From 6aae411c22e66bacc404a2d4b03b47f58345ac74 Mon Sep 17 00:00:00 2001
From: "Agarwal, Udit" <udit.agarwal@intel.com>
Date: Fri, 15 Nov 2024 13:58:38 -0800
Subject: [PATCH] Remove build options from fast kernel cache key

---
 sycl/source/detail/kernel_program_cache.hpp   | 19 ++++++++++++++-----
 .../program_manager/program_manager.cpp       | 10 ++--------
 2 files changed, 16 insertions(+), 13 deletions(-)

diff --git a/sycl/source/detail/kernel_program_cache.hpp b/sycl/source/detail/kernel_program_cache.hpp
index 5794d6930016a..f58cda059bcce 100644
--- a/sycl/source/detail/kernel_program_cache.hpp
+++ b/sycl/source/detail/kernel_program_cache.hpp
@@ -163,10 +163,19 @@ class KernelProgramCache {
       ::boost::unordered_map<ur_program_handle_t, KernelByNameT>;
 
   using KernelFastCacheKeyT =
-      std::tuple<SerializedObj, ur_device_handle_t, std::string, std::string>;
+      std::tuple<SerializedObj,      /* Serialized spec constants. */
+                 ur_device_handle_t, /* UR device handle pointer */
+                 std::string         /* Kernel Name */
+                 >;
+
   using KernelFastCacheValT =
-      std::tuple<ur_kernel_handle_t, std::mutex *, const KernelArgMask *,
-                 ur_program_handle_t>;
+      std::tuple<ur_kernel_handle_t,    /* UR kernel handle pointer. */
+                 std::mutex *,          /* Mutex guarding this kernel. */
+                 const KernelArgMask *, /* Eliminated kernel argument mask. */
+                 ur_program_handle_t /* UR program handle corresponding to this
+                                     kernel. */
+                 >;
+
   // This container is used as a fast path for retrieving cached kernels.
   // unordered_flat_map is used here to reduce lookup overhead.
   // The slow path is used only once for each newly created kernel, so the
@@ -283,7 +292,7 @@ class KernelProgramCache {
     std::unique_lock<std::mutex> Lock(MKernelFastCacheMutex);
     auto It = MKernelFastCache.find(CacheKey);
     if (It != MKernelFastCache.end()) {
-      traceKernel("Kernel fetched.", std::get<3>(CacheKey), true);
+      traceKernel("Kernel fetched.", std::get<2>(CacheKey), true);
       return It->second;
     }
     return std::make_tuple(nullptr, nullptr, nullptr, nullptr);
@@ -294,7 +303,7 @@ class KernelProgramCache {
     std::unique_lock<std::mutex> Lock(MKernelFastCacheMutex);
     // if no insertion took place, thus some other thread has already inserted
     // smth in the cache
-    traceKernel("Kernel inserted.", std::get<3>(CacheKey), true);
+    traceKernel("Kernel inserted.", std::get<2>(CacheKey), true);
     MKernelFastCache.emplace(CacheKey, CacheVal);
   }
 
diff --git a/sycl/source/detail/program_manager/program_manager.cpp b/sycl/source/detail/program_manager/program_manager.cpp
index 0c188b9fef718..25e03bff57a82 100644
--- a/sycl/source/detail/program_manager/program_manager.cpp
+++ b/sycl/source/detail/program_manager/program_manager.cpp
@@ -964,17 +964,11 @@ ProgramManager::getOrCreateKernel(const ContextImplPtr &ContextImpl,
   using KernelArgMaskPairT = KernelProgramCache::KernelArgMaskPairT;
 
   KernelProgramCache &Cache = ContextImpl->getKernelProgramCache();
-
-  std::string CompileOpts, LinkOpts;
   SerializedObj SpecConsts;
-  applyOptionsFromEnvironment(CompileOpts, LinkOpts);
-  // Should always come last!
-  appendCompileEnvironmentVariablesThatAppend(CompileOpts);
-  appendLinkEnvironmentVariablesThatAppend(LinkOpts);
+
   ur_device_handle_t UrDevice = DeviceImpl->getHandleRef();
 
-  auto key = std::make_tuple(std::move(SpecConsts), UrDevice,
-                             CompileOpts + LinkOpts, KernelName);
+  auto key = std::make_tuple(std::move(SpecConsts), UrDevice, KernelName);
   if (SYCLConfig<SYCL_CACHE_IN_MEM>::get()) {
     auto ret_tuple = Cache.tryToGetKernelFast(key);
     constexpr size_t Kernel = 0;  // see KernelFastCacheValT tuple