SYCL: Reduce most of the compiler warnings (#10748)
* Try to reduce some unused and typecast warnings * Reduce compiler warnings step 2 * add a newline at the end of the file * Initialize nreduce as size_t * [SYCL] Remove pragma directives from mmq.cpp * SYCL: mmq add condition to prevent blocks_per_tile_x_row variable from becoming 0 * SYCL softmax: Initialize nreduce as size_t * ggml-sycl.cpp: fix some trailing whitespaces * SYCL: remove the unused variables instead of commenting it out * SYCL poo2d kernel: set NAN for invalid pooling op * SYCL gemm.hpp: remove pragma directives * SYCL gemm.hpp: use const cast to properly support dnnl::memory * SYCL: wkv6 remove a comment * SYCL: clean comments step 2 * SYCL: clean comments and variables step 3 * SYCL: Use GGML_UNUSED for unused variables * SYCL: remove extra empty lines and a comment * Remove TODO * cleanup spaces * add a stdout for unsupported op * use sycl printf over fprintf * remove prints for CI * SYCL ggml-sycl: pool2D use sycl::nan and remove if-else block --------- Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
This commit is contained in:
Akarshan Biswas
GitHub
parent
d583cd03f6
commit
83ed24a97b
17 changed files with 205 additions and 187 deletions
|
|
@ -237,7 +237,7 @@ void upscale_f32(const float *x, float *dst, const int nb00, const int nb01,
|
|||
int i02 = i12 / sf2;
|
||||
int i03 = i13 / sf3;
|
||||
|
||||
dst[index] = *(float *)((char *)x + i03 * nb03 + i02 * nb02 + i01 * nb01 + i00 * nb00);
|
||||
dst[index] = *(const float *)((const char *)x + i03 * nb03 + i02 * nb02 + i01 * nb01 + i00 * nb00);
|
||||
}
|
||||
|
||||
void pad_f32(const float *x, float *dst, const int ne0, const int ne00, const int ne01, const int ne02,
|
||||
|
|
@ -251,8 +251,7 @@ void pad_f32(const float *x, float *dst, const int ne0, const int ne00, const i
|
|||
// operation
|
||||
int offset_dst = nidx + item_ct1.get_group(1) * ne0 +
|
||||
item_ct1.get_group(0) * ne0 * item_ct1.get_group_range(1);
|
||||
if (nidx < ne00 && item_ct1.get_group(1) < ne01 &&
|
||||
item_ct1.get_group(0) < ne02) {
|
||||
if (nidx < ne00 && item_ct1.get_group(1) < (size_t) ne01 && item_ct1.get_group(0) < (size_t) ne02) {
|
||||
int offset_src = nidx + item_ct1.get_group(1) * ne00 +
|
||||
item_ct1.get_group(0) * ne00 * ne01;
|
||||
dst[offset_dst] = x[offset_src];
|
||||
|
|
@ -520,9 +519,10 @@ inline void ggml_sycl_op_silu(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
silu_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_gelu(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
@ -535,9 +535,10 @@ inline void ggml_sycl_op_gelu(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
gelu_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
inline void ggml_sycl_op_gelu_quick(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
const ggml_tensor *src1, ggml_tensor *dst,
|
||||
|
|
@ -550,9 +551,10 @@ inline void ggml_sycl_op_gelu_quick(ggml_backend_sycl_context & ctx, const ggml_
|
|||
|
||||
gelu_quick_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_tanh(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
@ -564,9 +566,10 @@ inline void ggml_sycl_op_tanh(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
GGML_ASSERT( dst->type == GGML_TYPE_F32);
|
||||
tanh_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_relu(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
@ -579,9 +582,10 @@ inline void ggml_sycl_op_relu(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
relu_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_hardsigmoid(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -595,9 +599,10 @@ inline void ggml_sycl_op_hardsigmoid(ggml_backend_sycl_context & ctx, const ggml
|
|||
|
||||
hardsigmoid_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_hardswish(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -610,9 +615,10 @@ inline void ggml_sycl_op_hardswish(ggml_backend_sycl_context & ctx, const ggml_t
|
|||
|
||||
hardswish_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_exp(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -625,9 +631,10 @@ inline void ggml_sycl_op_exp(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
exp_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_log(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -640,9 +647,10 @@ inline void ggml_sycl_op_log(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
log_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_sigmoid(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -655,9 +663,10 @@ inline void ggml_sycl_op_sigmoid(ggml_backend_sycl_context & ctx, const ggml_ten
|
|||
|
||||
sigmoid_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_sqrt(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -670,9 +679,10 @@ inline void ggml_sycl_op_sqrt(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
sqrt_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_sin(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -685,9 +695,10 @@ inline void ggml_sycl_op_sin(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
sin_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_cos(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -700,9 +711,10 @@ inline void ggml_sycl_op_cos(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
cos_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_step(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -715,9 +727,10 @@ inline void ggml_sycl_op_step(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
step_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_neg(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -730,9 +743,10 @@ inline void ggml_sycl_op_neg(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
neg_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_leaky_relu(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -749,9 +763,10 @@ inline void ggml_sycl_op_leaky_relu(ggml_backend_sycl_context & ctx, const ggml_
|
|||
|
||||
leaky_relu_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), negative_slope, main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_sqr(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
@ -764,9 +779,10 @@ inline void ggml_sycl_op_sqr(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
sqr_f32_sycl(src0_dd, dst_dd, ggml_nelements(src0), main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_upscale(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
|
||||
|
|
@ -787,9 +803,10 @@ inline void ggml_sycl_op_upscale(ggml_backend_sycl_context & ctx, const ggml_ten
|
|||
dst->ne[0], dst->ne[1], dst->ne[2], dst->ne[3], sf0, sf1, sf2, sf3,
|
||||
main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_pad(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
@ -805,9 +822,10 @@ inline void ggml_sycl_op_pad(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
src0->ne[0], src0->ne[1], src0->ne[2],
|
||||
dst->ne[0], dst->ne[1], dst->ne[2], main_stream);
|
||||
|
||||
(void) src1;
|
||||
(void) dst;
|
||||
(void) src1_dd;
|
||||
GGML_UNUSED(src1);
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(src1_dd);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_acc(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
@ -827,7 +845,8 @@ inline void ggml_sycl_op_acc(ggml_backend_sycl_context & ctx, const ggml_tensor
|
|||
|
||||
acc_f32_sycl(src0_dd, src1_dd, dst_dd, ggml_nelements(dst), src1->ne[0], src1->ne[1], src1->ne[2], nb1, nb2, offset, main_stream);
|
||||
|
||||
(void) dst;
|
||||
GGML_UNUSED(dst);
|
||||
GGML_UNUSED(ctx);
|
||||
}
|
||||
|
||||
inline void ggml_sycl_op_add(ggml_backend_sycl_context & ctx, const ggml_tensor *src0, const ggml_tensor *src1,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue