fix erroneous correction

Titus-von-Koeller · web-flow · commit 678f9f3ec19f · 2024-02-04T17:19:42.000-03:00
diff --git a/csrc/kernels.cu b/csrc/kernels.cu
@@ -2259,7 +2259,7 @@ template<typename T, int THREADS, int ITEMS_PER_THREAD, int TILE_ROWS, int TILE_
   }
 
   // 4. store data via atomicMax
-  // to store col data efficiency we need to rewrite the smem blocked data [0, 1, 2, 3...] for t0
+  // to store col data efficiently we need to rewrite the smem blocked data [0, 1, 2, 3...] for t0
   // into a striped arrangement: [0, 8, 16, 24, ..] for t0
   __syncthreads();
   BlockExchange(temp_storage.exchange).BlockedToStriped(local_col_absmax_values);

Original file line number	Diff line number	Diff line change
`@@ -2259,7 +2259,7 @@ template<typename T, int THREADS, int ITEMS_PER_THREAD, int TILE_ROWS, int TILE_`
`2259`	`2259`	`}`
`2260`	`2260`
`2261`	`2261`	`// 4. store data via atomicMax`
`2262`		`- // to store col data efficiency we need to rewrite the smem blocked data [0, 1, 2, 3...] for t0`
	`2262`	`+ // to store col data efficiently we need to rewrite the smem blocked data [0, 1, 2, 3...] for t0`
`2263`	`2263`	`// into a striped arrangement: [0, 8, 16, 24, ..] for t0`
`2264`	`2264`	`__syncthreads();`
`2265`	`2265`	`BlockExchange(temp_storage.exchange).BlockedToStriped(local_col_absmax_values);`