diff --git a/CREDITS b/CREDITS
index d68bcca01..fd0bcb5b3 100644
--- a/CREDITS
+++ b/CREDITS
@@ -46,6 +46,7 @@ but many others have contributed code and feedback, including
   Matthew Honnibal         @honnibal
   Stefan Husmann           @stefanhusmann
   Francisco Igual          @figual             (Universidad Complutense de Madrid)
+  Madeesh Kannan           @shadeMe
   Tony Kelman              @tkelman
   Lee Killough             @leekillough        (Cray)
   Mike Kistler             @mkistler           (IBM, Austin Research Laboratory)
diff --git a/kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_s6x16m.c b/kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_s6x16m.c
index 426e5157e..877e636b8 100644
--- a/kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_s6x16m.c
+++ b/kernels/haswell/3/sup/bli_gemmsup_rv_haswell_asm_s6x16m.c
@@ -4475,34 +4475,39 @@ void bli_sgemmsup_rv_haswell_asm_6x2m
 
 	
 	label(.SROWSTORED)
-	
-	
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+
+	vmovsd(mem(rcx, 0*32), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	add(rdi, rcx)
-	
-	
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm6)
+
+
+	vmovsd(mem(rcx, 0*32), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm6)
 	vmovsd(xmm6, mem(rcx, 0*32))
 	add(rdi, rcx)
-	
-	
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm8)
+
+
+	vmovsd(mem(rcx, 0*32), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm8)
 	vmovsd(xmm8, mem(rcx, 0*32))
 	add(rdi, rcx)
-	
-	
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm10)
+
+
+	vmovsd(mem(rcx, 0*32), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm10)
 	vmovsd(xmm10, mem(rcx, 0*32))
 	add(rdi, rcx)
-	
-	
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm12)
+
+
+	vmovsd(mem(rcx, 0*32), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm12)
 	vmovsd(xmm12, mem(rcx, 0*32))
 	add(rdi, rcx)
-	
-	
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm14)
+
+
+	vmovsd(mem(rcx, 0*32), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm14)
 	vmovsd(xmm14, mem(rcx, 0*32))
 	//add(rdi, rcx)