into sycl-develop

  AD2605

  committed
  4e901a6

  Copy full SHA for 4e901a6

Commits on Apr 8, 2024

• Cute examples in SYCL (codeplaysoftware#14)

  Show description for fea43b7
  

  3 peopleauthored
  fea43b7

  Copy full SHA for fea43b7

Commits on Apr 9, 2024

• Merge branch 'codeplaysoftware:sycl-develop' into sycl-develop

  AD2605

  authored
  9fd5087

  Copy full SHA for 9fd5087

Commits on Apr 10, 2024

• Migrate cute components to SYCL (codeplaysoftware#19)

  Show description for 13adaed
  AD2605

  authored
  13adaed

  Copy full SHA for 13adaed

• Add CMake configuration (codeplaysoftware#20)

  Show description for f07d0ee
  

  aacostadiaz

  and

  mehdi-goli

  authored
  f07d0ee

  Copy full SHA for f07d0ee

• Merge remote-tracking branch 'upstream/sycl-develop' into sycl-develop

  AD2605

  committed
  a57b605

  Copy full SHA for a57b605

• Update README-sycl.md (codeplaysoftware#22)

  Show description for aa9c364
  mehdi-goli

  authored
  aa9c364

  Copy full SHA for aa9c364

• Add XE MMA/copy atom

  rolandschulz

  committed
  4f3e97d

  Copy full SHA for 4f3e97d

• Update to 3.5 API

  rolandschulz

  committed
  2fd2d84

  Copy full SHA for 2fd2d84

Commits on Apr 11, 2024

• fixing device only code that get called in the host side (codeplaysoftware#25)

  mehdi-goli

  authored
  d30f750

  Copy full SHA for d30f750

• Fix GPU clock (codeplaysoftware#21)

  aacostadiaz

  authored
  43d692f

  Copy full SHA for 43d692f

Commits on Apr 12, 2024

• Apply suggestions from code review

  Show description for 4d2b315
  

  rolandschulz

  and

  mehdi-goli

  authored
  4d2b315

  Copy full SHA for 4d2b315

Commits on Apr 16, 2024

• Merge remote-tracking branch 'upstream/sycl-develop' into sycl-develop

  AD2605

  committed
  256f6c5

  Copy full SHA for 256f6c5

• Fix typo in Macro (codeplaysoftware#28)

  Show description for ae6989a
  

  3 peopleauthored
  ae6989a

  Copy full SHA for ae6989a

• Merge remote-tracking branch 'upstream/sycl-develop' into sycl-develop

  AD2605

  committed
  4568ea7

  Copy full SHA for 4568ea7

Commits on Apr 17, 2024

• Merge pull request codeplaysoftware#23 from rolandschulz/add-xe-atoms

  Show description for ddbba2f
  rolandschulz

  authored
  ddbba2f

  Copy full SHA for ddbba2f

• Update README-sycl.md (codeplaysoftware#31)

  mehdi-goli

  authored
  51f5c2e

  Copy full SHA for 51f5c2e

Commits on Apr 18, 2024

• Merge remote-tracking branch 'upstream/sycl-develop' into sycl-develop

  AD2605

  committed
  b9cb745

  Copy full SHA for b9cb745

• use cute::bfloat16_t (codeplaysoftware#32)

  rolandschulz

  authored
  53147de

  Copy full SHA for 53147de

• Make atom type a make_2d_copy argument (codeplaysoftware#33)

  rolandschulz

  authored
  b2746a2

  Copy full SHA for b2746a2

Commits on Apr 23, 2024

• Merge branch 'codeplaysoftware:sycl-develop' into sycl-develop

  AD2605

  authored
  ad37663

  Copy full SHA for ad37663

Commits on Apr 29, 2024

• Fixed block dims and grid dims through syclcompat (codeplaysoftware#50)

  Show description for 6a8aee6
  

  muhammad-tanvir-1211

  and

  mehdi-goli

  authored
  6a8aee6

  Copy full SHA for 6a8aee6

Commits on Apr 30, 2024

• Add cute components and utils for 2D copy (codeplaysoftware#44)

  Show description for 8a45671
  

  4 peopleauthored
  8a45671

  Copy full SHA for 8a45671

Commits on May 1, 2024

• Fix compilation errors with PVC pipeline (codeplaysoftware#58)

  muhammad-tanvir-1211

  authored
  1445385

  Copy full SHA for 1445385

Commits on May 7, 2024

• Remove CUDA toolkit dependency for SYCL (codeplaysoftware#49)

  Show description for f4782bf
  

  3 peopleauthored
  f4782bf

  Copy full SHA for f4782bf

Commits on May 9, 2024

• Define CUdeviceptr type (codeplaysoftware#60)

  muhammad-tanvir-1211

  authored
  6217cc6

  Copy full SHA for 6217cc6

Commits on May 13, 2024

• [CP-Sec] Add SECURITY.md file (codeplaysoftware#62)

  carlewis

  authored
  da086af

  Copy full SHA for da086af

• Fix issues with the ampere example (codeplaysoftware#61)

  Show description for b9c5187
  

  aacostadiaz

  and

  muhammad-tanvir-1211

  authored
  b9c5187

  Copy full SHA for b9c5187

• Enable Cute tests (codeplaysoftware#57)

  Show description for 9d12ff6
  

  3 peopleauthored
  9d12ff6

  Copy full SHA for 9d12ff6

• Merge remote-tracking branch 'codeplay_cutlass/sycl-develop' into sycl-develop

  AD2605

  committed
  dc016e4

  Copy full SHA for dc016e4

Commits on May 15, 2024

• CMake Changes for using oneMKL in examples

  AD2605

  committed
  113a4c3

  Copy full SHA for 113a4c3

• fix verification issue and restore default sizes

  AD2605

  committed
  6ea9c67

  Copy full SHA for 6ea9c67

• add new line

  AD2605

  committed
  7afff5d

  Copy full SHA for 7afff5d

Commits on May 16, 2024

• Include changes for Intel PVC pipeline (codeplaysoftware#51)

  Show description for 7e7db70
  muhammad-tanvir-1211

  authored
  7e7db70

  Copy full SHA for 7e7db70

• Example changes for Intel PVC pipeline (codeplaysoftware#52)

  Show description for ce10e06
  muhammad-tanvir-1211

  authored
  ce10e06

  Copy full SHA for ce10e06

• Make sure SYCL_TARGET is defined before setting MKL Backend

  Show description for 197c4a2
  

  AD2605

  and

  aacostadiaz

  authored
  197c4a2

  Copy full SHA for 197c4a2

• Update examples/CMakeLists.txt

  Show description for 2713e7b
  

  AD2605

  and

  aacostadiaz

  authored
  2713e7b

  Copy full SHA for 2713e7b

• removed repeated check from onemkl.cmake

  AD2605

  committed
  2341884

  Copy full SHA for 2341884

• Merge remote-tracking branch 'codeplay_cutlass/sycl-develop' into atharva/add_mkl

  AD2605

  committed
  5610cc6

  Copy full SHA for 5610cc6

• change device_memory.h after PVC example merge

  AD2605

  committed
  b1f7aa1

  Copy full SHA for b1f7aa1

Commits on May 20, 2024

• restore global offset flag

  AD2605

  committed
  59c371e

  Copy full SHA for 59c371e

Commits on May 28, 2024

• Update CMakeLists.txt

  Show description for 9cdba84
  

  AD2605

  and

  mehdi-goli

  authored
  9cdba84

  Copy full SHA for 9cdba84

• Update CMakeLists.txt

  Show description for 7b6eadd
  

  AD2605

  and

  mehdi-goli

  authored
  7b6eadd

  Copy full SHA for 7b6eadd

• Update CMakeLists.txt

  Show description for ca61e2a
  

  AD2605

  and

  mehdi-goli

  authored
  ca61e2a

  Copy full SHA for ca61e2a

• Update examples/CMakeLists.txt

  Show description for e632ea0
  

  AD2605

  and

  mehdi-goli

  authored
  e632ea0

  Copy full SHA for e632ea0