Remove unused variables (#1955)

Author: zasdfgbnm

benchmarks/cpp/nvfuser/batch_norm_channels_first.cpp

@@ -73,10 +73,6 @@ static void NvFuserScheduler_BatchNorm(
     DataType dtype) {
   TORCH_INTERNAL_ASSERT(dtype == DataType::Float || dtype == DataType::Half);
 
-  const bool kTraining = true;
-  const float kMomentum = 0.1;
-  const float kEps = 1e-5;
-
   std::vector<int64_t> input_shape{
       benchmark_state.range(0),
       benchmark_state.range(1),

benchmarks/cpp/nvfuser/batch_norm_channels_first_backward.cpp

@@ -25,7 +25,6 @@ static void setupBatchNorm_BWD(Fusion* fusion, DataType dtype) {
   FusionGuard fg(fusion);
 
   const bool kTraining = true;
-  const float kMomentum = 0.1;
   const float kEps = 1e-5;
 
   // setup fusion
@@ -85,9 +84,6 @@ static void NvFuserScheduler_BatchNorm_BWD(
     DataType dtype) {
   TORCH_INTERNAL_ASSERT(dtype == DataType::Float || dtype == DataType::Half);
 
-  const bool kTraining = true;
-  const float kEps = 1e-5;
-
   std::vector<int64_t> input_shape{
       benchmark_state.range(0),
       benchmark_state.range(1),

benchmarks/cpp/nvfuser/batch_norm_channels_last.cpp

@@ -74,10 +74,6 @@ static void NvFuserScheduler_BatchNorm_nhwc(
     DataType dtype) {
   TORCH_INTERNAL_ASSERT(dtype == DataType::Float || dtype == DataType::Half);
 
-  const bool kTraining = true;
-  const float kMomentum = 0.1;
-  const float kEps = 1e-5;
-
   std::vector<int64_t> input_shape{
       benchmark_state.range(0),
       benchmark_state.range(2),

benchmarks/cpp/nvfuser/batch_norm_channels_last_backward.cpp

@@ -25,7 +25,6 @@ static void setupBatchNorm_nhwc_BWD(Fusion* fusion, DataType dtype) {
   FusionGuard fg(fusion);
 
   const bool kTraining = true;
-  const float kMomentum = 0.1;
   const float kEps = 1e-5;
 
   // setup fusion
@@ -86,9 +85,6 @@ static void NvFuserScheduler_BatchNorm_nhwc_BWD(
     DataType dtype) {
   TORCH_INTERNAL_ASSERT(dtype == DataType::Float || dtype == DataType::Half);
 
-  const bool kTraining = true;
-  const float kEps = 1e-5;
-
   std::vector<int64_t> input_shape{
       benchmark_state.range(0),
       benchmark_state.range(2),

benchmarks/cpp/nvfuser/gelu_backward.cpp

@@ -113,9 +113,6 @@ BENCHMARK(GeluBackward_AutoSchedule)->Unit(benchmark::kMicrosecond);
 //------------------------------------------------------------------------------
 
 static void GeluBackward_Lower(benchmark::State& benchmark_state) {
-  constexpr int kHiddenFeatures = 512;
-  constexpr int kBatchSize = 64;
-
   Fusion fusion;
 
   // setup fusion

benchmarks/cpp/nvfuser/layer_norm.cpp

@@ -22,7 +22,6 @@ static void setupLayerNorm(Fusion* fusion, DataType dtype) {
 
   FusionGuard fg(fusion);
 
-  const int kReductionAxis = 1;
   const float kEps = 1e-5;
 
   Double* eps_ptr = IrBuilder::create<Double>(kEps);
@@ -61,7 +60,6 @@ static void NvFuserScheduler_LayerNorm(
 
   std::vector<int64_t> input_shape{
       benchmark_state.range(0), benchmark_state.range(1)};
-  const float kEps = 1e-5;
 
   // inputs
   at::manual_seed(0);

benchmarks/cpp/nvfuser/layer_norm_backward.cpp

@@ -22,9 +22,6 @@ static void setupLayerNorm_BWD(Fusion* fusion, DataType dtype) {
 
   TORCH_INTERNAL_ASSERT(dtype == DataType::Float || dtype == DataType::Half);
 
-  const int kReductionAxis = 1;
-  Double* eps_ptr = IrBuilder::create<Double>(1e-5);
-
   // setup fusion
   auto grad_out = makeContigTensor(2, dtype);
   auto input = makeContigTensor(2, dtype);

benchmarks/cpp/nvfuser/rms_norm.cpp

@@ -24,7 +24,6 @@ static void setupRMSNorm(Fusion* fusion, DataType dtype) {
 
   FusionGuard fg(fusion);
 
-  const int kReductionAxis = 2;
   const float kEps = 1e-6;
 
   Double* eps_ptr = IrBuilder::create<Double>(kEps);
@@ -61,7 +60,6 @@ static void NvFuserScheduler_RMSNorm(
       dtype == DataType::BFloat16);
 
   std::vector<int64_t> input_shape{8, benchmark_state.range(0), 1024};
-  const float kEps = 1e-6;
 
   // inputs
   at::manual_seed(0);

benchmarks/cpp/nvfuser/rms_norm_backward.cpp

@@ -24,9 +24,6 @@ static void setupRMSNorm_BWD(Fusion* fusion, DataType dtype) {
       dtype == DataType::Float || dtype == DataType::Half ||
       dtype == DataType::BFloat16);
 
-  const int kReductionAxis = 2;
-  Double* eps_ptr = IrBuilder::create<Double>(1e-6);
-
   // setup fusion
   auto grad_out = makeContigTensor(3, dtype);
   auto input = makeContigTensor(3, dtype);

benchmarks/cpp/nvfuser/timm.cpp

@@ -139,7 +139,6 @@ static void setup_vit_base_patch16_224_bcast5(Fusion* fusion, void* null) {
   auto t20 = sum(t37, {2});
   auto t24 = broadcast(t20, bcast_pattern1);
   auto d95 = castOp(DataType::Double, t2->axis(2)->extent());
-  auto d96 = mul(IrBuilder::create<Double>(1.0), d95);
   auto d105 = reciprocal(d95);
   auto t25 = mul(t24, d105);
   auto t26 = add(t25, IrBuilder::create<Double>(1e-6));
@@ -320,8 +319,6 @@ static void NvFuserScheduler_TIMM_vit_base_patch16_224_norm_inner3(
 
   at::manual_seed(0);
   auto fp16_options = at::TensorOptions().dtype(at::kHalf).device(at::kCUDA, 0);
-  auto fp32_options =
-      at::TensorOptions().dtype(at::kFloat).device(at::kCUDA, 0);
 
   auto t0 = at::randn(input_shape, fp16_options);