Fix silk_VQ_WMat_EC_sse4_1().

During review of c95c9a048f32, I replaced a call to
 _mm_cvtepi8_epi32() with the OP_CVTEPI16_EPI32_M64() macro (note
 the 16 instead of 8).
Make a separate OP_CVTEPI8_EPI32_M32() macro and use that instead.

Thaks to Wei Zhou for the report.

2 files changed, 17 insertions, 9 deletions

diff --git a/celt/x86/x86cpu.h b/celt/x86/x86cpu.h
index 2394b05e..44b3a597 100644
--- a/celt/x86/x86cpu.h
+++ b/celt/x86/x86cpu.h
@@ -44,18 +44,26 @@
 int opus_select_arch(void);
 # endif
 
-/*gcc appears to emit MOVDQA's to load the argument of an _mm_cvtepi16_epi32()
-  when optimizations are disabled, even though the actual PMOVSXWD instruction
-  takes an m64. Unlike a normal m64 reference, these require 16-byte alignment
-  and load 16 bytes instead of 8, possibly reading out of bounds.
-
-  We can insert an explicit MOVQ using _mm_loadl_epi64(), which should have the
-  same semantics as an m64 reference in the PMOVSXWD instruction itself, but
-  gcc is not smart enough to optimize this out when optimizations ARE enabled.*/
+/*gcc appears to emit MOVDQA's to load the argument of an _mm_cvtepi8_epi32()
+  or _mm_cvtepi16_epi32() when optimizations are disabled, even though the
+  actual PMOVSXWD instruction takes an m32 or m64. Unlike a normal memory
+  reference, these require 16-byte alignment and load a full 16 bytes (instead
+  of 4 or 8), possibly reading out of bounds.
+
+  We can insert an explicit MOVD or MOVQ using _mm_cvtsi32_si128() or
+  _mm_loadl_epi64(), which should have the same semantics as an m32 or m64
+  reference in the PMOVSXWD instruction itself, but gcc is not smart enough to
+  optimize this out when optimizations ARE enabled.*/
 # if !defined(__OPTIMIZE__)
+#  define OP_CVTEPI8_EPI32_M32(x) \
+ (_mm_cvtepi8_epi32(_mm_cvtsi32_si128(*(int *)(x))))
+
 #  define OP_CVTEPI16_EPI32_M64(x) \
  (_mm_cvtepi16_epi32(_mm_loadl_epi64((__m128i *)(x))))
 # else
+#  define OP_CVTEPI8_EPI32_M32(x) \
+ (_mm_cvtepi8_epi32(*(__m128i *)(x)))
+
 #  define OP_CVTEPI16_EPI32_M64(x) \
  (_mm_cvtepi16_epi32(*(__m128i *)(x)))
 # endif
diff --git a/silk/x86/VQ_WMat_EC_sse.c b/silk/x86/VQ_WMat_EC_sse.c
index 1460cead..74d6c6d0 100644
--- a/silk/x86/VQ_WMat_EC_sse.c
+++ b/silk/x86/VQ_WMat_EC_sse.c
@@ -65,7 +65,7 @@ void silk_VQ_WMat_EC_sse4_1(
         diff_Q14[ 0 ] = in_Q14[ 0 ] - silk_LSHIFT( cb_row_Q7[ 0 ], 7 );
 
         C_tmp1 = OP_CVTEPI16_EPI32_M64( &in_Q14[ 1 ] );
-        C_tmp2 = OP_CVTEPI16_EPI32_M64( &cb_row_Q7[ 1 ] );
+        C_tmp2 = OP_CVTEPI8_EPI32_M32( &cb_row_Q7[ 1 ] );
         C_tmp2 = _mm_slli_epi32( C_tmp2, 7 );
         C_tmp1 = _mm_sub_epi32( C_tmp1, C_tmp2 );