[llvm] [llvm-exegesis] Fix snippet value scaling (PR #77226)

[Aiden Grossman via llvm-commits]

https://github.com/boomanaiden154 created https://github.com/llvm/llvm-project/pull/77226

Currently, BenchmarkRunner scales the per snippet counters by multiplying the raw counter values by the number of instructions (casted to a double) divided by the minimum number of instructions. This is incorrect for the loop repetition mode for snippets that don't fit a whole number of times into the minimum instruction count. For example, with 3 instructions in the snippet and the minimum number of instructions set to 4, the loop repetitor will execute a total of six instructions, but BenchmarkRunner will scale the raw count by 3/4 instead of 3/6=1/2. This will also be incorrect for the duplicate snippet repetitor after #77224.

This patch fixes this behavior by dividing the raw count by the ceiling of the number of repetitions divided by the instruction count.

>From 5d96e908d85a36f84cf8fd9b37517477c69e87b2 Mon Sep 17 00:00:00 2001
From: Aiden Grossman <agrossman154 at yahoo.com>
Date: Sat, 6 Jan 2024 22:43:12 -0800
Subject: [PATCH] [llvm-exegesis] Fix snippet value scaling

Currently, BenchmarkRunner scales the per snippet counters by
multiplying the raw counter values by the number of instructions (casted
to a double) divided by the minimum number of instructions. This is
incorrect for the loop repetition mode for snippets that don't fit a
whole number of times into the minimum instruction count. For example,
with 3 instructions in the snippet and the minimum number of
instructions set to 4, the loop repetitor will execute a total of six
instructions, but BenchmarkRunner will scale the raw count by 3/4
instead of 3/6=1/2. This will also be incorrect for the duplicate
snippet repetitor after #77224.

This patch fixes this behavior by dividing the raw count by the ceiling
of the number of repetitions divided by the instruction count.
---
 llvm/tools/llvm-exegesis/lib/BenchmarkRunner.cpp | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/llvm/tools/llvm-exegesis/lib/BenchmarkRunner.cpp b/llvm/tools/llvm-exegesis/lib/BenchmarkRunner.cpp
index dee7af5fd520a4..87e2b768d5e63f 100644
--- a/llvm/tools/llvm-exegesis/lib/BenchmarkRunner.cpp
+++ b/llvm/tools/llvm-exegesis/lib/BenchmarkRunner.cpp
@@ -6,6 +6,7 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include <cmath>
 #include <memory>
 #include <string>
 
@@ -615,9 +616,9 @@ std::pair<Error, Benchmark> BenchmarkRunner::runConfiguration(
     // Scale the measurements by instruction.
     BM.PerInstructionValue /= BenchmarkResult.NumRepetitions;
     // Scale the measurements by snippet.
-    BM.PerSnippetValue *=
-        static_cast<double>(BenchmarkResult.Key.Instructions.size()) /
-        BenchmarkResult.NumRepetitions;
+    BM.PerSnippetValue /=
+        std::ceil(BenchmarkResult.NumRepetitions /
+                  static_cast<double>(BenchmarkResult.Key.Instructions.size()));
   }
   BenchmarkResult.Measurements = std::move(*NewMeasurements);