diff --git a/include/libyuv/row.h b/include/libyuv/row.h
index 4f5e582d4..945b32458 100644
--- a/include/libyuv/row.h
+++ b/include/libyuv/row.h
@@ -559,6 +559,7 @@ extern "C" {
 #define HAS_I212TOAR30ROW_SVE2
 #define HAS_I212TOARGBROW_SVE2
 #define HAS_I400TOARGBROW_SVE2
+#define HAS_I410ALPHATOARGBROW_SVE2
 #define HAS_I410TOARGBROW_SVE2
 #define HAS_I422ALPHATOARGBROW_SVE2
 #define HAS_I422TOARGB1555ROW_SVE2
@@ -1083,6 +1084,13 @@ void I410AlphaToARGBRow_NEON(const uint16_t* src_y,
                              uint8_t* rgb_buf,
                              const struct YuvConstants* yuvconstants,
                              int width);
+void I410AlphaToARGBRow_SVE2(const uint16_t* src_y,
+                             const uint16_t* src_u,
+                             const uint16_t* src_v,
+                             const uint16_t* src_a,
+                             uint8_t* rgb_buf,
+                             const struct YuvConstants* yuvconstants,
+                             int width);
 void I444ToARGBRow_NEON(const uint8_t* src_y,
                         const uint8_t* src_u,
                         const uint8_t* src_v,
diff --git a/source/convert_argb.cc b/source/convert_argb.cc
index dfcd4a7ce..599dcc313 100644
--- a/source/convert_argb.cc
+++ b/source/convert_argb.cc
@@ -2986,6 +2986,11 @@ int I410AlphaToARGBMatrix(const uint16_t* src_y,
     }
   }
 #endif
+#if defined(HAS_I410ALPHATOARGBROW_SVE2)
+  if (TestCpuFlag(kCpuHasSVE2)) {
+    I410AlphaToARGBRow = I410AlphaToARGBRow_SVE2;
+  }
+#endif
 #if defined(HAS_I410ALPHATOARGBROW_SSSE3)
   if (TestCpuFlag(kCpuHasSSSE3)) {
     I410AlphaToARGBRow = I410AlphaToARGBRow_Any_SSSE3;
@@ -7799,6 +7804,11 @@ static int I010AlphaToARGBMatrixBilinear(
     }
   }
 #endif
+#if defined(HAS_I410ALPHATOARGBROW_SVE2)
+  if (TestCpuFlag(kCpuHasSVE2)) {
+    I410AlphaToARGBRow = I410AlphaToARGBRow_SVE2;
+  }
+#endif
 #if defined(HAS_I410ALPHATOARGBROW_SSSE3)
   if (TestCpuFlag(kCpuHasSSSE3)) {
     I410AlphaToARGBRow = I410AlphaToARGBRow_Any_SSSE3;
@@ -7975,6 +7985,11 @@ static int I210AlphaToARGBMatrixLinear(const uint16_t* src_y,
     }
   }
 #endif
+#if defined(HAS_I410ALPHATOARGBROW_SVE2)
+  if (TestCpuFlag(kCpuHasSVE2)) {
+    I410AlphaToARGBRow = I410AlphaToARGBRow_SVE2;
+  }
+#endif
 #if defined(HAS_I410ALPHATOARGBROW_SSSE3)
   if (TestCpuFlag(kCpuHasSSSE3)) {
     I410AlphaToARGBRow = I410AlphaToARGBRow_Any_SSSE3;
diff --git a/source/row_sve.cc b/source/row_sve.cc
index dac1d753d..f91e2175c 100644
--- a/source/row_sve.cc
+++ b/source/row_sve.cc
@@ -2183,6 +2183,58 @@ void I410ToARGBRow_SVE2(const uint16_t* src_y,
       : "cc", "memory", YUVTORGB_SVE_REGS);
 }
 
+void I410AlphaToARGBRow_SVE2(const uint16_t* src_y,
+                             const uint16_t* src_u,
+                             const uint16_t* src_v,
+                             const uint16_t* src_a,
+                             uint8_t* dst_argb,
+                             const struct YuvConstants* yuvconstants,
+                             int width) {
+  uint64_t vl;
+  asm("cnth %0" : "=r"(vl));
+  int width_last_y = width & (vl - 1);
+  width_last_y = width_last_y == 0 ? vl : width_last_y;
+  asm volatile(
+      "ptrue    p0.b                                    \n" YUVTORGB_SVE_SETUP
+      "cmp      %w[width], %w[vl]                       \n"
+      "subs     %w[width], %w[width], %w[vl]            \n"
+      "b.lt     2f                                      \n"
+
+      // Run bulk of computation with an all-true predicate to avoid predicate
+      // generation overhead.
+      "ptrue    p1.h                                    \n"
+      "1:                                               \n" READI410_SVE
+      "ld1h     {z19.h}, p1/z, [%[src_a]]               \n" I4XXTORGB_SVE
+      "incb     %[src_a]                                \n" RGBATOARGB8_SVE
+      "subs     %w[width], %w[width], %w[vl]            \n"
+      "st2h     {z16.h, z17.h}, p1, [%[dst_argb]]       \n"
+      "add      %[dst_argb], %[dst_argb], %[vl], lsl #2 \n"
+      "b.ge     1b                                      \n"
+
+      "2:                                               \n"
+      "adds     %w[width], %w[width], %w[vl]            \n"
+      "b.eq     99f                                     \n"
+
+      // Calculate a predicate for the final iteration to deal with the tail.
+      "whilelt  p1.h, wzr, %w[width_last_y]             \n" READI410_SVE
+      "ld1h     {z19.h}, p1/z, [%[src_a]]               \n"  //
+      I4XXTORGB_SVE RGBATOARGB8_SVE
+      "st2h     {z16.h, z17.h}, p1, [%[dst_argb]]       \n"
+
+      "99:                                              \n"
+      : [src_y] "+r"(src_y),                                // %[src_y]
+        [src_u] "+r"(src_u),                                // %[src_u]
+        [src_v] "+r"(src_v),                                // %[src_v]
+        [src_a] "+r"(src_a),                                // %[src_a]
+        [dst_argb] "+r"(dst_argb),                          // %[dst_argb]
+        [width] "+r"(width)                                 // %[width]
+      : [vl] "r"(vl),                                       // %[vl]
+        [kUVCoeff] "r"(&yuvconstants->kUVCoeff),            // %[kUVCoeff]
+        [kRGBCoeffBias] "r"(&yuvconstants->kRGBCoeffBias),  // %[kRGBCoeffBias]
+        [width_last_y] "r"(width_last_y)                    // %[width_last_y]
+      : "cc", "memory", YUVTORGB_SVE_REGS);
+}
+
 void P410ToARGBRow_SVE2(const uint16_t* src_y,
                         const uint16_t* src_uv,
                         uint8_t* dst_argb,