// Tile size: 8x1
	// Accumulators: 0-7
	// Col regs: 8-14
	// Row regs: 15

	vbroadcastss    ymm15,  dword ptr [rcx]

    vmovaps         ymm8, [rax + 0]
	vmovaps         ymm9, [rax + 32]
	vmovaps         ymm10, [rax + 64]
	vmovaps         ymm11, [rax + 96]

    vfmadd231ps     ymm0, ymm8, ymm15
    vfmadd231ps     ymm1, ymm9, ymm15

    vmovaps         ymm12, [rax + 128]
	vmovaps         ymm13, [rax + 160]

    vfmadd231ps     ymm2, ymm10, ymm15
    vfmadd231ps     ymm3, ymm11, ymm15

    vmovaps         ymm14, [rax + 192]
	vmovaps         ymm11, [rax + 224]

    vfmadd231ps     ymm4, ymm12, ymm15
    vfmadd231ps     ymm5, ymm13, ymm15


    vfmadd231ps     ymm6, ymm14, ymm15
    vfmadd231ps     ymm7, ymm11, ymm15

    add rcx, 4
	add rax, 256