From a862f5b7007ef50b5def30506f0cea138b73c710 Mon Sep 17 00:00:00 2001 From: Yong He Date: Wed, 29 Mar 2023 10:00:48 -0700 Subject: Update a1-02-slangpy.md --- docs/user-guide/a1-02-slangpy.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'docs') diff --git a/docs/user-guide/a1-02-slangpy.md b/docs/user-guide/a1-02-slangpy.md index 6ee039d43..6a9b8baa3 100644 --- a/docs/user-guide/a1-02-slangpy.md +++ b/docs/user-guide/a1-02-slangpy.md @@ -37,7 +37,7 @@ void square_fwd_kernel(TensorView input, TensorView output) { uint3 globalIdx = cudaBlockIdx() * cudaBlockDim() + cudaThreadIdx(); - if (globalIdx.x > input.size(0) || globalIdx.x > input.size(1)) + if (globalIdx.x > input.size(0) || globalIdx.y > input.size(1)) return; float result = square(input[globalIdx.xy]); output[globalIdx.xy] = result; @@ -134,7 +134,7 @@ void square_bwd_kernel(TensorView input, TensorView grad_out, Tens { uint3 globalIdx = cudaBlockIdx() * cudaBlockDim() + cudaThreadIdx(); - if (globalIdx.x > input.size(0) || globalIdx.x > input.size(1)) + if (globalIdx.x > input.size(0) || globalIdx.y > input.size(1)) return; DifferentialPair dpInput = diffPair(input[globalIdx.xy]); -- cgit v1.2.3