wmantly/llama.cpp-xrip
1
0 Fork 0
Code Issues Pull Requests Actions 33 Packages Projects Releases Wiki Activity

hexagon: add CEIL op (#31006)

Browse Source 
* hex-ceil: add CEIL(f32) op

* hex-ceil: add f16 version

* hex-ops: update supported ops

* hex-ops: update docs with supported ops
This commit is contained in:
Max Krasnyansky authored and GitHub committed 2026-10-23 07:46:53 -07:00
1 parent e1e3b2c409
commit 36e36e63a5
9 files changed
+6911 -5065
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/ops.md
+14 -14
View File
@@ -14,7 +14,7 @@ Legend:
| Operation | BLAS | CANN | CPU | CUDA | ET | HTP | MTL | OpenCL | SYCL | Vulkan | WebGPU | ZenDNN | zDNN |
|-----------|------|------|------|------|------|------|------|------|------|------|------|------|------|
| ABS | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| ABS | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| ACC | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| ADD | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| ADD1 | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
@@ -22,12 +22,12 @@ Legend:
| ARANGE | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| ARGMAX | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| ARGSORT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| CEIL | ❌ | ❌ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| CEIL | ❌ | ❌ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| CLAMP | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| COL2IM_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| CONCAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
| CONT | ❌ | 🟡 | ✅ | ✅ | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
| CONV_1D_DW | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ✅ |
| CONV_1D_DW | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ✅ |
| CONV_2D | ❌ | ❌ | 🟡 | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ |
| CONV_2D_DW | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| CONV_3D | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
@@ -45,7 +45,7 @@ Legend:
| DSV4_HC_COMB | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| DSV4_HC_POST | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| DSV4_HC_PRE | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| DUP | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ | ❌ |
| DUP | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ | ❌ |
| ELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| EXP | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| EXPM1 | ❌ | ❌ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
@@ -55,10 +55,10 @@ Legend:
| GATED_DELTA_NET | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | 🟡 | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| GATED_LINEAR_ATTN | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| GEGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| GEGLU_ERF | ❌ | ✅ | ✅ | ✅ | 🟡 | ❌ | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| GEGLU_ERF | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| GEGLU_QUICK | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| GELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| GELU_ERF | ❌ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| GELU_ERF | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| GELU_QUICK | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| GET_ROWS | ❌ | 🟡 | ✅ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ❌ | ❌ |
| GET_ROWS_BACK | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ |
@@ -66,7 +66,7 @@ Legend:
| HARDSIGMOID | ❌ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| HARDSWISH | ❌ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| IM2COL | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| IM2COL_3D | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| IM2COL_3D | ❌ | ❌ | ✅ | ✅ | ❌ | 🟡 | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| L2_NORM | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | 🟡 | ❌ | ❌ |
| LEAKY_RELU | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 | 🟡 | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| LIGHTNING_INDEXER | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
@@ -74,7 +74,7 @@ Legend:
| MEAN | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | 🟡 | ✅ | ❌ | ❌ | ❌ |
| MUL | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| MUL_MAT | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 |
| MUL_MAT_HADAMARD | ❌ | ❌ | ✅ | ❌ | ✅ | 🟡 | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 |
| MUL_MAT_HADAMARD | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | 🟡 |
| MUL_MAT_ID | ❌ | 🟡 | ✅ | ✅ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | 🟡 | ❌ |
| MUL_MAT_ID_W4A4 | ❌ | ❌ | ✅ | ❌ | ❌ | 🟡 | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| MUL_MAT_ID_W4A8 | ❌ | ❌ | ✅ | ❌ | ❌ | 🟡 | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
@@ -87,9 +87,9 @@ Legend:
| OUT_PROD | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ | ❌ | ❌ | 🟡 | 🟡 | ❌ | ❌ | ❌ |
| PAD | ❌ | 🟡 | ✅ | 🟡 | ❌ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ |
| PAD_REFLECT_1D | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| POOL_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| POOL_2D | ❌ | 🟡 | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| REGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | ❌ | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| POOL_1D | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| POOL_2D | ❌ | 🟡 | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| REGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| RELU | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | ✅ | ❌ | ❌ |
| REPEAT | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | 🟡 | ✅ | ✅ | 🟡 | ❌ | ❌ |
| REPEAT_BACK | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
@@ -101,7 +101,7 @@ Legend:
| ROUND | ❌ | ❌ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| RWKV_WKV6 | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| RWKV_WKV7 | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| SCALE | ❌ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SCALE | ❌ | 🟡 | ✅ | ✅ | ✅ | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SET | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ✅ | ❌ | 🟡 | ✅ | ✅ | ❌ | ❌ |
| SET_ROWS | ❌ | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | 🟡 | ❌ | ❌ |
| SGN | ❌ | ✅ | ✅ | 🟡 | 🟡 | ❌ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
@@ -117,12 +117,12 @@ Legend:
| SQRT | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SSM_CONV | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SSM_SCAN | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | 🟡 | 🟡 | ✅ | ❌ | ❌ |
| STEP | ❌ | ✅ | ✅ | 🟡 | 🟡 | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| STEP | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SUB | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SUM | ❌ | 🟡 | ✅ | 🟡 | ❌ | 🟡 | 🟡 | ❌ | 🟡 | 🟡 | 🟡 | ❌ | ❌ |
| SUM_ROWS | ❌ | ✅ | ✅ | 🟡 | ❌ | 🟡 | ✅ | 🟡 | 🟡 | ✅ | ✅ | ❌ | ❌ |
| SWIGLU | ❌ | ✅ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| SWIGLU_CLAMP | ❌ | ❌ | ✅ | ❌ | ❌ | 🟡 | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| SWIGLU_CLAMP | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| SWIGLU_OAI | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| TANH | ❌ | ✅ | ✅ | 🟡 | 🟡 | 🟡 | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ |
| TIMESTEP_EMBEDDING | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ |
docs/ops/Hexagon.csv
+6792 -5051
View File
File diff suppressed because it is too large. Load diff
ggml/src/ggml-hexagon/htp-kparams.cpp
+2
View File
@@ -72,6 +72,7 @@ htp_op_code htp_op_remap(const struct ggml_tensor * t) {
case GGML_UNARY_OP_ABS: return HTP_OP_UNARY_ABS;
case GGML_UNARY_OP_RELU: return HTP_OP_UNARY_RELU;
case GGML_UNARY_OP_STEP: return HTP_OP_UNARY_STEP;
case GGML_UNARY_OP_CEIL: return HTP_OP_UNARY_CEIL;
default: break;
}
break;
@@ -1433,6 +1434,7 @@ static bool htp_kparams_solve_unary_impl(
case HTP_OP_UNARY_LOG:
case HTP_OP_UNARY_ABS:
case HTP_OP_UNARY_STEP:
case HTP_OP_UNARY_CEIL:
break;
default:
return false;
ggml/src/ggml-hexagon/htp/htp-ops.h
+1
View File
@@ -112,6 +112,7 @@ enum htp_op_code {
HTP_OP_HADAMARD,
HTP_OP_GLU_REGLU,
HTP_OP_GLU_SIGMOID,
HTP_OP_UNARY_CEIL,
HTP_OP_INVALID
};
ggml/src/ggml-hexagon/htp/hvx-arith.h
+55
View File
@@ -7,6 +7,7 @@
#include <math.h>
#include "hvx-base.h"
#include "hvx-floor.h"
#include "hex-utils.h"
//
@@ -700,6 +701,60 @@ static inline void hvx_step_f16_aa(uint8_t * restrict dst, const uint8_t * restr
}
}
//
// Ceil
//
static inline void hvx_ceil_f32_aa(uint8_t * restrict dst, const uint8_t * restrict src, uint32_t n) {
assert((unsigned long) dst % 128 == 0);
assert((unsigned long) src % 128 == 0);
HVX_Vector * restrict vdst = (HVX_Vector *) dst;
HVX_Vector * restrict vsrc = (HVX_Vector *) src;
const uint32_t elem_size = sizeof(float);
const uint32_t epv = 128 / elem_size;
const uint32_t nvec = n / epv;
const uint32_t nloe = n % epv;
uint32_t i = 0;
_Pragma("unroll(4)")
for (; i < nvec; i++) {
vdst[i] = hvx_vec_ceil_f32(vsrc[i]);
}
if (nloe) {
HVX_Vector v = hvx_vec_ceil_f32(vsrc[i]);
hvx_vec_store_a((void *) &vdst[i], nloe * elem_size, v);
}
}
static inline void hvx_ceil_f16_aa(uint8_t * restrict dst, const uint8_t * restrict src, uint32_t n) {
assert((unsigned long) dst % 128 == 0);
assert((unsigned long) src % 128 == 0);
HVX_Vector * restrict vdst = (HVX_Vector *) dst;
HVX_Vector * restrict vsrc = (HVX_Vector *) src;
const uint32_t elem_size = sizeof(_Float16);
const uint32_t epv = 128 / elem_size;
const uint32_t nvec = n / epv;
const uint32_t nloe = n % epv;
uint32_t i = 0;
_Pragma("unroll(4)")
for (; i < nvec; i++) {
HVX_VectorPair p = hvx_vec_f16_to_f32(vsrc[i]);
vdst[i] = hvx_vec_f32_to_f16(hvx_vec_ceil_f32(Q6_V_lo_W(p)), hvx_vec_ceil_f32(Q6_V_hi_W(p)));
}
if (nloe) {
HVX_VectorPair p = hvx_vec_f16_to_f32(vsrc[i]);
HVX_Vector v = hvx_vec_f32_to_f16(hvx_vec_ceil_f32(Q6_V_lo_W(p)), hvx_vec_ceil_f32(Q6_V_hi_W(p)));
hvx_vec_store_a((void *) &vdst[i], nloe * elem_size, v);
}
}
//
// Square
//
ggml/src/ggml-hexagon/htp/hvx-floor.h
+8
View File
@@ -97,4 +97,12 @@ static inline HVX_Vector hvx_vec_floor_f32(HVX_Vector in_vec) {
return vout;
}
// ceil(x) = -floor(-x); keep +-0 as is since floor(-0) returns -1
static inline HVX_Vector hvx_vec_ceil_f32(HVX_Vector in_vec) {
HVX_Vector vout = hvx_vec_neg_f32(hvx_vec_floor_f32(hvx_vec_neg_f32(in_vec)));
HVX_Vector vabs = Q6_V_vand_VV(in_vec, Q6_V_vsplat_R(0x7fffffff));
HVX_VectorPred q_zero = Q6_Q_vcmp_eq_VwVw(vabs, Q6_V_vzero());
return Q6_V_vmux_QVV(q_zero, in_vec, vout);
}
#endif /* HVX_FLOOR_H */
ggml/src/ggml-hexagon/htp/main.c
+1
View File
@@ -945,6 +945,7 @@ static int execute_op(struct htp_ops_context * octx) {
case HTP_OP_UNARY_LOG:
case HTP_OP_UNARY_RELU:
case HTP_OP_UNARY_STEP:
case HTP_OP_UNARY_CEIL:
case HTP_OP_L2_NORM:
case HTP_OP_HADAMARD:
return op_unary(octx);
ggml/src/ggml-hexagon/htp/unary-ops.c
+37
View File
@@ -426,6 +426,20 @@ static void step_f16(const void * restrict src,
}
}
static void ceil_f16(const void * restrict src,
void * restrict dst,
const uint32_t num_rows,
const struct htp_unary_context * uctx) {
htp_unary_op_preamble;
for (uint32_t ir = 0; ir < num_rows; ir++) {
const uint8_t * restrict src_local = (const uint8_t *)src + (ir * src0_row_size_aligned);
uint8_t * restrict dst_local = (uint8_t *)dst + (ir * dst_row_size_aligned);
hvx_ceil_f16_aa((uint8_t *) dst_local, (const uint8_t *) src_local, ne0);
}
}
static void l2_norm_f16(const void * restrict src,
void * restrict dst,
const uint32_t num_rows,
@@ -948,6 +962,20 @@ static void step_f32(const void * restrict src,
}
}
static void ceil_f32(const void * restrict src,
void * restrict dst,
const uint32_t num_rows,
const struct htp_unary_context * uctx) {
htp_unary_op_preamble;
for (uint32_t ir = 0; ir < num_rows; ir++) {
const uint8_t * restrict src_local = (const uint8_t *)src + (ir * src0_row_size_aligned);
uint8_t * restrict dst_local = (uint8_t *)dst + (ir * dst_row_size_aligned);
hvx_ceil_f32_aa(dst_local, src_local, ne0);
}
}
static void log_f32(const void * restrict src,
void * restrict dst,
const uint32_t num_rows,
@@ -1061,6 +1089,11 @@ static void tile_step_f32(void * restrict dst, const void * restrict src, uint32
hvx_step_f32_aa((uint8_t *) dst, (const uint8_t *) src, tw);
}
static void tile_ceil_f32(void * restrict dst, const void * restrict src, uint32_t tw, const struct htp_unary_context * uctx) {
(void) uctx;
hvx_ceil_f32_aa((uint8_t *) dst, (const uint8_t *) src, tw);
}
static void tri_apply_tile_f32(const void * restrict src, void * restrict dst,
uint32_t tile_elems, uint32_t col_start, uint32_t i01,
uint32_t ne0, int32_t ttype) {
@@ -1704,6 +1737,7 @@ static int execute_op_unary(struct htp_ops_context * octx) {
case HTP_OP_UNARY_LOG: op_type = is_f16 ? "log-f16" : "log-f32"; break;
case HTP_OP_UNARY_RELU: op_type = "relu-f32"; break;
case HTP_OP_UNARY_STEP: op_type = is_f16 ? "step-f16" : "step-f32"; break;
case HTP_OP_UNARY_CEIL: op_type = is_f16 ? "ceil-f16" : "ceil-f32"; break;
case HTP_OP_L2_NORM: op_type = is_f16 ? "l2norm-f16" : "l2norm-f32"; break;
case HTP_OP_TRI: op_type = "tri-f32"; break;
case HTP_OP_HADAMARD: op_type = is_f16 ? "hadamard-f16" : "hadamard-f32"; break;
@@ -1837,6 +1871,7 @@ static int execute_op_unary(struct htp_ops_context * octx) {
case HTP_OP_UNARY_LOG: compute_func = (void *) tile_log_f32; break;
case HTP_OP_UNARY_RELU: compute_func = (void *) tile_relu_f32; break;
case HTP_OP_UNARY_STEP: compute_func = (void *) tile_step_f32; break;
case HTP_OP_UNARY_CEIL: compute_func = (void *) tile_ceil_f32; break;
case HTP_OP_TRI:
task_func = unary_thread_tiled_tri_f32;
compute_func = (void *) tri_apply_tile_f32;
@@ -1856,6 +1891,7 @@ static int execute_op_unary(struct htp_ops_context * octx) {
case HTP_OP_UNARY_ABS: compute_func = (void *) abs_f16; break;
case HTP_OP_UNARY_LOG: compute_func = (void *) log_f16; break;
case HTP_OP_UNARY_STEP: compute_func = (void *) step_f16; break;
case HTP_OP_UNARY_CEIL: compute_func = (void *) ceil_f16; break;
case HTP_OP_HADAMARD: compute_func = (void *) hadamard_f16; break;
default: break;
}
@@ -1886,6 +1922,7 @@ static int execute_op_unary(struct htp_ops_context * octx) {
case HTP_OP_UNARY_LOG: compute_func = (void *) log_f32; break;
case HTP_OP_UNARY_RELU: compute_func = (void *) relu_f32; break;
case HTP_OP_UNARY_STEP: compute_func = (void *) step_f32; break;
case HTP_OP_UNARY_CEIL: compute_func = (void *) ceil_f32; break;
case HTP_OP_L2_NORM: compute_func = (void *) l2_norm_f32; break;
case HTP_OP_HADAMARD: compute_func = (void *) hadamard_f32; break;
case HTP_OP_TRI:
ggml/src/ggml-hexagon/htp/unary-ops.h
+1
View File
@@ -55,6 +55,7 @@ static inline bool htp_op_is_unary(uint32_t opcode) {
case HTP_OP_UNARY_LOG:
case HTP_OP_UNARY_RELU:
case HTP_OP_UNARY_STEP:
case HTP_OP_UNARY_CEIL:
case HTP_OP_L2_NORM:
case HTP_OP_TRI:
case HTP_OP_HADAMARD: