tests : filter out no-ops from coverage report (#15900)

* tests : filter out no-ops from coverage report

This commit is a follow-up commit for #15745 to address the feedback on
how no-op operations should be filtered out from the coverage report.

The feedback regarding the UNARY and GLU sub-operations not being
handled I not exactly sure what should be done. They are included in the
coverage, for example ABS, ELU, EXP, GELU, GEGLU, GEGLU_ERF etc are in
the list of covered operations:
```console
$ ./build/bin/test-backend-ops --show-coverage
Operations covered by tests (89):
  ✓ ABS
  ✓ ACC
  ✓ ADD
  ✓ ADD1
  ✓ ADD_ID
  ✓ ARANGE
  ✓ ARGMAX
  ✓ ARGSORT
  ✓ CLAMP
  ✓ CONCAT
  ✓ CONV_2D
  ✓ CONV_2D_DW
  ✓ CONV_3D
  ✓ CONV_TRANSPOSE_1D
  ✓ CONV_TRANSPOSE_2D
  ✓ COS
  ✓ COUNT_EQUAL
  ✓ CPY
  ✓ CROSS_ENTROPY_LOSS
  ✓ CROSS_ENTROPY_LOSS_BACK
  ✓ DIAG_MASK_INF
  ✓ DIV
  ✓ DUP
  ✓ ELU
  ✓ EXP
  ✓ FLASH_ATTN_EXT
  ✓ GATED_LINEAR_ATTN
  ✓ GEGLU
  ✓ GEGLU_ERF
  ✓ GEGLU_QUICK
  ✓ GELU
  ✓ GELU_ERF
  ✓ GELU_QUICK
  ✓ GET_ROWS
  ✓ GET_ROWS_BACK
  ✓ GROUP_NORM
  ✓ HARDSIGMOID
  ✓ HARDSWISH
  ✓ IM2COL
  ✓ IM2COL_3D
  ✓ L2_NORM
  ✓ LEAKY_RELU
  ✓ LOG
  ✓ MEAN
  ✓ MUL
  ✓ MUL_MAT
  ✓ MUL_MAT_ID
  ✓ NEG
  ✓ NORM
  ✓ OPT_STEP_ADAMW
  ✓ OPT_STEP_SGD
  ✓ OUT_PROD
  ✓ PAD
  ✓ PAD_REFLECT_1D
  ✓ POOL_2D
  ✓ REGLU
  ✓ RELU
  ✓ REPEAT
  ✓ REPEAT_BACK
  ✓ RMS_NORM
  ✓ RMS_NORM_BACK
  ✓ ROLL
  ✓ ROPE
  ✓ ROPE_BACK
  ✓ RWKV_WKV6
  ✓ RWKV_WKV7
  ✓ SCALE
  ✓ SET
  ✓ SET_ROWS
  ✓ SGN
  ✓ SIGMOID
  ✓ SILU
  ✓ SILU_BACK
  ✓ SIN
  ✓ SOFT_MAX
  ✓ SOFT_MAX_BACK
  ✓ SQR
  ✓ SQRT
  ✓ SSM_CONV
  ✓ SSM_SCAN
  ✓ STEP
  ✓ SUB
  ✓ SUM
  ✓ SUM_ROWS
  ✓ SWIGLU
  ✓ SWIGLU_OAI
  ✓ TANH
  ✓ TIMESTEP_EMBEDDING
  ✓ UPSCALE

Operations without tests (14):
  ✗ ADD_REL_POS
  ✗ CUSTOM
  ✗ DIAG
  ✗ DIAG_MASK_ZERO
  ✗ FLASH_ATTN_BACK
  ✗ GET_REL_POS
  ✗ IM2COL_BACK
  ✗ MAP_CUSTOM1
  ✗ MAP_CUSTOM2
  ✗ MAP_CUSTOM3
  ✗ POOL_1D
  ✗ POOL_2D_BACK
  ✗ WIN_PART
  ✗ WIN_UNPART

Coverage Summary:
  Total operations: 103
  Tested operations: 89
  Untested operations: 14
  Coverage: 86.4%
```

Refs: https://github.com/ggml-org/llama.cpp/pull/15745

* use of ggml_op enum values instead of strcmp

diff --git a/tests/test-backend-ops.cpp b/tests/test-backend-ops.cpp
index adf91ab6f9edd822f2b420237d29c3a3ce7f9bcc..4a882ab072cc01051dc009e06c3a99685d9ef3a0 100644 (file)
--- a/tests/test-backend-ops.cpp
+++ b/tests/test-backend-ops.cpp
@@ -6807,7 +6807,17 @@ static void list_all_ops() {
 static void show_test_coverage() {
     std::set<std::string> all_ops;
     for (int i = 1; i < GGML_OP_COUNT; i++) {
-        all_ops.insert(ggml_op_name((enum ggml_op)i));
+        auto op = (enum ggml_op)i;
+        if (op == GGML_OP_VIEW      ||
+            op == GGML_OP_RESHAPE   ||
+            op == GGML_OP_PERMUTE   ||
+            op == GGML_OP_TRANSPOSE ||
+            op == GGML_OP_CONT      ||
+            op == GGML_OP_GLU       ||
+            op == GGML_OP_UNARY) {
+            continue;
+        }
+        all_ops.insert(ggml_op_name(op));
     }
     for (int i = 0; i < GGML_UNARY_OP_COUNT; i++) {
         all_ops.insert(ggml_unary_op_name((enum ggml_unary_op)i));