Why unsigned types are more efficient in arm cpu?

by

Prior to ARMv4, ARM had no native support for loading halfwords and signed bytes. To load a signed byte you had to LDRB then sign extend the value (LSL it up then ASR it back down). This is painful so char is unsigned by default.

In ARMv4 instructions were added to handle halfwords and signed values. These new instructions had to be squeezed into the available instruction space. Limits on the space available meant that they could not be made as flexible as the original instructions, which are able to do various address computations when loading the value.

So you may find that LDRSB, for example, is unable to combine a fetch from memory with an address computation whereas LDRB could. This can cost cycles. Sometimes we can rework short-heavy code to operate on pairs of ints to avoid this.

There’s more info on my site here: http://www.davespace.co.uk/arm/efficient-c-for-arm/memaccess.html

More Related Contents:

  1. How is load->store reordering possible with in-order commit?
  2. What is the difference between FIQ and IRQ interrupt system?
  3. TrustZone monitor mode and IFAR, IFSR, DFAR, DFSR
  4. Arm Neon Intrinsics vs hand assembly
  5. Explaination of ARM (especifically mobile) Peripherals Addressing and Bus architecture?
  6. Explicitly accessing banked registers on ARM
  7. what is the right way to update MMU translation table
  8. SSE _mm_movemask_epi8 equivalent method for ARM NEON
  9. qemu-system-aarch64 entering el1 when emulating a53 power up
  10. How to run code from RAM on ARM architecture
  11. What registers to save in the ARM C calling convention?
  12. Looking for an efficient integer square root algorithm for ARM Thumb2
  13. Android Studio – How Can I Make an AVD With ARM Instead of HAXM?
  14. Methods to vectorise histogram in SIMD?
  15. exit.c:(.text+0x18): undefined reference to `_exit’ when using arm-none-eabi-gcc
  16. Working of __asm__ __volatile__ (“” : : : “memory”)
  17. What is the difference between =label (equals sign) and [label] (brackets) in ARMv6 assembly?
  18. Linux kernel ARM exception stack init
  19. memory alignment within gcc structs
  20. How to create static linked shared libraries
  21. Find the physical address of exception vector table from kernel module
  22. Does hardware memory barrier make visibility of atomic operations faster in addition to providing necessary guarantees?
  23. How to install SciPy on Apple Silicon (ARM / M1)
  24. How can I do memory test on Arm architecture hardware? (something like Memtest86) [closed]
  25. ARM inline asm: exit system call with value read from memory
  26. Cross compiling static C hello world for Android using arm-linux-gnueabi-gcc
  27. How to specify an individual register as constraint in ARM GCC inline assembly?
  28. Cross Compile OpenSSH for ARM
  29. Converting Int to Float or Float to Int using Bitwise operations (software floating point)
  30. Handling ARM TrustZones

Leave a Comment