17 | const float* __restrict__ input,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
18 | const float* __restrict__ bias,
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:17:31: note: the first parameter in the range is 'input'
17 | const float* __restrict__ input,
| ^~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:18:31: note: the last parameter in the range is 'bias'
18 | const float* __restrict__ bias,
| ^~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:20:5: warning: 2 adjacent parameters of 'conv_transpose2d_forward_kernel' of similar type ('const int') are easily swapped by mistake [bugprone-easily-swappable-parameters]
20 | const int N,
| ^~~~~~~~~~~~
21 | const int C_in,
| ~~~~~~~~~~~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:20:15: note: the first parameter in the range is 'N'
20 | const int N,
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:21:15: note: the last parameter in the range is 'C_in'
21 | const int C_in,
| ^~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:23:5: warning: 2 adjacent parameters of 'conv_transpose2d_forward_kernel' of similar type ('const int') are easily swapped by mistake [bugprone-easily-swappable-parameters]
23 | const int W_in,
| ^~~~~~~~~~~~~~~
24 | const int C_out,
| ~~~~~~~~~~~~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:23:15: note: the first parameter in the range is 'W_in'
23 | const int W_in,
| ^~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:24:15: note: the last parameter in the range is 'C_out'
24 | const int C_out,
| ^~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:26:5: warning: 2 adjacent parameters of 'conv_transpose2d_forward_kernel' of similar type ('const int') are easily swapped by mistake [bugprone-easily-swappable-parameters]
26 | const int W_out,
| ^~~~~~~~~~~~~~~~
27 | const int kH,
| ~~~~~~~~~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:26:15: note: the first parameter in the range is 'W_out'
26 | const int W_out,
| ^~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:27:15: note: the last parameter in the range is 'kH'
27 | const int kH,
| ^~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:28:5: warning: 2 adjacent parameters of 'conv_transpose2d_forward_kernel' of similar type ('const int') are easily swapped by mistake [bugprone-easily-swappable-parameters]
28 | const int kW,
| ^~~~~~~~~~~~~
29 | const int sH,
| ~~~~~~~~~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:28:15: note: the first parameter in the range is 'kW'
28 | const int kW,
| ^~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:29:15: note: the last parameter in the range is 'sH'
29 | const int sH,
| ^~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:30:5: warning: 2 adjacent parameters of 'conv_transpose2d_forward_kernel' of similar type ('const int') are easily swapped by mistake [bugprone-easily-swappable-parameters]
30 | const int sW,
| ^~~~~~~~~~~~~
31 | const int pH,
| ~~~~~~~~~~~~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:30:15: note: the first parameter in the range is 'sW'
30 | const int sW,
| ^~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:31:15: note: the last parameter in the range is 'pH'
31 | const int pH,
| ^~
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:34:21: warning: narrowing conversion from 'unsigned int' to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
34 | const int tid = threadIdx.x;
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:35:21: warning: narrowing conversion from 'unsigned int' to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
35 | const int bid = blockIdx.x;
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:81:19: warning: the parameter 'x' is copied for each invocation but only used as a const reference; consider making it a const reference [performance-unnecessary-value-param]
81 | torch::Tensor x,
| ^
| const &
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:82:19: warning: the parameter 'weight' is copied for each invocation but only used as a const reference; consider making it a const reference [performance-unnecessary-value-param]
82 | torch::Tensor weight,
| ^
| const &
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:83:16: warning: the parameter 'bias_obj' is copied for each invocation but only used as a const reference; consider making it a const reference [performance-unnecessary-value-param]
83 | py::object bias_obj,
| ^
| const &
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:88:24: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
88 | int weight_numel = weight.numel();
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:89:23: warning: narrowing conversion from 'unsigned long' to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
89 | int weight_size = weight_numel * sizeof(float);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:109:19: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
109 | const int N = x.size(0);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:110:22: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
110 | const int C_in = x.size(1);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:111:22: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
111 | const int H_in = x.size(2);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:112:22: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
112 | const int W_in = x.size(3);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:114:20: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
114 | const int kH = weight.size(2);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:115:20: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
115 | const int kW = weight.size(3);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:116:23: warning: narrowing conversion from 'int64_t' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
116 | const int C_out = weight.size(1);
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:118:20: warning: narrowing conversion from 'value_type' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
118 | const int sH = stride[0];
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:119:20: warning: narrowing conversion from 'value_type' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
119 | const int sW = stride[1];
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:120:20: warning: narrowing conversion from 'value_type' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
120 | const int pH = padding[0];
| ^
/home/robert_sakana_ai/llm_cuda/experiments/20250202_optimize_b10_s4_e0_sweep/level_1/task_78/b6_s3_conv_trans_unroll_optimized/base/base.cu:121:20: warning: narrowing conversion from 'value_type' (aka 'long') to signed type 'int' is implementation-defined [bugprone-narrowing-conversions]
121 | const int pW = padding[1];
| ^