Skip to content

R
riscv-gcc-1
Commit ca449d26 by Jiong Wang Committed by Jiong Wang
Options

[AArch64, testsuite] Fix vmul_elem_1.c on big-endian 

gcc/testsuite/
        * gcc.target/aarch64/simd/vmul_elem_1.c: Force result variables to be
        kept in memory.

From-SVN: r236762
parent 9de98f89
Showing with 71 additions and 44 deletions
gcc/testsuite/ChangeLog
2016-05-26 Jiong Wang <jiong.wang@arm.com>
* gcc.target/aarch64/simd/vmul_elem_1.c: Force result variables to be
kept in memory.
2016-05-25 Jeff Law <law@redhat.com> 2016-05-25 Jeff Law <law@redhat.com>
PR tree-optimization/71272 PR tree-optimization/71272
......
gcc/testsuite/gcc.target/aarch64/simd/vmul_elem_1.c
...@@ -142,13 +142,15 @@ check_v2sf (float32_t elemA, float32_t elemB) ...@@ -142,13 +142,15 @@ check_v2sf (float32_t elemA, float32_t elemB)
int32_t indx; int32_t indx;
const float32_t vec32x2_buf[2] = {A, B}; const float32_t vec32x2_buf[2] = {A, B};
float32x2_t vec32x2_src = vld1_f32 (vec32x2_buf); float32x2_t vec32x2_src = vld1_f32 (vec32x2_buf);
float32x2_t vec32x2_res = vmul_n_f32 (vec32x2_src, elemA); float32_t vec32x2_res[2];
vst1_f32 (vec32x2_res, vmul_n_f32 (vec32x2_src, elemA));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (* (uint32_t *) &vec32x2_res[indx] != * (uint32_t *) &expected2_1[indx]) if (* (uint32_t *) &vec32x2_res[indx] != * (uint32_t *) &expected2_1[indx])
abort (); abort ();
vec32x2_res = vmul_n_f32 (vec32x2_src, elemB); vst1_f32 (vec32x2_res, vmul_n_f32 (vec32x2_src, elemB));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (* (uint32_t *) &vec32x2_res[indx] != * (uint32_t *) &expected2_2[indx]) if (* (uint32_t *) &vec32x2_res[indx] != * (uint32_t *) &expected2_2[indx])
...@@ -163,25 +165,27 @@ check_v4sf (float32_t elemA, float32_t elemB, float32_t elemC, float32_t elemD) ...@@ -163,25 +165,27 @@ check_v4sf (float32_t elemA, float32_t elemB, float32_t elemC, float32_t elemD)
int32_t indx; int32_t indx;
const float32_t vec32x4_buf[4] = {A, B, C, D}; const float32_t vec32x4_buf[4] = {A, B, C, D};
float32x4_t vec32x4_src = vld1q_f32 (vec32x4_buf); float32x4_t vec32x4_src = vld1q_f32 (vec32x4_buf);
float32x4_t vec32x4_res = vmulq_n_f32 (vec32x4_src, elemA); float32_t vec32x4_res[4];
vst1q_f32 (vec32x4_res, vmulq_n_f32 (vec32x4_src, elemA));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_1[indx]) if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_1[indx])
abort (); abort ();
vec32x4_res = vmulq_n_f32 (vec32x4_src, elemB); vst1q_f32 (vec32x4_res, vmulq_n_f32 (vec32x4_src, elemB));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_2[indx]) if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_2[indx])
abort (); abort ();
vec32x4_res = vmulq_n_f32 (vec32x4_src, elemC); vst1q_f32 (vec32x4_res, vmulq_n_f32 (vec32x4_src, elemC));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_3[indx]) if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_3[indx])
abort (); abort ();
vec32x4_res = vmulq_n_f32 (vec32x4_src, elemD); vst1q_f32 (vec32x4_res, vmulq_n_f32 (vec32x4_src, elemD));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_4[indx]) if (* (uint32_t *) &vec32x4_res[indx] != * (uint32_t *) &expected4_4[indx])
...@@ -196,13 +200,15 @@ check_v2df (float64_t elemdC, float64_t elemdD) ...@@ -196,13 +200,15 @@ check_v2df (float64_t elemdC, float64_t elemdD)
int32_t indx; int32_t indx;
const float64_t vec64x2_buf[2] = {AD, BD}; const float64_t vec64x2_buf[2] = {AD, BD};
float64x2_t vec64x2_src = vld1q_f64 (vec64x2_buf); float64x2_t vec64x2_src = vld1q_f64 (vec64x2_buf);
float64x2_t vec64x2_res = vmulq_n_f64 (vec64x2_src, elemdC); float64_t vec64x2_res[2];
vst1q_f64 (vec64x2_res, vmulq_n_f64 (vec64x2_src, elemdC));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (* (uint64_t *) &vec64x2_res[indx] != * (uint64_t *) &expectedd2_1[indx]) if (* (uint64_t *) &vec64x2_res[indx] != * (uint64_t *) &expectedd2_1[indx])
abort (); abort ();
vec64x2_res = vmulq_n_f64 (vec64x2_src, elemdD); vst1q_f64 (vec64x2_res, vmulq_n_f64 (vec64x2_src, elemdD));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (* (uint64_t *) &vec64x2_res[indx] != * (uint64_t *) &expectedd2_2[indx]) if (* (uint64_t *) &vec64x2_res[indx] != * (uint64_t *) &expectedd2_2[indx])
...@@ -217,13 +223,15 @@ check_v2si (int32_t elemsA, int32_t elemsB) ...@@ -217,13 +223,15 @@ check_v2si (int32_t elemsA, int32_t elemsB)
int32_t indx; int32_t indx;
const int32_t vecs32x2_buf[2] = {AS, BS}; const int32_t vecs32x2_buf[2] = {AS, BS};
int32x2_t vecs32x2_src = vld1_s32 (vecs32x2_buf); int32x2_t vecs32x2_src = vld1_s32 (vecs32x2_buf);
int32x2_t vecs32x2_res = vmul_n_s32 (vecs32x2_src, elemsA); int32_t vecs32x2_res[2];
vst1_s32 (vecs32x2_res, vmul_n_s32 (vecs32x2_src, elemsA));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (vecs32x2_res[indx] != expecteds2_1[indx]) if (vecs32x2_res[indx] != expecteds2_1[indx])
abort (); abort ();
vecs32x2_res = vmul_n_s32 (vecs32x2_src, elemsB); vst1_s32 (vecs32x2_res, vmul_n_s32 (vecs32x2_src, elemsB));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (vecs32x2_res[indx] != expecteds2_2[indx]) if (vecs32x2_res[indx] != expecteds2_2[indx])
...@@ -236,13 +244,15 @@ check_v2si_unsigned (uint32_t elemusA, uint32_t elemusB) ...@@ -236,13 +244,15 @@ check_v2si_unsigned (uint32_t elemusA, uint32_t elemusB)
int indx; int indx;
const uint32_t vecus32x2_buf[2] = {AUS, BUS}; const uint32_t vecus32x2_buf[2] = {AUS, BUS};
uint32x2_t vecus32x2_src = vld1_u32 (vecus32x2_buf); uint32x2_t vecus32x2_src = vld1_u32 (vecus32x2_buf);
uint32x2_t vecus32x2_res = vmul_n_u32 (vecus32x2_src, elemusA); uint32_t vecus32x2_res[2];
vst1_u32 (vecus32x2_res, vmul_n_u32 (vecus32x2_src, elemusA));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (vecus32x2_res[indx] != expectedus2_1[indx]) if (vecus32x2_res[indx] != expectedus2_1[indx])
abort (); abort ();
vecus32x2_res = vmul_n_u32 (vecus32x2_src, elemusB); vst1_u32 (vecus32x2_res, vmul_n_u32 (vecus32x2_src, elemusB));
for (indx = 0; indx < 2; indx++) for (indx = 0; indx < 2; indx++)
if (vecus32x2_res[indx] != expectedus2_2[indx]) if (vecus32x2_res[indx] != expectedus2_2[indx])
...@@ -257,25 +267,27 @@ check_v4si (int32_t elemsA, int32_t elemsB, int32_t elemsC, int32_t elemsD) ...@@ -257,25 +267,27 @@ check_v4si (int32_t elemsA, int32_t elemsB, int32_t elemsC, int32_t elemsD)
int32_t indx; int32_t indx;
const int32_t vecs32x4_buf[4] = {AS, BS, CS, DS}; const int32_t vecs32x4_buf[4] = {AS, BS, CS, DS};
int32x4_t vecs32x4_src = vld1q_s32 (vecs32x4_buf); int32x4_t vecs32x4_src = vld1q_s32 (vecs32x4_buf);
int32x4_t vecs32x4_res = vmulq_n_s32 (vecs32x4_src, elemsA); int32_t vecs32x4_res[4];
vst1q_s32 (vecs32x4_res, vmulq_n_s32 (vecs32x4_src, elemsA));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecs32x4_res[indx] != expecteds4_1[indx]) if (vecs32x4_res[indx] != expecteds4_1[indx])
abort (); abort ();
vecs32x4_res = vmulq_n_s32 (vecs32x4_src, elemsB); vst1q_s32 (vecs32x4_res, vmulq_n_s32 (vecs32x4_src, elemsB));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecs32x4_res[indx] != expecteds4_2[indx]) if (vecs32x4_res[indx] != expecteds4_2[indx])
abort (); abort ();
vecs32x4_res = vmulq_n_s32 (vecs32x4_src, elemsC); vst1q_s32 (vecs32x4_res, vmulq_n_s32 (vecs32x4_src, elemsC));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecs32x4_res[indx] != expecteds4_3[indx]) if (vecs32x4_res[indx] != expecteds4_3[indx])
abort (); abort ();
vecs32x4_res = vmulq_n_s32 (vecs32x4_src, elemsD); vst1q_s32 (vecs32x4_res, vmulq_n_s32 (vecs32x4_src, elemsD));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecs32x4_res[indx] != expecteds4_4[indx]) if (vecs32x4_res[indx] != expecteds4_4[indx])
...@@ -289,25 +301,27 @@ check_v4si_unsigned (uint32_t elemusA, uint32_t elemusB, uint32_t elemusC, ...@@ -289,25 +301,27 @@ check_v4si_unsigned (uint32_t elemusA, uint32_t elemusB, uint32_t elemusC,
int indx; int indx;
const uint32_t vecus32x4_buf[4] = {AUS, BUS, CUS, DUS}; const uint32_t vecus32x4_buf[4] = {AUS, BUS, CUS, DUS};
uint32x4_t vecus32x4_src = vld1q_u32 (vecus32x4_buf); uint32x4_t vecus32x4_src = vld1q_u32 (vecus32x4_buf);
uint32x4_t vecus32x4_res = vmulq_n_u32 (vecus32x4_src, elemusA); uint32_t vecus32x4_res[4];
vst1q_u32 (vecus32x4_res, vmulq_n_u32 (vecus32x4_src, elemusA));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecus32x4_res[indx] != expectedus4_1[indx]) if (vecus32x4_res[indx] != expectedus4_1[indx])
abort (); abort ();
vecus32x4_res = vmulq_n_u32 (vecus32x4_src, elemusB); vst1q_u32 (vecus32x4_res, vmulq_n_u32 (vecus32x4_src, elemusB));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecus32x4_res[indx] != expectedus4_2[indx]) if (vecus32x4_res[indx] != expectedus4_2[indx])
abort (); abort ();
vecus32x4_res = vmulq_n_u32 (vecus32x4_src, elemusC); vst1q_u32 (vecus32x4_res, vmulq_n_u32 (vecus32x4_src, elemusC));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecus32x4_res[indx] != expectedus4_3[indx]) if (vecus32x4_res[indx] != expectedus4_3[indx])
abort (); abort ();
vecus32x4_res = vmulq_n_u32 (vecus32x4_src, elemusD); vst1q_u32 (vecus32x4_res, vmulq_n_u32 (vecus32x4_src, elemusD));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecus32x4_res[indx] != expectedus4_4[indx]) if (vecus32x4_res[indx] != expectedus4_4[indx])
...@@ -323,25 +337,27 @@ check_v4hi (int16_t elemhA, int16_t elemhB, int16_t elemhC, int16_t elemhD) ...@@ -323,25 +337,27 @@ check_v4hi (int16_t elemhA, int16_t elemhB, int16_t elemhC, int16_t elemhD)
int32_t indx; int32_t indx;
const int16_t vech16x4_buf[4] = {AH, BH, CH, DH}; const int16_t vech16x4_buf[4] = {AH, BH, CH, DH};
int16x4_t vech16x4_src = vld1_s16 (vech16x4_buf); int16x4_t vech16x4_src = vld1_s16 (vech16x4_buf);
int16x4_t vech16x4_res = vmul_n_s16 (vech16x4_src, elemhA); int16_t vech16x4_res[4];
vst1_s16 (vech16x4_res, vmul_n_s16 (vech16x4_src, elemhA));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vech16x4_res[indx] != expectedh4_1[indx]) if (vech16x4_res[indx] != expectedh4_1[indx])
abort (); abort ();
vech16x4_res = vmul_n_s16 (vech16x4_src, elemhB); vst1_s16 (vech16x4_res, vmul_n_s16 (vech16x4_src, elemhB));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vech16x4_res[indx] != expectedh4_2[indx]) if (vech16x4_res[indx] != expectedh4_2[indx])
abort (); abort ();
vech16x4_res = vmul_n_s16 (vech16x4_src, elemhC); vst1_s16 (vech16x4_res, vmul_n_s16 (vech16x4_src, elemhC));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vech16x4_res[indx] != expectedh4_3[indx]) if (vech16x4_res[indx] != expectedh4_3[indx])
abort (); abort ();
vech16x4_res = vmul_n_s16 (vech16x4_src, elemhD); vst1_s16 (vech16x4_res, vmul_n_s16 (vech16x4_src, elemhD));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vech16x4_res[indx] != expectedh4_4[indx]) if (vech16x4_res[indx] != expectedh4_4[indx])
...@@ -355,25 +371,27 @@ check_v4hi_unsigned (uint16_t elemuhA, uint16_t elemuhB, uint16_t elemuhC, ...@@ -355,25 +371,27 @@ check_v4hi_unsigned (uint16_t elemuhA, uint16_t elemuhB, uint16_t elemuhC,
int indx; int indx;
const uint16_t vecuh16x4_buf[4] = {AUH, BUH, CUH, DUH}; const uint16_t vecuh16x4_buf[4] = {AUH, BUH, CUH, DUH};
uint16x4_t vecuh16x4_src = vld1_u16 (vecuh16x4_buf); uint16x4_t vecuh16x4_src = vld1_u16 (vecuh16x4_buf);
uint16x4_t vecuh16x4_res = vmul_n_u16 (vecuh16x4_src, elemuhA); uint16_t vecuh16x4_res[4];
vst1_u16 (vecuh16x4_res, vmul_n_u16 (vecuh16x4_src, elemuhA));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecuh16x4_res[indx] != expecteduh4_1[indx]) if (vecuh16x4_res[indx] != expecteduh4_1[indx])
abort (); abort ();
vecuh16x4_res = vmul_n_u16 (vecuh16x4_src, elemuhB); vst1_u16 (vecuh16x4_res, vmul_n_u16 (vecuh16x4_src, elemuhB));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecuh16x4_res[indx] != expecteduh4_2[indx]) if (vecuh16x4_res[indx] != expecteduh4_2[indx])
abort (); abort ();
vecuh16x4_res = vmul_n_u16 (vecuh16x4_src, elemuhC); vst1_u16 (vecuh16x4_res, vmul_n_u16 (vecuh16x4_src, elemuhC));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecuh16x4_res[indx] != expecteduh4_3[indx]) if (vecuh16x4_res[indx] != expecteduh4_3[indx])
abort (); abort ();
vecuh16x4_res = vmul_n_u16 (vecuh16x4_src, elemuhD); vst1_u16 (vecuh16x4_res, vmul_n_u16 (vecuh16x4_src, elemuhD));
for (indx = 0; indx < 4; indx++) for (indx = 0; indx < 4; indx++)
if (vecuh16x4_res[indx] != expecteduh4_4[indx]) if (vecuh16x4_res[indx] != expecteduh4_4[indx])
...@@ -389,49 +407,51 @@ check_v8hi (int16_t elemhA, int16_t elemhB, int16_t elemhC, int16_t elemhD, ...@@ -389,49 +407,51 @@ check_v8hi (int16_t elemhA, int16_t elemhB, int16_t elemhC, int16_t elemhD,
int32_t indx; int32_t indx;
const int16_t vech16x8_buf[8] = {AH, BH, CH, DH, EH, FH, GH, HH}; const int16_t vech16x8_buf[8] = {AH, BH, CH, DH, EH, FH, GH, HH};
int16x8_t vech16x8_src = vld1q_s16 (vech16x8_buf); int16x8_t vech16x8_src = vld1q_s16 (vech16x8_buf);
int16x8_t vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhA); int16_t vech16x8_res[8];
vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhA));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_1[indx]) if (vech16x8_res[indx] != expectedh8_1[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhB); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhB));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_2[indx]) if (vech16x8_res[indx] != expectedh8_2[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhC); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhC));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_3[indx]) if (vech16x8_res[indx] != expectedh8_3[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhD); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhD));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_4[indx]) if (vech16x8_res[indx] != expectedh8_4[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhE); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhE));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_5[indx]) if (vech16x8_res[indx] != expectedh8_5[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhF); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhF));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_6[indx]) if (vech16x8_res[indx] != expectedh8_6[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhG); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhG));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_7[indx]) if (vech16x8_res[indx] != expectedh8_7[indx])
abort (); abort ();
vech16x8_res = vmulq_n_s16 (vech16x8_src, elemhH); vst1q_s16 (vech16x8_res, vmulq_n_s16 (vech16x8_src, elemhH));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vech16x8_res[indx] != expectedh8_8[indx]) if (vech16x8_res[indx] != expectedh8_8[indx])
...@@ -446,49 +466,51 @@ check_v8hi_unsigned (uint16_t elemuhA, uint16_t elemuhB, uint16_t elemuhC, ...@@ -446,49 +466,51 @@ check_v8hi_unsigned (uint16_t elemuhA, uint16_t elemuhB, uint16_t elemuhC,
int indx; int indx;
const uint16_t vecuh16x8_buf[8] = {AUH, BUH, CUH, DUH, EUH, FUH, GUH, HUH}; const uint16_t vecuh16x8_buf[8] = {AUH, BUH, CUH, DUH, EUH, FUH, GUH, HUH};
uint16x8_t vecuh16x8_src = vld1q_u16 (vecuh16x8_buf); uint16x8_t vecuh16x8_src = vld1q_u16 (vecuh16x8_buf);
uint16x8_t vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhA); uint16_t vecuh16x8_res[8];
vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhA));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_1[indx]) if (vecuh16x8_res[indx] != expecteduh8_1[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhB); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhB));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_2[indx]) if (vecuh16x8_res[indx] != expecteduh8_2[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhC); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhC));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_3[indx]) if (vecuh16x8_res[indx] != expecteduh8_3[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhD); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhD));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_4[indx]) if (vecuh16x8_res[indx] != expecteduh8_4[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhE); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhE));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_5[indx]) if (vecuh16x8_res[indx] != expecteduh8_5[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhF); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhF));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_6[indx]) if (vecuh16x8_res[indx] != expecteduh8_6[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhG); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhG));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_7[indx]) if (vecuh16x8_res[indx] != expecteduh8_7[indx])
abort (); abort ();
vecuh16x8_res = vmulq_n_u16 (vecuh16x8_src, elemuhH); vst1q_u16 (vecuh16x8_res, vmulq_n_u16 (vecuh16x8_src, elemuhH));
for (indx = 0; indx < 8; indx++) for (indx = 0; indx < 8; indx++)
if (vecuh16x8_res[indx] != expecteduh8_8[indx]) if (vecuh16x8_res[indx] != expecteduh8_8[indx])
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment