diff --git a/src/include/cpu/rpp_cpu_common.hpp b/src/include/cpu/rpp_cpu_common.hpp
index bdf893dcf..f9d43f956 100644
--- a/src/include/cpu/rpp_cpu_common.hpp
+++ b/src/include/cpu/rpp_cpu_common.hpp
@@ -4995,10 +4995,10 @@ inline void compute_generic_bilinear_srclocs_and_interpolate(T *srcPtrChannel, R
 
     for (int c = 0; c < srcDescPtr->c; c++)
     {
-        dst[c] = (T)((*(srcPtrChannel + srcLoc[0]) * bilinearCoeffs[0]) +       // TopRow R01 Pixel * coeff0
+        dst[c] = (T)std::nearbyintf(((*(srcPtrChannel + srcLoc[0]) * bilinearCoeffs[0]) +        // TopRow R01 Pixel * coeff0
                     (*(srcPtrChannel + srcLoc[1]) * bilinearCoeffs[1]) +        // TopRow R02 Pixel * coeff1
                     (*(srcPtrChannel + srcLoc[2]) * bilinearCoeffs[2]) +        // BottomRow R01 Pixel * coeff2
-                    (*(srcPtrChannel + srcLoc[3]) * bilinearCoeffs[3]));        // BottomRow R02 Pixel * coeff3
+                    (*(srcPtrChannel + srcLoc[3]) * bilinearCoeffs[3])));        // BottomRow R02 Pixel * coeff3
         srcPtrChannel += srcDescPtr->strides.cStride;
     }
 }
diff --git a/src/include/cpu/rpp_cpu_simd.hpp b/src/include/cpu/rpp_cpu_simd.hpp
index 6378e0d8c..d11a893c1 100644
--- a/src/include/cpu/rpp_cpu_simd.hpp
+++ b/src/include/cpu/rpp_cpu_simd.hpp
@@ -2973,7 +2973,8 @@ inline void rpp_store8_u8pln1_to_u8pln1_avx(Rpp8u* dstPtr, __m256i &p)
 inline void rpp_store8_f32pln1_to_u8pln1_avx(Rpp8u* dstPtr, __m256 &p)
 {
     __m256i px1 = _mm256_permute4x64_epi64(_mm256_packus_epi32(_mm256_cvtps_epi32(p), avx_px0), _MM_SHUFFLE(3,1,2,0));
-    rpp_storeu_si64((__m128i *)(dstPtr), _mm256_packus_epi16(px1, avx_px0));
+    px1 = _mm256_packus_epi16(px1, avx_px0);
+    rpp_store8_u8pln1_to_u8pln1_avx(dstPtr, px1);
 }
 
 inline void rpp_store24_f32pln3_to_u8pln3_avx(Rpp8u* dstRPtr, Rpp8u* dstGPtr, Rpp8u* dstBPtr, __m256* p)