high/low parts VPERM2I128 $0x20, Y2, Y0, Y4 VPERM2I128 $0x31, Y2, Y0, Y5 VPERM2I128 $0x20, Y3, Y1, Y6 VPERM2I128 $0x31, Y3, Y1, Y7 LEAQ K256<>+0(SB), BP avx2_last_block_enter: ADDQ $0x40, DI MOVQ DI, 520(SP) XORQ SI, SI avx2_loop1: // Do 4 rounds and scheduling VPADDD (BP)(SI*1), Y4, Y9 VMOVDQU Y9, (SP)(SI*1) MOVL AX, DI RORXL $0x19, DX, R13 RORXL $0x0b, DX, R14 ADDL (SP)(SI*1), R11 ORL CX, DI VPALIGNR $0x04, Y6, Y7, Y0 MOVL R9, R15 RORXL $0x0d, AX, R12 XORL R14, R13 XORL R10, R15 VPADDD Y4, Y0, Y0 RORXL...

	// This benchmark models a situation where spinning in the mutex should be
	// profitable. To achieve this we create a goroutine per-proc.
	// These goroutines access considerable amount of local data so that
	// unnecessary rescheduling is penalized by cache misses.
	m := NewDRWMutex(ds, "")
	var acc0, acc1 uint64
	b.RunParallel(func(pb *testing.PB) {
		var data [16 << 10]uint64
		for i := 0; pb.Next(); i++ {
			m.Lock(id, source)