Skip to content
Commit 60cf00c9 authored by Nate Begeman's avatar Nate Begeman
Browse files

Handle some more real world cases of rlwimi. These don't come up that

regularly in "normal" code, but for things like software graphics, they
make a big difference.

For the following code:
unsigned short Trans16Bit(unsigned srcA,unsigned srcB,unsigned alpha)
{
	unsigned tmpA,tmpB,mixed;
	tmpA = ((srcA & 0x03E0) << 15) | (srcA & 0x7C1F);
	tmpB = ((srcB & 0x03E0) << 15) | (srcB & 0x7C1F);
	mixed = (tmpA * alpha) + (tmpB * (32 - alpha));
	return ((mixed >> 5) & 0x7C1F) | ((mixed >> 20) & 0x03E0);
}

We now generate:
_Trans16Bit:
.LBB_Trans16Bit_0:      ; entry
        andi. r2, r4, 31775
        rlwimi r2, r4, 15, 7, 11
        subfic r4, r5, 32
        mullw r2, r2, r4
        andi. r4, r3, 31775
        rlwimi r4, r3, 15, 7, 11
        mullw r3, r4, r5
        add r2, r2, r3
        srwi r3, r2, 5
        andi. r3, r3, 31775
        rlwimi r3, r2, 12, 22, 26
        blr

Instead of:
_Trans16Bit:
.LBB_Trans16Bit_0:      ; entry
        slwi r2, r4, 15
        rlwinm r2, r2, 0, 7, 11
        andi. r4, r4, 31775
        or r2, r2, r4
        subfic r4, r5, 32
        mullw r2, r2, r4
        slwi r4, r3, 15
        rlwinm r4, r4, 0, 7, 11
        andi. r3, r3, 31775
        or r3, r4, r3
        mullw r3, r3, r5
        add r2, r2, r3
        srwi r3, r2, 5
        andi. r3, r3, 31775
        srwi r2, r2, 20
        rlwimi r3, r2, 0, 22, 26
        blr

llvm-svn: 22201
parent 85c7d546
Loading
Loading
Loading
Loading
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment