From 3cdd5e524a4c74de49e936cb5d9580d56aacfe07 Mon Sep 17 00:00:00 2001
From: Jan Wassenberg <janwas@google.com>
Date: Tue, 5 Mar 2024 23:00:09 -0800
Subject: [PATCH] Fix loop iteration in GeluMulToBF16 Also attempt to speed up
 builders (parallel)

PiperOrigin-RevId: 613092863
---
 .github/workflows/build.yml | 2 +-
 ops.h                       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index 06f4dfa..a0e9dc2 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -44,7 +44,7 @@ jobs:
         -D CMAKE_CXX_COMPILER_LAUNCHER=ccache
 
     - name: Build
-      run: cmake --build ${{ github.workspace }}/build --preset ${{ matrix.preset }} --config ${{ matrix.build_type }}
+      run: cmake --build ${{ github.workspace }}/build --preset ${{ matrix.preset }} --config ${{ matrix.build_type }} -j 4
 
     - name: Archive production artifacts
       uses: actions/upload-artifact@v4
diff --git a/ops.h b/ops.h
index 8f92d82..3725776 100644
--- a/ops.h
+++ b/ops.h
@@ -241,7 +241,7 @@ static HWY_NOINLINE HWY_MAYBE_UNUSED void GeluMulToBF16(
 
   size_t i = 0;
   if (size >= 2 * NF) {
-    for (; i < size - 2 * NF; i += 2 * NF) {
+    for (; i <= size - 2 * NF; i += 2 * NF) {
       const VF mul0 = hn::LoadU(df, mul + i);
       const VF mul1 = hn::LoadU(df, mul + i + NF);
       const VF g0 = hn::Mul(mul0, Gelu(df, hn::LoadU(df, gelu_in + i)));