From e7d94ba02018a9973bba7012c32267cba97cd9f1 Mon Sep 17 00:00:00 2001
From: Eddy Kim <eddy.kim@intel.com>
Date: Wed, 10 May 2023 15:56:43 +0900
Subject: [PATCH] [GPU] fix adaptive pooling kernel (#17429)

* fixed not to use ceil

* added an unit test
---
 .../cl_kernels/adaptive_pooling_gpu_ref.cl               | 9 ++++++---
 .../unit/test_cases/adaptive_avg_pooling_gpu_test.cpp    | 2 +-
 .../unit/test_cases/adaptive_max_pooling_gpu_test.cpp    | 2 +-
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/src/plugins/intel_gpu/src/kernel_selector/cl_kernels/adaptive_pooling_gpu_ref.cl b/src/plugins/intel_gpu/src/kernel_selector/cl_kernels/adaptive_pooling_gpu_ref.cl
index 85b44df0cf7..f3eaa90f6e5 100644
--- a/src/plugins/intel_gpu/src/kernel_selector/cl_kernels/adaptive_pooling_gpu_ref.cl
+++ b/src/plugins/intel_gpu/src/kernel_selector/cl_kernels/adaptive_pooling_gpu_ref.cl
@@ -45,12 +45,15 @@ KERNEL(adaptive_pooling_gpu)(
 
 #if OUTPUT_DIMS == 5
     uint z_start = z * INPUT0_SIZE_Z / OUTPUT_SIZE_Z;
-    uint z_end = ceil((float)((z + 1) * INPUT0_SIZE_Z) / OUTPUT_SIZE_Z);
+    uint z_end = ((z + 1) * INPUT0_SIZE_Z) / OUTPUT_SIZE_Z;
+    z_end += (((z + 1) * INPUT0_SIZE_Z) - OUTPUT_SIZE_Z * z_end != 0) ? 1 : 0;
 #endif
     uint y_start = y * INPUT0_SIZE_Y / OUTPUT_SIZE_Y;
-    uint y_end = ceil((float)((y + 1) * INPUT0_SIZE_Y) / OUTPUT_SIZE_Y);
+    uint y_end = ((y + 1) * INPUT0_SIZE_Y) / OUTPUT_SIZE_Y;
+    y_end += (((y + 1) * INPUT0_SIZE_Y) - OUTPUT_SIZE_Y * y_end != 0) ? 1 : 0;
     uint x_start = x * INPUT0_SIZE_X / OUTPUT_SIZE_X;
-    uint x_end = ceil((float)((x + 1) * INPUT0_SIZE_X) / OUTPUT_SIZE_X);
+    uint x_end = ((x + 1) * INPUT0_SIZE_X) / OUTPUT_SIZE_X;
+    x_end += (((x + 1) * INPUT0_SIZE_X) - OUTPUT_SIZE_X * x_end != 0) ? 1 : 0;
 
 
 #if OUTPUT_DIMS == 5
diff --git a/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_avg_pooling_gpu_test.cpp b/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_avg_pooling_gpu_test.cpp
index 094b7d5e0f7..11f7c601aa7 100644
--- a/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_avg_pooling_gpu_test.cpp
+++ b/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_avg_pooling_gpu_test.cpp
@@ -171,7 +171,7 @@ INSTANTIATE_TEST_SUITE_P(smoke_adaptive_avg_pooling_test_f32_2d,
                                  ::testing::ValuesIn(std::vector<AdaptiveAvgPoolingParams>{
                                         { tensor(1, 2, 7, 3), tensor(1, 2, 3, 3) },
                                         { tensor(2, 3, 7, 3), tensor(2, 3, 3, 3) },
-                                        { tensor(1, 3, 16, 16), tensor(1, 3, 16, 16) },
+                                        { tensor(1, 3, 7, 7), tensor(1, 3, 7, 7) },
                                     }),
                                  ::testing::Values(format::bfyx),
                                  ::testing::Values(format::bfyx),
diff --git a/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_max_pooling_gpu_test.cpp b/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_max_pooling_gpu_test.cpp
index faa9520af55..b1cb0e7329f 100644
--- a/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_max_pooling_gpu_test.cpp
+++ b/src/plugins/intel_gpu/tests/unit/test_cases/adaptive_max_pooling_gpu_test.cpp
@@ -69,7 +69,7 @@ ov::Shape tensorToShape(const tensor& t, const format f)
 template<typename T>
 void generateTestData(const AdaptiveMaxPoolingParams& p, const format fmt,
                       std::vector<T>& inputs, std::vector<T>& outputs, std::vector<int32_t>& indices) {
-    const auto in = generate_random_1d<float>(p.inputTensor.count(), -127, 127, 1);
+    const auto in = generate_random_1d<float>(p.inputTensor.count(), -127, 127, 8);
     std::vector<float> out(p.outputTensor.count());
     std::vector<int32_t> ind(p.outputTensor.count());