[Mlir-commits] [mlir] e8b31fb - [mlir] fix latex formulas in the tutorial

[llvmlistbot at llvm.org]

Author: Oleksandr "Alex" Zinenko
Date: 2024-04-22T14:49:28+02:00
New Revision: e8b31fb39d9728e7505dfee7630158f14bc224de

URL: https://github.com/llvm/llvm-project/commit/e8b31fb39d9728e7505dfee7630158f14bc224de
DIFF: https://github.com/llvm/llvm-project/commit/e8b31fb39d9728e7505dfee7630158f14bc224de.diff

LOG: [mlir] fix latex formulas in the tutorial

Added: 
    

Modified: 
    mlir/docs/Tutorials/transform/ChH.md

Removed: 
    


################################################################################
diff  --git a/mlir/docs/Tutorials/transform/ChH.md b/mlir/docs/Tutorials/transform/ChH.md
index f4dae5c1b99bdb..aadfddb89393f7 100644
--- a/mlir/docs/Tutorials/transform/ChH.md
+++ b/mlir/docs/Tutorials/transform/ChH.md
@@ -583,10 +583,11 @@ LLVM IR and processed by the LLVM compiler to produce an executable or JITted.
 
 The generated code runs in ~420ms on an Intel processor with Skylake
 microarchitecture clocked at 2.0GHz. Given that the computation performs
-$5*80*100*128*(2*3*3*128 + 2) ~= 5.9 * 10^9$ floating point operations, it
-reaches ~14 GFlops. With 1 FMA unit available, the single-core performance of
-the test processor is 64 GFlops $16 * 2 * 2 * 10^9$, where 16 is the vector
-width), so only 22% of the theoretical peak is achieved.
+$`5 \cdot 80 \cdot 100 \cdot 128 \cdot (2 \cdot 3 \cdot 3 \cdot 128 + 2) \approx 5.9 * 10^9`$
+floating point operations, it reaches ~14 GFlops. With 1 FMA unit available,
+the single-core performance of the test processor is 64 GFlops
+($`16 \cdot 2 \cdot 2 \cdot 10^9`$, where 16 is the vector width), so only 
+22% of the theoretical peak is achieved.
 
 The code produced by Halide runs in ~120ms on the same processor, a 3.5x
 improvement and 77% of peak. Let us analyze the generated assembly to understand