| /cmsis-dsp-latest/Source/StatisticsFunctions/ |
| D | arm_mse_f32.c | 61 float32x4_t vecSum; in arm_mse_f32() local
64 vecSum = vdupq_n_f32(0.0f); in arm_mse_f32()
78 vecSum = vfmaq(vecSum, vecA, vecA); in arm_mse_f32()
94 vecSum = vfmaq_m(vecSum, vecA, vecA, p0); in arm_mse_f32()
97 sum = vecAddAcrossF32Mve(vecSum); in arm_mse_f32()
115 float32x4_t vecSum; in arm_mse_f32() local
119 vecSum = vdupq_n_f32(0.0f); in arm_mse_f32()
136 vecSum = vfmaq_f32(vecSum, vecA, vecA); in arm_mse_f32()
144 sum = vpadds_f32(vpadd_f32(vget_low_f32(vecSum), vget_high_f32(vecSum))); in arm_mse_f32()
146 tmp = vpadd_f32(vget_low_f32(vecSum), vget_high_f32(vecSum)); in arm_mse_f32()
|
| D | arm_accumulate_f32.c | 58 f32x4_t vecSum; in arm_accumulate_f32() local
61 vecSum = vdupq_n_f32(0.0f); in arm_accumulate_f32()
75 vecSum = vaddq_f32(vecSum, vecA); in arm_accumulate_f32()
90 vecSum = vaddq_m(vecSum,vecSum, vecA, p0); in arm_accumulate_f32()
93 sum = vecAddAcrossF32Mve(vecSum); in arm_accumulate_f32()
|
| D | arm_mse_f16.c | 61 float16x8_t vecSum; in arm_mse_f16() local
64 vecSum = vdupq_n_f16(0.0f16); in arm_mse_f16()
77 vecSum = vfmaq(vecSum, vecA, vecA); in arm_mse_f16()
93 vecSum = vfmaq_m(vecSum, vecA, vecA, p0); in arm_mse_f16()
96 sum = vecAddAcrossF16Mve(vecSum); in arm_mse_f16()
|
| /cmsis-dsp-latest/Source/BasicMathFunctions/ |
| D | arm_dot_prod_f16.c | 61 f16x8_t vecSum; in arm_dot_prod_f16() local
64 vecSum = vdupq_n_f16(0.0f); in arm_dot_prod_f16()
81 vecSum = vfmaq(vecSum, vecA, vecB); in arm_dot_prod_f16()
97 vecSum = vfmaq_m(vecSum, vecA, vecB, p0); in arm_dot_prod_f16()
100 sum = vecAddAcrossF16Mve(vecSum); in arm_dot_prod_f16()
|
| D | arm_dot_prod_f32.c | 73 f32x4_t vecSum; in arm_dot_prod_f32() local
76 vecSum = vdupq_n_f32(0.0f); in arm_dot_prod_f32()
93 vecSum = vfmaq(vecSum, vecA, vecB); in arm_dot_prod_f32()
109 vecSum = vfmaq_m(vecSum, vecA, vecB, p0); in arm_dot_prod_f32()
112 sum = vecAddAcrossF32Mve(vecSum); in arm_dot_prod_f32()
|
| /cmsis-dsp-latest/Source/TransformFunctions/ |
| D | arm_cfft_f16.c | 260 f16x8_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_f16_mve() local
277 vecSum = vaddq(vecIn0, vecIn1); in arm_cfft_radix4by2_f16_mve()
282 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_f16_mve()
473 f16x8_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_inverse_f16_mve() local
490 vecSum = vaddq(vecIn0, vecIn1); in arm_cfft_radix4by2_inverse_f16_mve()
495 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_inverse_f16_mve()
|
| D | arm_cfft_q31.c | 229 q31x4_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_q31_mve() local
245 vecSum = vhaddq(vecIn0, vecIn1); in arm_cfft_radix4by2_q31_mve()
246 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_q31_mve()
481 q31x4_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_inverse_q31_mve() local
499 vecSum = vhaddq(vecIn0, vecIn1); in arm_cfft_radix4by2_inverse_q31_mve()
500 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_inverse_q31_mve()
|
| D | arm_cfft_q15.c | 211 q15x8_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_q15_mve() local
230 vecSum = vhaddq(vecIn0, vecIn1); in arm_cfft_radix4by2_q15_mve()
231 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_q15_mve()
448 q15x8_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_inverse_q15_mve() local
467 vecSum = vhaddq(vecIn0, vecIn1); in arm_cfft_radix4by2_inverse_q15_mve()
468 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_inverse_q15_mve()
|
| D | arm_cfft_f32.c | 263 f32x4_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_f32_mve() local
280 vecSum = vecIn0 + vecIn1; in arm_cfft_radix4by2_f32_mve()
285 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_f32_mve()
476 f32x4_t vecIn0, vecIn1, vecSum, vecDiff; in arm_cfft_radix4by2_inverse_f32_mve() local
493 vecSum = vecIn0 + vecIn1; in arm_cfft_radix4by2_inverse_f32_mve()
498 vst1q(pIn0, vecSum); in arm_cfft_radix4by2_inverse_f32_mve()
|
