diff --git a/CREDITS b/CREDITS
index 43c7b3ed5..bb2b3798f 100644
--- a/CREDITS
+++ b/CREDITS
@@ -23,6 +23,7 @@ but many others have contributed code and feedback, including
   Dilyn Corner             @dilyn-corner
   Mat Cross                @matcross           (NAG)
                            @decandia50
+  Daniël de Kok            @danieldk           (Explosion)
   Kay Dewhurst             @jkd2016            (Max Planck Institute, Halle, Germany)
   Jeff Diamond                                 (Oracle)
   Johannes Dieterich       @iotamudelta
diff --git a/kernels/haswell/3/sup/s6x16/bli_gemmsup_rv_haswell_asm_sMx2.c b/kernels/haswell/3/sup/s6x16/bli_gemmsup_rv_haswell_asm_sMx2.c
index 53a70d15f..efb336395 100644
--- a/kernels/haswell/3/sup/s6x16/bli_gemmsup_rv_haswell_asm_sMx2.c
+++ b/kernels/haswell/3/sup/s6x16/bli_gemmsup_rv_haswell_asm_sMx2.c
@@ -389,32 +389,38 @@ void bli_sgemmsup_rv_haswell_asm_6x2
 	label(.SROWSTORED)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm6)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm6)
 	vmovsd(xmm6, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm8)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm8)
 	vmovsd(xmm8, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm10)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm10)
 	vmovsd(xmm10, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm12)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm12)
 	vmovsd(xmm12, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm14)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm14)
 	vmovsd(xmm14, mem(rcx, 0*32))
 	//add(rdi, rcx)
 
@@ -848,27 +854,32 @@ void bli_sgemmsup_rv_haswell_asm_5x2
 	label(.SROWSTORED)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm6)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm6)
 	vmovsd(xmm6, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm8)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm8)
 	vmovsd(xmm8, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm10)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm10)
 	vmovsd(xmm10, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm12)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm12)
 	vmovsd(xmm12, mem(rcx, 0*32))
 	//add(rdi, rcx)
 
@@ -1288,22 +1299,26 @@ void bli_sgemmsup_rv_haswell_asm_4x2
 	label(.SROWSTORED)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm6)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm6)
 	vmovsd(xmm6, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm8)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm8)
 	vmovsd(xmm8, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm10)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm10)
 	vmovsd(xmm10, mem(rcx, 0*32))
 	//add(rdi, rcx)
 
@@ -1683,17 +1698,20 @@ void bli_sgemmsup_rv_haswell_asm_3x2
 	label(.SROWSTORED)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm6)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm6)
 	vmovsd(xmm6, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm8)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm8)
 	vmovsd(xmm8, mem(rcx, 0*32))
 	//add(rdi, rcx)
 
@@ -2066,12 +2084,14 @@ void bli_sgemmsup_rv_haswell_asm_2x2
 	label(.SROWSTORED)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	add(rdi, rcx)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm6)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm6)
 	vmovsd(xmm6, mem(rcx, 0*32))
 	//add(rdi, rcx)
 
@@ -2404,7 +2424,8 @@ void bli_sgemmsup_rv_haswell_asm_1x2
 	label(.SROWSTORED)
 
 
-	vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)
+	vmovsd(mem(rcx), xmm0)
+	vfmadd231ps(xmm0, xmm3, xmm4)
 	vmovsd(xmm4, mem(rcx, 0*32))
 	//add(rdi, rcx)