haraldwolff
/
whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691) 

* scripts : add sync-ggml-am.sh

* sync : ggml (VMM, ARM dot prod fix, etc.)

* build : fix CUDA build

* ggml : fix some mul mat cases + add tests for src1 F16

dbd02958fa
pull/1703/head
Georgi Gerganov 2023-12-29 11:30:47 +02:00 committed by GitHub
parent a5cc3dc8a2
commit e77b27c331
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 720 additions and 766 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
CMakeLists.txt
View File

@ -218,11 +218,17 @@ if (WHISPER_CUBLAS)
add_compile_definitions(GGML_USE_CUBLAS)
if (WHISPER_STATIC)
set(WHISPER_EXTRA_LIBS ${WHISPER_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
if (WIN32)
# As of 12.3.1 CUDA Tookit for Windows does not offer a static cublas library
set(WHISPER_EXTRA_LIBS ${WHISPER_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas CUDA::cublasLt)
else ()
set(WHISPER_EXTRA_LIBS ${WHISPER_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
endif()
else()
set(WHISPER_EXTRA_LIBS ${WHISPER_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
endif()
set(WHISPER_EXTRA_LIBS ${WHISPER_EXTRA_LIBS} CUDA::cuda_driver)
else()
message(FATAL_ERROR "cuBLAS not found")
endif()

2
Makefile
View File

@ -206,7 +206,7 @@ ifdef WHISPER_CUBLAS
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include
CXXFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/$(UNAME_M)-linux/include
LDFLAGS += -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/$(UNAME_M)-linux/lib
LDFLAGS += -lcuda -lcublas -lculibos -lcudart -lcublasLt -lpthread -ldl -lrt -L/usr/local/cuda/lib64 -L/opt/cuda/lib64 -L$(CUDA_PATH)/targets/$(UNAME_M)-linux/lib
WHISPER_OBJ += ggml-cuda.o
NVCC = nvcc
NVCCFLAGS = --forward-unknown-to-host-compiler -arch=$(CUDA_ARCH_FLAG)

138
extra/sync-ggml-am.sh 100755
View File

@ -0,0 +1,138 @@
#!/bin/bash
#
# Synchronize ggml changes to whisper.cpp
#
# Usage:
#
# $ cd /path/to/whisper.cpp
# $ ./extra/sync-ggml-am.sh
#
set -e
sd=$(dirname $0)
cd $sd/../
SRC_WHISPER=$(pwd)
SRC_GGML=$(cd ../ggml; pwd)
if [ ! -d $SRC_GGML ]; then
echo "ggml not found at $SRC_GGML"
exit 1
fi
lc=$(cat $SRC_WHISPER/extra/sync-ggml.last)
echo "Syncing ggml changes since commit $lc"
cd $SRC_GGML
git log --oneline $lc..HEAD
git format-patch $lc --stdout -- \
include/ggml/ggml*.h \
src/ggml*.h \
src/ggml*.c \
src/ggml*.cpp \
src/ggml*.m \
src/ggml*.metal \
src/ggml*.cu \
tests/test-opt.cpp \
tests/test-grad0.cpp \
tests/test-quantize-fns.cpp \
tests/test-quantize-perf.cpp \
tests/test-backend-ops.cpp \
> $SRC_WHISPER/ggml-src.patch
# delete files if empty
if [ ! -s $SRC_WHISPER/ggml-src.patch ]; then
rm -v $SRC_WHISPER/ggml-src.patch
fi
cd $SRC_WHISPER
if [ -f $SRC_WHISPER/ggml-src.patch ]; then
# replace PR numbers
#
# Subject: some text (#1234)
# Subject: some text (ggml/1234)
cat ggml-src.patch | sed -e 's/^Subject: \(.*\) (#\([0-9]*\))/Subject: \1 (ggml\/\2)/' > ggml-src.patch.tmp
mv ggml-src.patch.tmp ggml-src.patch
cat ggml-src.patch | sed -e 's/^\(.*\) (#\([0-9]*\))$/\1 (ggml\/\2)/' > ggml-src.patch.tmp
mv ggml-src.patch.tmp ggml-src.patch
# replace filenames:
#
# src/ggml.c -> ggml.c
# src/ggml-alloc.c -> ggml-alloc.c
# src/ggml-backend-impl.h -> ggml-backend-impl.h
# src/ggml-backend.c -> ggml-backend.c
# src/ggml-cuda.cu -> ggml-cuda.cu
# src/ggml-cuda.h -> ggml-cuda.h
# src/ggml-impl.h -> ggml-impl.h
# src/ggml-metal.h -> ggml-metal.h
# src/ggml-metal.m -> ggml-metal.m
# src/ggml-metal.metal -> ggml-metal.metal
# src/ggml-mpi.h -> ggml-mpi.h
# src/ggml-mpi.c -> ggml-mpi.c
# src/ggml-opencl.cpp -> ggml-opencl.cpp
# src/ggml-opencl.h -> ggml-opencl.h
# src/ggml-quants.c -> ggml-quants.c
# src/ggml-quants.h -> ggml-quants.h
# include/ggml/ggml.h -> ggml.h
# include/ggml/ggml-alloc.h -> ggml-alloc.h
# include/ggml/ggml-backend.h -> ggml-backend.h
#
# examples/common.h -> examples/common.h
# examples/common.cpp -> examples/common.cpp
# examples/common-ggml.h -> examples/common-ggml.h
# examples/common-ggml.cpp -> examples/common-ggml.cpp
#
# examples/whisper/whisper.h -> whisper.h
# examples/whisper/whisper.cpp -> whisper.cpp
# examples/whisper/main.cpp -> examples/main/main.cpp
# examples/whisper/quantize.cpp -> examples/quantize/quantize.cpp
cat ggml-src.patch | sed \
-e 's/src\/ggml\.c/ggml.c/g' \
-e 's/src\/ggml-alloc\.c/ggml-alloc.c/g' \
-e 's/src\/ggml-backend-impl\.h/ggml-backend-impl.h/g' \
-e 's/src\/ggml-backend\.c/ggml-backend.c/g' \
-e 's/src\/ggml-cuda\.cu/ggml-cuda.cu/g' \
-e 's/src\/ggml-cuda\.h/ggml-cuda.h/g' \
-e 's/src\/ggml-impl\.h/ggml-impl.h/g' \
-e 's/src\/ggml-metal\.h/ggml-metal.h/g' \
-e 's/src\/ggml-metal\.m/ggml-metal.m/g' \
-e 's/src\/ggml-metal\.metal/ggml-metal.metal/g' \
-e 's/src\/ggml-mpi\.h/ggml-mpi.h/g' \
-e 's/src\/ggml-mpi\.c/ggml-mpi.c/g' \
-e 's/src\/ggml-opencl\.cpp/ggml-opencl.cpp/g' \
-e 's/src\/ggml-opencl\.h/ggml-opencl.h/g' \
-e 's/src\/ggml-quants\.c/ggml-quants.c/g' \
-e 's/src\/ggml-quants\.h/ggml-quants.h/g' \
-e 's/include\/ggml\/ggml\.h/ggml.h/g' \
-e 's/include\/ggml\/ggml-alloc\.h/ggml-alloc.h/g' \
-e 's/include\/ggml\/ggml-backend\.h/ggml-backend.h/g' \
-e 's/examples\/common\.h/examples\/common.h/g' \
-e 's/examples\/common\.cpp/examples\/common.cpp/g' \
-e 's/examples\/common-ggml\.h/examples\/common-ggml.h/g' \
-e 's/examples\/common-ggml\.cpp/examples\/common-ggml.cpp/g' \
-e 's/examples\/whisper\/whisper\.h/whisper.h/g' \
-e 's/examples\/whisper\/whisper\.cpp/whisper.cpp/g' \
-e 's/examples\/whisper\/main\.cpp/examples\/main\/main.cpp/g' \
-e 's/examples\/whisper\/quantize\.cpp/examples\/quantize\/quantize.cpp/g' \
> ggml-src.patch.tmp
mv ggml-src.patch.tmp ggml-src.patch
git am ggml-src.patch
rm -v $SRC_WHISPER/ggml-src.patch
fi
# update last commit
cd $SRC_GGML
git log -1 --format=%H > $SRC_WHISPER/extra/sync-ggml.last
echo "Done"
exit 0

1
extra/sync-ggml.last 100644
View File

@ -0,0 +1 @@
1467a4eb71bdb5ac316d248a7f3f26cdadc56b68

24
ggml-backend.c
View File

@ -297,7 +297,7 @@ static void ggml_backend_registry_init(void) {
void ggml_backend_register(const char * name, ggml_backend_init_fn init_fn, ggml_backend_buffer_type_t default_buffer_type, void * user_data) {
GGML_ASSERT(ggml_backend_registry_count < GGML_MAX_BACKENDS_REG);
int id = ggml_backend_registry_count;
size_t id = ggml_backend_registry_count;
ggml_backend_registry[id] = (struct ggml_backend_reg) {
/* .name = */ {0},
@ -330,6 +330,8 @@ size_t ggml_backend_reg_find_by_name(const char * name) {
return i;
}
}
// not found
return SIZE_MAX;
}
@ -340,15 +342,15 @@ ggml_backend_t ggml_backend_reg_init_backend_from_str(const char * backend_str)
const char * params = strchr(backend_str, ':');
char backend_name[128];
if (params == NULL) {
strcpy(backend_name, backend_str);
snprintf(backend_name, sizeof(backend_name), "%s", backend_str);
params = "";
} else {
strncpy(backend_name, backend_str, params - backend_str);
backend_name[params - backend_str] = '\0';
snprintf(backend_name, sizeof(backend_name), "%.*s", (int)(params - backend_str), backend_str);
params++;
}
size_t backend_i = ggml_backend_reg_find_by_name(backend_name);
if (backend_i == SIZE_MAX) {
fprintf(stderr, "%s: backend %s not found\n", __func__, backend_name);
return NULL;
@ -396,18 +398,12 @@ static void ggml_backend_cpu_buffer_free_buffer(ggml_backend_buffer_t buffer) {
}
static void ggml_backend_cpu_buffer_set_tensor(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor, const void * data, size_t offset, size_t size) {
GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor write out of bounds");
GGML_ASSERT(tensor->data != NULL && "tensor not allocated");
memcpy((char *)tensor->data + offset, data, size);
GGML_UNUSED(buffer);
}
static void ggml_backend_cpu_buffer_get_tensor(ggml_backend_buffer_t buffer, const struct ggml_tensor * tensor, void * data, size_t offset, size_t size) {
GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor read out of bounds");
GGML_ASSERT(tensor->data != NULL && "tensor not allocated");
memcpy(data, (const char *)tensor->data + offset, size);
GGML_UNUSED(buffer);
@ -618,10 +614,14 @@ static void ggml_backend_cpu_graph_compute(ggml_backend_t backend, struct ggml_c
}
static bool ggml_backend_cpu_supports_op(ggml_backend_t backend, const struct ggml_tensor * op) {
return true;
switch (op->op) {
case GGML_OP_MUL_MAT:
return op->src[1]->type == GGML_TYPE_F32 || op->src[1]->type == ggml_internal_get_type_traits(op->src[0]->type).vec_dot_type;
default:
return true;
}
GGML_UNUSED(backend);
GGML_UNUSED(op);
}
static struct ggml_backend_i cpu_backend_i = {

937
ggml-cuda.cu
View File

File diff suppressed because it is too large Load Diff

363
ggml-quants.c
View File

@ -407,6 +407,18 @@ inline static ggml_int8x16x4_t ggml_vld1q_s8_x4(const int8_t * ptr) {
#define ggml_vld1q_s8_x4 vld1q_s8_x4
#endif
#if !defined(__ARM_FEATURE_DOTPROD)
inline static int32x4_t vdotq_s32(int32x4_t acc, int8x16_t a, int8x16_t b) {
const int16x8_t p0 = vmull_s8(vget_low_s8 (a), vget_low_s8 (b));
const int16x8_t p1 = vmull_s8(vget_high_s8(a), vget_high_s8(b));
return vaddq_s32(acc, vaddq_s32(vpaddlq_s16(p0), vpaddlq_s16(p1)));
}
#endif
#endif
#if defined(__ARM_NEON) || defined(__wasm_simd128__)
@ -2468,32 +2480,12 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * restrict s, const void * restrict vx,
const int8x16_t v1_1l = vld1q_s8(y1->qs);
const int8x16_t v1_1h = vld1q_s8(y1->qs + 16);
#if defined(__ARM_FEATURE_DOTPROD)
// dot product into int32x4_t
const int32x4_t p_0 = vdotq_s32(vdotq_s32(vdupq_n_s32(0), v0_0ls, v1_0l), v0_0hs, v1_0h);
const int32x4_t p_1 = vdotq_s32(vdotq_s32(vdupq_n_s32(0), v0_1ls, v1_1l), v0_1hs, v1_1h);
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(p_0), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(p_1), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
#else
const int16x8_t pl0l = vmull_s8(vget_low_s8 (v0_0ls), vget_low_s8 (v1_0l));
const int16x8_t pl0h = vmull_s8(vget_high_s8(v0_0ls), vget_high_s8(v1_0l));
const int16x8_t ph0l = vmull_s8(vget_low_s8 (v0_0hs), vget_low_s8 (v1_0h));
const int16x8_t ph0h = vmull_s8(vget_high_s8(v0_0hs), vget_high_s8(v1_0h));
const int16x8_t pl1l = vmull_s8(vget_low_s8 (v0_1ls), vget_low_s8 (v1_1l));
const int16x8_t pl1h = vmull_s8(vget_high_s8(v0_1ls), vget_high_s8(v1_1l));
const int16x8_t ph1l = vmull_s8(vget_low_s8 (v0_1hs), vget_low_s8 (v1_1h));
const int16x8_t ph1h = vmull_s8(vget_high_s8(v0_1hs), vget_high_s8(v1_1h));
const int32x4_t pl0 = vaddq_s32(vpaddlq_s16(pl0l), vpaddlq_s16(pl0h));
const int32x4_t ph0 = vaddq_s32(vpaddlq_s16(ph0l), vpaddlq_s16(ph0h));
const int32x4_t pl1 = vaddq_s32(vpaddlq_s16(pl1l), vpaddlq_s16(pl1h));
const int32x4_t ph1 = vaddq_s32(vpaddlq_s16(ph1l), vpaddlq_s16(ph1h));
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(pl0, ph0)), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(pl1, ph1)), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
#endif
}
*s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1);
@ -2776,32 +2768,12 @@ void ggml_vec_dot_q4_1_q8_1(const int n, float * restrict s, const void * restri
const int8x16_t v1_1l = vld1q_s8(y1->qs);
const int8x16_t v1_1h = vld1q_s8(y1->qs + 16);
#if defined(__ARM_FEATURE_DOTPROD)
// dot product into int32x4_t
const int32x4_t p_0 = vdotq_s32(vdotq_s32(vdupq_n_s32(0), v0_0l, v1_0l), v0_0h, v1_0h);
const int32x4_t p_1 = vdotq_s32(vdotq_s32(vdupq_n_s32(0), v0_1l, v1_1l), v0_1h, v1_1h);
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(p_0), GGML_FP16_TO_FP32(x0->d)*y0->d);
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(p_1), GGML_FP16_TO_FP32(x1->d)*y1->d);
#else
const int16x8_t pl0l = vmull_s8(vget_low_s8 (v0_0l), vget_low_s8 (v1_0l));
const int16x8_t pl0h = vmull_s8(vget_high_s8(v0_0l), vget_high_s8(v1_0l));
const int16x8_t ph0l = vmull_s8(vget_low_s8 (v0_0h), vget_low_s8 (v1_0h));
const int16x8_t ph0h = vmull_s8(vget_high_s8(v0_0h), vget_high_s8(v1_0h));
const int16x8_t pl1l = vmull_s8(vget_low_s8 (v0_1l), vget_low_s8 (v1_1l));
const int16x8_t pl1h = vmull_s8(vget_high_s8(v0_1l), vget_high_s8(v1_1l));
const int16x8_t ph1l = vmull_s8(vget_low_s8 (v0_1h), vget_low_s8 (v1_1h));
const int16x8_t ph1h = vmull_s8(vget_high_s8(v0_1h), vget_high_s8(v1_1h));
const int32x4_t pl0 = vaddq_s32(vpaddlq_s16(pl0l), vpaddlq_s16(pl0h));
const int32x4_t ph0 = vaddq_s32(vpaddlq_s16(ph0l), vpaddlq_s16(ph0h));
const int32x4_t pl1 = vaddq_s32(vpaddlq_s16(pl1l), vpaddlq_s16(pl1h));
const int32x4_t ph1 = vaddq_s32(vpaddlq_s16(ph1l), vpaddlq_s16(ph1h));
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(pl0, ph0)), GGML_FP16_TO_FP32(x0->d)*y0->d);
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(pl1, ph1)), GGML_FP16_TO_FP32(x1->d)*y1->d);
#endif
}
*s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1) + summs;
@ -2963,32 +2935,12 @@ void ggml_vec_dot_q5_0_q8_0(const int n, float * restrict s, const void * restri
const int8x16_t v1_1l = vld1q_s8(y1->qs);
const int8x16_t v1_1h = vld1q_s8(y1->qs + 16);
#if defined(__ARM_FEATURE_DOTPROD)
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(
vdotq_s32(vdupq_n_s32(0), v0_0lf, v1_0l),
vdotq_s32(vdupq_n_s32(0), v0_0hf, v1_0h))), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(
vdotq_s32(vdupq_n_s32(0), v0_1lf, v1_1l),
vdotq_s32(vdupq_n_s32(0), v0_1hf, v1_1h))), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
#else
const int16x8_t pl0l = vmull_s8(vget_low_s8 (v0_0lf), vget_low_s8 (v1_0l));
const int16x8_t pl0h = vmull_s8(vget_high_s8(v0_0lf), vget_high_s8(v1_0l));
const int16x8_t ph0l = vmull_s8(vget_low_s8 (v0_0hf), vget_low_s8 (v1_0h));
const int16x8_t ph0h = vmull_s8(vget_high_s8(v0_0hf), vget_high_s8(v1_0h));
const int16x8_t pl1l = vmull_s8(vget_low_s8 (v0_1lf), vget_low_s8 (v1_1l));
const int16x8_t pl1h = vmull_s8(vget_high_s8(v0_1lf), vget_high_s8(v1_1l));
const int16x8_t ph1l = vmull_s8(vget_low_s8 (v0_1hf), vget_low_s8 (v1_1h));
const int16x8_t ph1h = vmull_s8(vget_high_s8(v0_1hf), vget_high_s8(v1_1h));
const int32x4_t pl0 = vaddq_s32(vpaddlq_s16(pl0l), vpaddlq_s16(pl0h));
const int32x4_t ph0 = vaddq_s32(vpaddlq_s16(ph0l), vpaddlq_s16(ph0h));
const int32x4_t pl1 = vaddq_s32(vpaddlq_s16(pl1l), vpaddlq_s16(pl1h));
const int32x4_t ph1 = vaddq_s32(vpaddlq_s16(ph1l), vpaddlq_s16(ph1h));
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(pl0, ph0)), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(pl1, ph1)), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
#endif
}
*s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1);
@ -3275,32 +3227,12 @@ void ggml_vec_dot_q5_1_q8_1(const int n, float * restrict s, const void * restri
const int8x16_t v1_1l = vld1q_s8(y1->qs);
const int8x16_t v1_1h = vld1q_s8(y1->qs + 16);
#if defined(__ARM_FEATURE_DOTPROD)
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(
vdotq_s32(vdupq_n_s32(0), v0_0lf, v1_0l),
vdotq_s32(vdupq_n_s32(0), v0_0hf, v1_0h))), GGML_FP16_TO_FP32(x0->d)*y0->d);
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(
vdotq_s32(vdupq_n_s32(0), v0_1lf, v1_1l),
vdotq_s32(vdupq_n_s32(0), v0_1hf, v1_1h))), GGML_FP16_TO_FP32(x1->d)*y1->d);
#else
const int16x8_t pl0l = vmull_s8(vget_low_s8 (v0_0lf), vget_low_s8 (v1_0l));
const int16x8_t pl0h = vmull_s8(vget_high_s8(v0_0lf), vget_high_s8(v1_0l));
const int16x8_t ph0l = vmull_s8(vget_low_s8 (v0_0hf), vget_low_s8 (v1_0h));
const int16x8_t ph0h = vmull_s8(vget_high_s8(v0_0hf), vget_high_s8(v1_0h));
const int16x8_t pl1l = vmull_s8(vget_low_s8 (v0_1lf), vget_low_s8 (v1_1l));
const int16x8_t pl1h = vmull_s8(vget_high_s8(v0_1lf), vget_high_s8(v1_1l));
const int16x8_t ph1l = vmull_s8(vget_low_s8 (v0_1hf), vget_low_s8 (v1_1h));
const int16x8_t ph1h = vmull_s8(vget_high_s8(v0_1hf), vget_high_s8(v1_1h));
const int32x4_t pl0 = vaddq_s32(vpaddlq_s16(pl0l), vpaddlq_s16(pl0h));
const int32x4_t ph0 = vaddq_s32(vpaddlq_s16(ph0l), vpaddlq_s16(ph0h));
const int32x4_t pl1 = vaddq_s32(vpaddlq_s16(pl1l), vpaddlq_s16(pl1h));
const int32x4_t ph1 = vaddq_s32(vpaddlq_s16(ph1l), vpaddlq_s16(ph1h));
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(pl0, ph0)), GGML_FP16_TO_FP32(x0->d)*y0->d);
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(pl1, ph1)), GGML_FP16_TO_FP32(x1->d)*y1->d);
#endif
}
*s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1) + summs0 + summs1;
@ -3550,7 +3482,6 @@ void ggml_vec_dot_q8_0_q8_0(const int n, float * restrict s, const void * restri
const int8x16_t y1_0 = vld1q_s8(y1->qs);
const int8x16_t y1_1 = vld1q_s8(y1->qs + 16);
#if defined(__ARM_FEATURE_DOTPROD)
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(
vdotq_s32(vdupq_n_s32(0), x0_0, y0_0),
vdotq_s32(vdupq_n_s32(0), x0_1, y0_1))), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
@ -3558,26 +3489,6 @@ void ggml_vec_dot_q8_0_q8_0(const int n, float * restrict s, const void * restri
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(
vdotq_s32(vdupq_n_s32(0), x1_0, y1_0),
vdotq_s32(vdupq_n_s32(0), x1_1, y1_1))), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
#else
const int16x8_t p0_0 = vmull_s8(vget_low_s8 (x0_0), vget_low_s8 (y0_0));
const int16x8_t p0_1 = vmull_s8(vget_high_s8(x0_0), vget_high_s8(y0_0));
const int16x8_t p0_2 = vmull_s8(vget_low_s8 (x0_1), vget_low_s8 (y0_1));
const int16x8_t p0_3 = vmull_s8(vget_high_s8(x0_1), vget_high_s8(y0_1));
const int16x8_t p1_0 = vmull_s8(vget_low_s8 (x1_0), vget_low_s8 (y1_0));
const int16x8_t p1_1 = vmull_s8(vget_high_s8(x1_0), vget_high_s8(y1_0));
const int16x8_t p1_2 = vmull_s8(vget_low_s8 (x1_1), vget_low_s8 (y1_1));
const int16x8_t p1_3 = vmull_s8(vget_high_s8(x1_1), vget_high_s8(y1_1));
const int32x4_t p0 = vaddq_s32(vpaddlq_s16(p0_0), vpaddlq_s16(p0_1));
const int32x4_t p1 = vaddq_s32(vpaddlq_s16(p0_2), vpaddlq_s16(p0_3));
const int32x4_t p2 = vaddq_s32(vpaddlq_s16(p1_0), vpaddlq_s16(p1_1));
const int32x4_t p3 = vaddq_s32(vpaddlq_s16(p1_2), vpaddlq_s16(p1_3));
sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(p0, p1)), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(p2, p3)), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
#endif
}
*s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1);
@ -3650,12 +3561,10 @@ void ggml_vec_dot_q2_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
const uint8x16_t m3 = vdupq_n_u8(0x3);
const uint8x16_t m4 = vdupq_n_u8(0xF);
#if defined(__ARM_FEATURE_DOTPROD)
const int32x4_t vzero = vdupq_n_s32(0);
#endif
const int32x4_t vzero = vdupq_n_s32(0);
ggml_int8x16x2_t q2bytes;
uint8_t aux[16];
@ -3663,7 +3572,6 @@ void ggml_vec_dot_q2_K_q8_K(const int n, float * restrict s, const void * restri
float sum = 0;
for (int i = 0; i < nb; ++i) {
const float d = y[i].d * GGML_FP16_TO_FP32(x[i].d);
const float dmin = -y[i].d * GGML_FP16_TO_FP32(x[i].dmin);
@ -3689,20 +3597,9 @@ void ggml_vec_dot_q2_K_q8_K(const int n, float * restrict s, const void * restri
// We use this macro instead of a function call because for some reason
// the code runs 2-3% slower, even if the function is declared inline
#if defined(__ARM_FEATURE_DOTPROD)
#define MULTIPLY_ACCUM_WITH_SCALE(index)\
isum += vaddvq_s32(vdotq_s32(vzero, q2bytes.val[0], q8bytes.val[0])) * aux[is+(index)];\
isum += vaddvq_s32(vdotq_s32(vzero, q2bytes.val[1], q8bytes.val[1])) * aux[is+1+(index)];
#else
#define MULTIPLY_ACCUM_WITH_SCALE(index)\
{\
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q2bytes.val[0]), vget_low_s8 (q8bytes.val[0])),\
vmull_s8(vget_high_s8(q2bytes.val[0]), vget_high_s8(q8bytes.val[0])));\
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q2bytes.val[1]), vget_low_s8 (q8bytes.val[1])),\
vmull_s8(vget_high_s8(q2bytes.val[1]), vget_high_s8(q8bytes.val[1])));\
isum += vaddvq_s16(p1) * aux[is+(index)] + vaddvq_s16(p2) * aux[is+1+(index)];\
}
#endif
#define SHIFT_MULTIPLY_ACCUM_WITH_SCALE(shift, index)\
q8bytes = ggml_vld1q_s8_x2(q8); q8 += 32;\
@ -3710,26 +3607,23 @@ void ggml_vec_dot_q2_K_q8_K(const int n, float * restrict s, const void * restri
q2bytes.val[1] = vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q2bits.val[1], (shift)), m3));\
MULTIPLY_ACCUM_WITH_SCALE((index));
for (int j = 0; j < QK_K/128; ++j) {
const ggml_uint8x16x2_t q2bits = ggml_vld1q_u8_x2(q2); q2 += 32;
ggml_int8x16x2_t q8bytes = ggml_vld1q_s8_x2(q8); q8 += 32;
q2bytes.val[0] = vreinterpretq_s8_u8(vandq_u8(q2bits.val[0], m3));
q2bytes.val[1] = vreinterpretq_s8_u8(vandq_u8(q2bits.val[1], m3));
MULTIPLY_ACCUM_WITH_SCALE(0);
SHIFT_MULTIPLY_ACCUM_WITH_SCALE(2, 2);
SHIFT_MULTIPLY_ACCUM_WITH_SCALE(4, 4);
SHIFT_MULTIPLY_ACCUM_WITH_SCALE(6, 6);
is += 8;
}
sum += d * isum;
sum += d * isum;
}
*s = sum;
@ -4043,11 +3937,9 @@ void ggml_vec_dot_q2_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
const uint8x16_t m3 = vdupq_n_u8(0x3);
#if defined(__ARM_FEATURE_DOTPROD)
const int32x4_t vzero = vdupq_n_s32(0);
#endif
const int32x4_t vzero = vdupq_n_s32(0);
ggml_int8x16x4_t q2bytes;
@ -4081,28 +3973,12 @@ void ggml_vec_dot_q2_K_q8_K(const int n, float * restrict s, const void * restri
q2bytes.val[2] = vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q2bits, 4), m3));
q2bytes.val[3] = vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q2bits, 6), m3));
#if defined(__ARM_FEATURE_DOTPROD)
isum1 += vaddvq_s32(vdotq_s32(vzero, q2bytes.val[0], q8bytes.val[0])) * scales[0];
isum2 += vaddvq_s32(vdotq_s32(vzero, q2bytes.val[1], q8bytes.val[1])) * scales[1];
isum1 += vaddvq_s32(vdotq_s32(vzero, q2bytes.val[2], q8bytes.val[2])) * scales[2];
isum2 += vaddvq_s32(vdotq_s32(vzero, q2bytes.val[3], q8bytes.val[3])) * scales[3];
#else
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q2bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q2bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q2bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q2bytes.val[1]), vget_high_s8(q8bytes.val[1])));
isum1 += vaddvq_s16(p1) * scales[0];
isum2 += vaddvq_s16(p2) * scales[1];
const int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q2bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q2bytes.val[2]), vget_high_s8(q8bytes.val[2])));
const int16x8_t p4 = vaddq_s16(vmull_s8(vget_low_s8 (q2bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q2bytes.val[3]), vget_high_s8(q8bytes.val[3])));
isum1 += vaddvq_s16(p3) * scales[2];
isum2 += vaddvq_s16(p4) * scales[3];
#endif
sum += d * (isum1 + isum2);
}
*s = sum;
@ -4328,9 +4204,7 @@ void ggml_vec_dot_q3_K_q8_K(const int n, float * restrict s, const void * restri
uint32_t utmp[4];
const uint8x16_t m3b = vdupq_n_u8(0x3);
#ifdef __ARM_FEATURE_DOTPROD
const int32x4_t vzero = vdupq_n_s32(0);
#endif
const uint8x16_t m0 = vdupq_n_u8(1);
const uint8x16_t m1 = vshlq_n_u8(m0, 1);
@ -4382,22 +4256,11 @@ void ggml_vec_dot_q3_K_q8_K(const int n, float * restrict s, const void * restri
q3bytes.val[2] = vsubq_s8(vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q3bits.val[0], 2), m3b)), vreinterpretq_s8_u8(q3h.val[2]));
q3bytes.val[3] = vsubq_s8(vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q3bits.val[1], 2), m3b)), vreinterpretq_s8_u8(q3h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[0], q8bytes_1.val[0])) * scale[0];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[1], q8bytes_1.val[1])) * scale[1];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[2], q8bytes_1.val[2])) * scale[2];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[3], q8bytes_1.val[3])) * scale[3];
#else
int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[0]), vget_low_s8 (q8bytes_1.val[0])),
vmull_s8(vget_high_s8(q3bytes.val[0]), vget_high_s8(q8bytes_1.val[0])));
int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[1]), vget_low_s8 (q8bytes_1.val[1])),
vmull_s8(vget_high_s8(q3bytes.val[1]), vget_high_s8(q8bytes_1.val[1])));
int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[2]), vget_low_s8 (q8bytes_1.val[2])),
vmull_s8(vget_high_s8(q3bytes.val[2]), vget_high_s8(q8bytes_1.val[2])));
int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[3]), vget_low_s8 (q8bytes_1.val[3])),
vmull_s8(vget_high_s8(q3bytes.val[3]), vget_high_s8(q8bytes_1.val[3])));
isum += vaddvq_s16(p0) * scale[0] + vaddvq_s16(p1) * scale[1] + vaddvq_s16(p2) * scale[2] + vaddvq_s16(p3) * scale[3];
#endif
scale += 4;
q3h.val[0] = vbicq_u8(m2, qhbits.val[0]);
@ -4410,22 +4273,11 @@ void ggml_vec_dot_q3_K_q8_K(const int n, float * restrict s, const void * restri
q3bytes.val[2] = vsubq_s8(vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q3bits.val[0], 6), m3b)), vreinterpretq_s8_u8(q3h.val[2]));
q3bytes.val[3] = vsubq_s8(vreinterpretq_s8_u8(vandq_u8(vshrq_n_u8(q3bits.val[1], 6), m3b)), vreinterpretq_s8_u8(q3h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[0], q8bytes_2.val[0])) * scale[0];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[1], q8bytes_2.val[1])) * scale[1];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[2], q8bytes_2.val[2])) * scale[2];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[3], q8bytes_2.val[3])) * scale[3];
#else
p0 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[0]), vget_low_s8 (q8bytes_2.val[0])),
vmull_s8(vget_high_s8(q3bytes.val[0]), vget_high_s8(q8bytes_2.val[0])));
p1 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[1]), vget_low_s8 (q8bytes_2.val[1])),
vmull_s8(vget_high_s8(q3bytes.val[1]), vget_high_s8(q8bytes_2.val[1])));
p2 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[2]), vget_low_s8 (q8bytes_2.val[2])),
vmull_s8(vget_high_s8(q3bytes.val[2]), vget_high_s8(q8bytes_2.val[2])));
p3 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[3]), vget_low_s8 (q8bytes_2.val[3])),
vmull_s8(vget_high_s8(q3bytes.val[3]), vget_high_s8(q8bytes_2.val[3])));
isum += vaddvq_s16(p0) * scale[0] + vaddvq_s16(p1) * scale[1] + vaddvq_s16(p2) * scale[2] + vaddvq_s16(p3) * scale[3];
#endif
scale += 4;
if (j == 0) {
@ -4864,10 +4716,7 @@ void ggml_vec_dot_q3_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
#ifdef __ARM_FEATURE_DOTPROD
const int32x4_t vzero = vdupq_n_s32(0);
#endif
const int32x4_t vzero = vdupq_n_s32(0);
const uint8x16_t m3b = vdupq_n_u8(0x3);
const uint8x16_t mh = vdupq_n_u8(4);
@ -4908,22 +4757,10 @@ void ggml_vec_dot_q3_K_q8_K(const int n, float * restrict s, const void * restri
q3bytes.val[2] = vreinterpretq_s8_u8(vorrq_u8(vandq_u8(vshrq_n_u8(q3bits, 4), m3b), q3h.val[2]));
q3bytes.val[3] = vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q3bits, 6), q3h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[0], q8bytes.val[0])) * scales[0];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[1], q8bytes.val[1])) * scales[2];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[2], q8bytes.val[2])) * scales[1];
isum += vaddvq_s32(vdotq_s32(vzero, q3bytes.val[3], q8bytes.val[3])) * scales[3];
#else
const int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q3bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q3bytes.val[1]), vget_high_s8(q8bytes.val[1])));
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q3bytes.val[2]), vget_high_s8(q8bytes.val[2])));
const int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q3bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q3bytes.val[3]), vget_high_s8(q8bytes.val[3])));
isum += vaddvq_s16(p0) * scales[0] + vaddvq_s16(p1) * scales[2] + vaddvq_s16(p2) * scales[1] + vaddvq_s16(p3) * scales[3];
#endif
sum += d * isum;
@ -5228,11 +5065,8 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri
uint32_t utmp[4];
#ifdef __ARM_NEON
const uint8x16_t m4b = vdupq_n_u8(0xf);
#ifdef __ARM_FEATURE_DOTPROD
const int32x4_t mzero = vdupq_n_s32(0);
#endif
ggml_int8x16x2_t q4bytes;
ggml_int8x16x2_t q8bytes;
@ -5269,10 +5103,8 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri
int32_t sumi2 = 0;
for (int j = 0; j < QK_K/64; ++j) {
const ggml_uint8x16x2_t q4bits = ggml_vld1q_u8_x2(q4); q4 += 32;
#ifdef __ARM_FEATURE_DOTPROD
q8bytes = ggml_vld1q_s8_x2(q8); q8 += 32;
q4bytes.val[0] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[0], m4b));
q4bytes.val[1] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[1], m4b));
@ -5287,26 +5119,6 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri
const int32x4_t p2 = vdotq_s32(vdotq_s32(mzero, q4bytes.val[0], q8bytes.val[0]), q4bytes.val[1], q8bytes.val[1]);
sumi2 += vaddvq_s32(p2) * scales[2*j+1];
#else
q8bytes = ggml_vld1q_s8_x2(q8); q8 += 32;
q4bytes.val[0] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[0], m4b));
q4bytes.val[1] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[1], m4b));
const int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q4bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q4bytes.val[1]), vget_high_s8(q8bytes.val[1])));
sumi1 += vaddvq_s16(vaddq_s16(p0, p1)) * scales[2*j+0];
q8bytes = ggml_vld1q_s8_x2(q8); q8 += 32;
q4bytes.val[0] = vreinterpretq_s8_u8(vshrq_n_u8(q4bits.val[0], 4));
q4bytes.val[1] = vreinterpretq_s8_u8(vshrq_n_u8(q4bits.val[1], 4));
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q4bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q4bytes.val[1]), vget_high_s8(q8bytes.val[1])));
sumi2 += vaddvq_s16(vaddq_s16(p2, p3)) * scales[2*j+1];
#endif
}
sumf += d * (sumi1 + sumi2);
@ -5603,12 +5415,9 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
const uint8x16_t m4b = vdupq_n_u8(0xf);
#ifdef __ARM_FEATURE_DOTPROD
const int32x4_t mzero = vdupq_n_s32(0);
#endif
float sumf = 0;
@ -5636,7 +5445,6 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri
const ggml_uint8x16x2_t q4bits = ggml_vld1q_u8_x2(q4);
#ifdef __ARM_FEATURE_DOTPROD
q8bytes = ggml_vld1q_s8_x4(q8);
q4bytes.val[0] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[0], m4b));
q4bytes.val[1] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[1], m4b));
@ -5650,27 +5458,7 @@ void ggml_vec_dot_q4_K_q8_K(const int n, float * restrict s, const void * restri
const int32x4_t p2 = vdotq_s32(vdotq_s32(mzero, q4bytes.val[0], q8bytes.val[2]), q4bytes.val[1], q8bytes.val[3]);
const int32_t sumi2 = vaddvq_s32(p2) * scales[1];
#else
q8bytes = ggml_vld1q_s8_x4(q8);
q4bytes.val[0] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[0], m4b));
q4bytes.val[1] = vreinterpretq_s8_u8(vandq_u8 (q4bits.val[1], m4b));
const int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q4bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q4bytes.val[1]), vget_high_s8(q8bytes.val[1])));
int32_t sumi1 = vaddvq_s16(vaddq_s16(p0, p1)) * scales[0];
q4bytes.val[0] = vreinterpretq_s8_u8(vshrq_n_u8(q4bits.val[0], 4));
q4bytes.val[1] = vreinterpretq_s8_u8(vshrq_n_u8(q4bits.val[1], 4));
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[0]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q4bytes.val[0]), vget_high_s8(q8bytes.val[2])));
const int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q4bytes.val[1]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q4bytes.val[1]), vget_high_s8(q8bytes.val[3])));
int32_t sumi2 = vaddvq_s16(vaddq_s16(p2, p3)) * scales[1];
#endif
sumf += d * (sumi1 + sumi2);
}
*s = sumf - sum_mins;
@ -5875,15 +5663,11 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri
uint32_t utmp[4];
#ifdef __ARM_NEON
const uint8x16_t m4b = vdupq_n_u8(0xf);
const uint8x16_t mone = vdupq_n_u8(1);
const uint8x16_t mtwo = vdupq_n_u8(2);
#if defined(__ARM_FEATURE_DOTPROD)
const int32x4_t mzero = vdupq_n_s32(0);
#endif
ggml_int8x16x4_t q5bytes;
@ -5938,28 +5722,11 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri
q5bytes.val[2] = vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q5bits.val[0], 4), q5h.val[2]));
q5bytes.val[3] = vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q5bits.val[1], 4), q5h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
sumi += vaddvq_s32(vdotq_s32(vdotq_s32(mzero, q5bytes.val[0], q8bytes.val[0]), q5bytes.val[1], q8bytes.val[1])) * *scales++;
sumi += vaddvq_s32(vdotq_s32(vdotq_s32(mzero, q5bytes.val[2], q8bytes.val[2]), q5bytes.val[3], q8bytes.val[3])) * *scales++;
#else
const int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q5bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q5bytes.val[1]), vget_high_s8(q8bytes.val[1])));
sumi += vaddvq_s16(vaddq_s16(p0, p1)) * *scales++;
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q5bytes.val[2]), vget_high_s8(q8bytes.val[2])));
const int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q5bytes.val[3]), vget_high_s8(q8bytes.val[3])));
sumi += vaddvq_s16(vaddq_s16(p2, p3)) * *scales++;
#endif
}
sumf += d * sumi - dmin * sumi_mins;
}
*s = sumf;
@ -6311,12 +6078,9 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
const uint8x16_t m4b = vdupq_n_u8(0xf);
const uint8x16_t mh = vdupq_n_u8(16);
#if defined(__ARM_FEATURE_DOTPROD)
const int32x4_t mzero = vdupq_n_s32(0);
#endif
ggml_int8x16x4_t q5bytes;
ggml_uint8x16x4_t q5h;
@ -6348,32 +6112,12 @@ void ggml_vec_dot_q5_K_q8_K(const int n, float * restrict s, const void * restri
q5bytes.val[2] = vsubq_s8(vreinterpretq_s8_u8(vshrq_n_u8(q5bits.val[0], 4)), vreinterpretq_s8_u8(q5h.val[2]));
q5bytes.val[3] = vsubq_s8(vreinterpretq_s8_u8(vshrq_n_u8(q5bits.val[1], 4)), vreinterpretq_s8_u8(q5h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
int32_t sumi1 = sc[0] * vaddvq_s32(vdotq_s32(mzero, q5bytes.val[0], q8bytes.val[0]));
int32_t sumi2 = sc[1] * vaddvq_s32(vdotq_s32(mzero, q5bytes.val[1], q8bytes.val[1]));
int32_t sumi3 = sc[2] * vaddvq_s32(vdotq_s32(mzero, q5bytes.val[2], q8bytes.val[2]));
int32_t sumi4 = sc[3] * vaddvq_s32(vdotq_s32(mzero, q5bytes.val[3], q8bytes.val[3]));
sumf += d * (sumi1 + sumi2 + sumi3 + sumi4);
#else
const int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q5bytes.val[0]), vget_high_s8(q8bytes.val[0])));
const int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q5bytes.val[1]), vget_high_s8(q8bytes.val[1])));
int32_t sumi = sc[0] * vaddvq_s16(p0) + sc[1] * vaddvq_s16(p1);
const int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q5bytes.val[2]), vget_high_s8(q8bytes.val[2])));
const int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q5bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q5bytes.val[3]), vget_high_s8(q8bytes.val[3])));
sumi += sc[2] * vaddvq_s16(p2) + sc[3] * vaddvq_s16(p3);
sumf += d*sumi;
#endif
}
*s = sumf;
@ -6600,13 +6344,10 @@ void ggml_vec_dot_q6_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
float sum = 0;
const uint8x16_t m4b = vdupq_n_u8(0xF);
#if defined(__ARM_FEATURE_DOTPROD)
const int32x4_t vzero = vdupq_n_s32(0);
#endif
//const int8x16_t m32s = vdupq_n_s8(32);
const uint8x16_t mone = vdupq_n_u8(3);
@ -6658,31 +6399,13 @@ void ggml_vec_dot_q6_K_q8_K(const int n, float * restrict s, const void * restri
q6bytes.val[2] = vreinterpretq_s8_u8(vorrq_u8(vandq_u8(q6bits.val[2], m4b), q6h.val[2]));
q6bytes.val[3] = vreinterpretq_s8_u8(vorrq_u8(vandq_u8(q6bits.val[3], m4b), q6h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
isum += vaddvq_s32(vdotq_s32(vzero, q6bytes.val[0], q8bytes.val[0])) * scale[0] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[1], q8bytes.val[1])) * scale[1] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[2], q8bytes.val[2])) * scale[2] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[3], q8bytes.val[3])) * scale[3];
scale += 4;
#else
int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q6bytes.val[0]), vget_high_s8(q8bytes.val[0])));
int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q6bytes.val[1]), vget_high_s8(q8bytes.val[1])));
isum += vaddvq_s16(p0) * scale[0] + vaddvq_s16(p1) * scale[1];
scale += 2;
int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q6bytes.val[2]), vget_high_s8(q8bytes.val[2])));
int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q6bytes.val[3]), vget_high_s8(q8bytes.val[3])));
isum += vaddvq_s16(p2) * scale[0] + vaddvq_s16(p3) * scale[1];
scale += 2;
#endif
q8bytes = ggml_vld1q_s8_x4(q8); q8 += 64;
shifted = vshrq_n_u8(qhbits.val[0], 4);
@ -6703,34 +6426,11 @@ void ggml_vec_dot_q6_K_q8_K(const int n, float * restrict s, const void * restri
q6bytes.val[2] = vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q6bits.val[2], 4), q6h.val[2]));
q6bytes.val[3] = vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q6bits.val[3], 4), q6h.val[3]));
#if defined(__ARM_FEATURE_DOTPROD)
isum += vaddvq_s32(vdotq_s32(vzero, q6bytes.val[0], q8bytes.val[0])) * scale[0] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[1], q8bytes.val[1])) * scale[1] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[2], q8bytes.val[2])) * scale[2] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[3], q8bytes.val[3])) * scale[3];
scale += 4;
//for (int l = 0; l < 4; ++l) {
// const int32x4_t p = vdotq_s32(vzero, q6bytes.val[l], q8bytes.val[l]);
// isum += vaddvq_s32(p) * *scale++;
//}
#else
p0 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q6bytes.val[0]), vget_high_s8(q8bytes.val[0])));
p1 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q6bytes.val[1]), vget_high_s8(q8bytes.val[1])));
isum += vaddvq_s16(p0) * scale[0] + vaddvq_s16(p1) * scale[1];
scale += 2;
p2 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q6bytes.val[2]), vget_high_s8(q8bytes.val[2])));
p3 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q6bytes.val[3]), vget_high_s8(q8bytes.val[3])));
isum += vaddvq_s16(p2) * scale[0] + vaddvq_s16(p3) * scale[1];
scale += 2;
#endif
}
//sum += isum * d_all * y[i].d;
sum += d_all * y[i].d * (isum - 32 * isum_mins);
@ -7076,14 +6776,11 @@ void ggml_vec_dot_q6_K_q8_K(const int n, float * restrict s, const void * restri
const int nb = n / QK_K;
#ifdef __ARM_NEON
float sum = 0;
const uint8x16_t m4b = vdupq_n_u8(0xF);
const int8x16_t m32s = vdupq_n_s8(32);
#if defined(__ARM_FEATURE_DOTPROD)
const int32x4_t vzero = vdupq_n_s32(0);
#endif
const uint8x16_t mone = vdupq_n_u8(3);
@ -7119,26 +6816,10 @@ void ggml_vec_dot_q6_K_q8_K(const int n, float * restrict s, const void * restri
q6bytes.val[2] = vsubq_s8(vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q6bits.val[0], 4), q6h.val[2])), m32s);
q6bytes.val[3] = vsubq_s8(vreinterpretq_s8_u8(vorrq_u8(vshrq_n_u8(q6bits.val[1], 4), q6h.val[3])), m32s);
#if defined(__ARM_FEATURE_DOTPROD)
isum += vaddvq_s32(vdotq_s32(vzero, q6bytes.val[0], q8bytes.val[0])) * scale[0] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[1], q8bytes.val[1])) * scale[1] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[2], q8bytes.val[2])) * scale[2] +
vaddvq_s32(vdotq_s32(vzero, q6bytes.val[3], q8bytes.val[3])) * scale[3];
#else
int16x8_t p0 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[0]), vget_low_s8 (q8bytes.val[0])),
vmull_s8(vget_high_s8(q6bytes.val[0]), vget_high_s8(q8bytes.val[0])));
int16x8_t p1 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[1]), vget_low_s8 (q8bytes.val[1])),
vmull_s8(vget_high_s8(q6bytes.val[1]), vget_high_s8(q8bytes.val[1])));
isum += vaddvq_s16(p0) * scale[0] + vaddvq_s16(p1) * scale[1];
int16x8_t p2 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[2]), vget_low_s8 (q8bytes.val[2])),
vmull_s8(vget_high_s8(q6bytes.val[2]), vget_high_s8(q8bytes.val[2])));
int16x8_t p3 = vaddq_s16(vmull_s8(vget_low_s8 (q6bytes.val[3]), vget_low_s8 (q8bytes.val[3])),
vmull_s8(vget_high_s8(q6bytes.val[3]), vget_high_s8(q8bytes.val[3])));
isum += vaddvq_s16(p2) * scale[2] + vaddvq_s16(p3) * scale[3];
#endif
sum += isum * d_all * y[i].d;

11
ggml.c
View File

@ -4041,7 +4041,6 @@ static struct ggml_tensor * ggml_group_norm_impl(
result->op = GGML_OP_GROUP_NORM;
result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
result->src[0] = a;
result->src[1] = NULL; // TODO: maybe store epsilon here?
return result;
}
@ -5541,7 +5540,6 @@ static struct ggml_tensor * ggml_upscale_impl(
result->op_params[0] = scale_factor;
result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
result->src[0] = a;
result->src[1] = NULL;
return result;
}
@ -5846,7 +5844,6 @@ struct ggml_tensor * ggml_get_rel_pos(
result->op = GGML_OP_GET_REL_POS;
result->grad = is_node ? ggml_dup_tensor(ctx, result) : NULL;
result->src[0] = a;
result->src[1] = NULL;
return result;
}
@ -9690,7 +9687,7 @@ static void ggml_compute_forward_mul_mat(
const size_t row_size = ggml_row_size(vec_dot_type, ne10);
assert(params->wsize >= ne11*ne12*ne13*row_size);
assert(src1->type == GGML_TYPE_F32);
GGML_ASSERT(src1->type == GGML_TYPE_F32);
for (int64_t i13 = 0; i13 < ne13; ++i13) {
for (int64_t i12 = 0; i12 < ne12; ++i12) {
@ -17456,9 +17453,9 @@ static void ggml_opt_acc_grad(int np, struct ggml_tensor * const ps[], float * g
}
//
// ADAM
// Using AdamW - ref: https://arxiv.org/pdf/1711.05101v3.pdf
//
// ref: https://arxiv.org/pdf/1412.6980.pdf
// (Original Adam - ref: https://arxiv.org/pdf/1412.6980.pdf)
//
static enum ggml_opt_result ggml_opt_adam(
@ -19351,7 +19348,7 @@ void gguf_set_kv(struct gguf_context * ctx, struct gguf_context * src) {
data[j] = ((struct gguf_str *)src->kv[i].value.arr.data)[j].data;
}
gguf_set_arr_str(ctx, src->kv[i].key.data, data, src->kv[i].value.arr.n);
free(data);
free((void *)data);
} else if (src->kv[i].value.arr.type == GGUF_TYPE_ARRAY) {
GGML_ASSERT(false && "nested arrays not supported");
} else {

2
ggml.h
View File

@ -255,6 +255,8 @@
#define GGML_UNREACHABLE() GGML_ASSERT(!"statement should not be reached")
#elif defined(__GNUC__)
#define GGML_UNREACHABLE() __builtin_unreachable()
#elif defined(_MSC_VER)
#define GGML_UNREACHABLE() __assume(0)
#else
#define GGML_UNREACHABLE() ((void) 0)
#endif