Displaying 1 result from an estimated 1 matches for "r10_11".
2012 Jul 06
2
[LLVMdev] Excessive register spilling in large automatically generated functions, such as is found in FFTW
...= SUB(t2, t3);
*r2 = UNPACK2HI(t4, t5);
*r3 = UNPACK2HI(t6, t7);
t7 = MULI(t7);
t0 = ADD(t4, t6);
t2 = SUB(t4, t6);
t1 = SUB(t5, t7);
t3 = ADD(t5, t7);
*r0 = UNPACK2LO(t0, t1);
*r1 = UNPACK2LO(t2, t3);
}
void fft32(const float *in, float *out) {
__m128 r0_1,r2_3,r4_5,r6_7,r8_9,r10_11,r12_13,r14_15,r16_17,r18_19,r20_21,r22_23,r24_25,r26_27,r28_29,r30_31;
L_4_4(in+0,in+32,in+16,in+48,&r0_1,&r2_3,&r16_17,&r18_19);
L_2_2(in+8,in+40,in+56,in+24,&r4_5,&r6_7,&r20_21,&r22_23);
K_N(VLIT4(0.7071,0.7071,1,1),VLIT4(0.7071,-0.7071,0,-0),&r0_1,&...