Implemented SIGNUM function kernel

[gkethamallax]

FPGA Log:

root@agilex7_dk_si_agf014ea:/tsi/ganesh/work# ./run_llama.sh
load_model: using TSavorite backend

Calculating mem_size 384 2 and creating ggml context

Creating input Tensor

Creating Backend Buffer

Loading Input Tensor Data to Backend Buffer

Bringing tensor data from Backend buffer and printing 32 tensor data:
[ 1.10 2.30 3.20 4.00 5.00 6.00 7.00 8.00 9.00 10.00 11.00 12.00 13.00 14.00 15.00 16.00 17.00 18.00 19.00 20.00 21.00 22.00 23.00 24.00 25.00 26.00 27.00 28.00 29.00 30.00 31.00 32.00 ]
main: compute buffer size: 0.2500 KB

Under Test case for compute API creating build_graph

Compute Done

operation type: 0, num of elements 32

compute is also done

TEST CASE PASSED

GGML Tsavorite Profiling Results:

Calls Total(ms) T/call Self(ms) Function

1    30.9820   30.9820      4.3060  [ 1.49%] [Thread] GGML Tsavorite 
1    26.6760   26.6760     22.3030  └─ [ 1.28%] tsi::runtime::TsavRTFPGA::initialize
1     2.9910    2.9910      2.9910    └─ [1.44e-01%] tsi::runtime::TsavRTFPGA::initializeQueues
1     0.9980    0.9980      0.9980    └─ [4.80e-02%] tsi::runtime::TsavRT::initialize
1     0.3840    0.3840      0.3500    └─ [1.85e-02%] tsi::runtime::TsavRTFPGA::sendNOPTestCommand
2     0.0340    0.0170      0.0340      └─ [1.63e-03%] tsi::runtime::executeWithTimeout

---

[Thread] tsi::runtime::TsavRT::awaitCommandListCompletion (cumulative over all threads)

1     1.4070    1.4070      0.0000  [6.77e-02%] [Thread] tsi::runtime::TsavRT::awaitCommandListCompletion
1    21.0506   21.0506     21.0506  └─ [ 1.01%] TXE 0 Idle
1     0.1633    0.1633      0.1633  └─ [7.85e-03%] [ txe_add ]

---

[Thread] tsi::runtime::TsavRT::finalizeCommandList (cumulative over all threads)

1     0.7080    0.7080      0.7000  [3.40e-02%] [Thread] tsi::runtime::TsavRT::finalizeCommandList
1     0.0080    0.0080      0.0080  └─ [3.85e-04%] tsi::runtime::executeWithTimeout

---

[Thread] tsi::runtime::TsavRT::processResponses (cumulative over all threads)

1     0.2550    0.2550      0.2440  [1.23e-02%] [Thread] tsi::runtime::TsavRT::processResponses
1     0.0110    0.0110      0.0110  └─ [5.29e-04%] tsi::runtime::executeWithTimeout

---

[Thread] tsi::runtime::TsavRTFPGA::finalize (cumulative over all threads)

1    35.4020   35.4020     34.8570  [ 1.70%] [Thread] tsi::runtime::TsavRTFPGA::finalize
1     0.5450    0.5450      0.5450  └─ [2.62e-02%] tsi::runtime::TsavRTFPGA::releaseTxes

---

[Thread] tsi::runtime::TsavRT::allocate (cumulative over all threads)

3     0.1390    0.0463      0.1390  [6.68e-03%] [Thread] tsi::runtime::TsavRT::allocate

---

[Thread] tsi::runtime::TsavRTFPGA::loadBlob (cumulative over all threads)

1     3.3130    3.3130      3.3130  [1.59e-01%] [Thread] tsi::runtime::TsavRTFPGA::loadBlob

---

[Thread] tsi::runtime::TsavRT::addCommandToList (cumulative over all threads)

1     0.6320    0.6320      0.6320  [3.04e-02%] [Thread] tsi::runtime::TsavRT::addCommandToList

---

[Thread] tsi::runtime::TsavRTFPGA::unloadBlob (cumulative over all threads)

1     0.0430    0.0430      0.0430  [2.07e-03%] [Thread] tsi::runtime::TsavRTFPGA::unloadBlob

---

[Thread] tsi::runtime::TsavRT::deallocate (cumulative over all threads)

1     0.0210    0.0210      0.0210  [1.01e-03%] [Thread] tsi::runtime::TsavRT::deallocate

========================================================================================================================
- 2079.6420 0.0000 2079.6420 [100.00%] TOTAL

Counter Metrics:

Metric Min Max Avg

Queue_0_Occupancy 0.0000 1.0000 0.3333

root@agilex7_dk_si_agf014ea:/tsi/ganesh/work#

[atrivedi-tsavoritesi]

A minor comment and other changes look good.

[atrivedi-tsavoritesi]

Is the results always -1 or 1 ?

[gkethamallax]

yes ashish, signum function have -1, 0, or 1.