|
|
|
|
# allow to use Host cuda functions in C/C++
|
|
|
|
|
DEF_INCLUDES = @CUDA_INCLUDES@
|
|
|
|
|
|
|
|
|
|
if WANT_JANSSON
|
|
|
|
|
JANSSON_INCLUDES= -I$(top_srcdir)/compat/jansson
|
|
|
|
|
else
|
|
|
|
|
JANSSON_INCLUDES=
|
|
|
|
|
endif
|
|
|
|
|
|
|
|
|
|
EXTRA_DIST = autogen.sh README.md README.txt LICENSE.txt \
|
|
|
|
|
ccminer.sln ccminer.vcxproj ccminer.vcxproj.filters \
|
|
|
|
|
compat/gettimeofday.c compat/getopt/getopt_long.c
|
|
|
|
|
|
|
|
|
|
SUBDIRS = compat
|
|
|
|
|
|
|
|
|
|
bin_PROGRAMS = ccminer
|
|
|
|
|
|
|
|
|
|
ccminer_SOURCES = elist.h miner.h compat.h \
|
|
|
|
|
compat/inttypes.h compat/stdbool.h compat/unistd.h \
|
|
|
|
|
compat/sys/time.h compat/getopt/getopt.h \
|
|
|
|
|
crc32.c hefty1.c \
|
|
|
|
|
ccminer.cpp pools.cpp util.cpp bench.cpp bignum.cpp \
|
|
|
|
|
api.cpp hashlog.cpp nvml.cpp stats.cpp sysinfos.cpp cuda.cpp \
|
|
|
|
|
heavy/heavy.cu \
|
|
|
|
|
heavy/cuda_blake512.cu heavy/cuda_blake512.h \
|
|
|
|
|
heavy/cuda_combine.cu heavy/cuda_combine.h \
|
|
|
|
|
heavy/cuda_groestl512.cu heavy/cuda_groestl512.h \
|
|
|
|
|
heavy/cuda_hefty1.cu heavy/cuda_hefty1.h \
|
|
|
|
|
heavy/cuda_keccak512.cu heavy/cuda_keccak512.h \
|
|
|
|
|
heavy/cuda_sha256.cu heavy/cuda_sha256.h \
|
|
|
|
|
heavy/bastion.cu heavy/cuda_bastion.cu \
|
|
|
|
|
fuguecoin.cpp Algo256/cuda_fugue256.cu sph/fugue.c uint256.h \
|
|
|
|
|
groestlcoin.cpp cuda_groestlcoin.cu cuda_groestlcoin.h \
|
|
|
|
|
myriadgroestl.cpp cuda_myriadgroestl.cu \
|
|
|
|
|
lyra2/Lyra2.c lyra2/Sponge.c \
|
|
|
|
|
lyra2/lyra2RE.cu lyra2/cuda_lyra2.cu \
|
|
|
|
|
lyra2/lyra2REv2.cu lyra2/cuda_lyra2v2.cu \
|
|
|
|
|
lyra2/Lyra2Z.c lyra2/lyra2Z.cu lyra2/cuda_lyra2Z.cu \
|
|
|
|
|
Algo256/cuda_bmw256.cu Algo256/cuda_cubehash256.cu \
|
|
|
|
|
Algo256/cuda_blake256.cu Algo256/cuda_groestl256.cu Algo256/cuda_keccak256.cu Algo256/cuda_skein256.cu \
|
|
|
|
|
Algo256/blake256.cu Algo256/decred.cu Algo256/vanilla.cu Algo256/keccak256.cu \
|
|
|
|
|
Algo256/blake2s.cu sph/blake2s.c \
|
|
|
|
|
Algo256/bmw.cu Algo256/cuda_bmw.cu \
|
|
|
|
|
crypto/xmr-rpc.cpp crypto/wildkeccak-cpu.cpp crypto/wildkeccak.cu \
|
|
|
|
|
crypto/cryptolight.cu crypto/cryptolight-core.cu crypto/cryptolight-cpu.cpp \
|
|
|
|
|
crypto/cryptonight.cu crypto/cryptonight-core.cu crypto/cryptonight-extra.cu \
|
|
|
|
|
crypto/cryptonight-cpu.cpp crypto/oaes_lib.cpp crypto/aesb.cpp crypto/cpu/c_keccak.c \
|
|
|
|
|
JHA/jackpotcoin.cu JHA/cuda_jha_keccak512.cu \
|
|
|
|
|
JHA/cuda_jha_compactionTest.cu cuda_checkhash.cu \
|
|
|
|
|
quark/cuda_jh512.cu quark/cuda_quark_blake512.cu quark/cuda_quark_groestl512.cu quark/cuda_skein512.cu \
|
|
|
|
|
quark/cuda_bmw512.cu quark/cuda_quark_keccak512.cu \
|
|
|
|
|
quark/nist5.cu \
|
|
|
|
|
quark/quarkcoin.cu quark/cuda_quark_compactionTest.cu \
|
|
|
|
|
neoscrypt/neoscrypt.cpp neoscrypt/neoscrypt-cpu.c neoscrypt/cuda_neoscrypt.cu \
|
|
|
|
|
pentablake.cu skein.cu cuda_skeincoin.cu skein2.cpp zr5.cu \
|
|
|
|
|
sha256/sha256t.cu sha256/cuda_sha256t.cu \
|
|
|
|
|
sia/sia.cu sia/sia-rpc.cpp sph/blake2b.c \
|
|
|
|
|
sph/bmw.c sph/blake.c sph/groestl.c sph/jh.c sph/keccak.c sph/skein.c \
|
|
|
|
|
sph/cubehash.c sph/echo.c sph/luffa.c sph/sha2.c sph/shavite.c sph/simd.c \
|
|
|
|
|
sph/hamsi.c sph/hamsi_helper.c sph/streebog.c \
|
|
|
|
|
sph/shabal.c sph/whirlpool.c sph/sha2big.c sph/haval.c \
|
|
|
|
|
sph/ripemd.c sph/sph_sha2.c \
|
|
|
|
|
lbry/lbry.cu lbry/cuda_sha256_lbry.cu lbry/cuda_sha512_lbry.cu lbry/cuda_lbry_merged.cu \
|
|
|
|
|
qubit/qubit.cu qubit/qubit_luffa512.cu qubit/deep.cu qubit/luffa.cu \
|
|
|
|
|
x11/x11.cu x11/fresh.cu x11/cuda_x11_luffa512.cu x11/cuda_x11_cubehash512.cu \
|
|
|
|
|
x11/cuda_x11_shavite512.cu x11/cuda_x11_simd512.cu x11/cuda_x11_echo.cu \
|
|
|
|
|
x11/cuda_x11_luffa512_Cubehash.cu x11/x11evo.cu \
|
|
|
|
|
x13/x13.cu x13/cuda_x13_hamsi512.cu x13/cuda_x13_fugue512.cu \
|
|
|
|
|
x15/x14.cu x15/x15.cu x15/cuda_x14_shabal512.cu x15/cuda_x15_whirlpool.cu \
|
|
|
|
|
x15/whirlpool.cu \
|
|
|
|
|
x17/x17.cu x17/hmq17.cu x17/cuda_x17_haval256.cu x17/cuda_x17_sha512.cu \
|
|
|
|
|
x11/c11.cu x11/s3.cu x11/sib.cu x11/veltor.cu x11/cuda_streebog.cu
|
|
|
|
|
|
|
|
|
|
# scrypt
|
|
|
|
|
ccminer_SOURCES += scrypt.cpp scrypt-jane.cpp \
|
|
|
|
|
scrypt/blake.cu scrypt/keccak.cu scrypt/sha256.cu \
|
|
|
|
|
scrypt/salsa_kernel.cu scrypt/test_kernel.cu \
|
|
|
|
|
scrypt/fermi_kernel.cu scrypt/kepler_kernel.cu \
|
|
|
|
|
scrypt/nv_kernel.cu scrypt/nv_kernel2.cu scrypt/titan_kernel.cu
|
|
|
|
|
|
|
|
|
|
if HAVE_NVML
|
|
|
|
|
nvml_defs = -DUSE_WRAPNVML
|
|
|
|
|
nvml_libs = -ldl
|
|
|
|
|
endif
|
|
|
|
|
|
|
|
|
|
if HAVE_WINDOWS
|
|
|
|
|
ccminer_SOURCES += compat/winansi.c
|
|
|
|
|
endif
|
|
|
|
|
|
|
|
|
|
ccminer_LDFLAGS = $(PTHREAD_FLAGS) @CUDA_LDFLAGS@
|
|
|
|
|
ccminer_LDADD = @LIBCURL@ @JANSSON_LIBS@ @PTHREAD_LIBS@ @WS2_LIBS@ @CUDA_LIBS@ @OPENMP_CFLAGS@ @LIBS@ $(nvml_libs)
|
|
|
|
|
ccminer_CPPFLAGS = @LIBCURL_CPPFLAGS@ @OPENMP_CFLAGS@ $(CPPFLAGS) $(PTHREAD_FLAGS) -fno-strict-aliasing $(JANSSON_INCLUDES) $(DEF_INCLUDES) $(nvml_defs)
|
|
|
|
|
|
|
|
|
|
nvcc_ARCH = -gencode=arch=compute_50,code=\"sm_50,compute_50\"
|
|
|
|
|
|
|
|
|
|
nvcc_ARCH += -gencode=arch=compute_52,code=\"sm_52,compute_52\"
|
|
|
|
|
#nvcc_ARCH += -gencode=arch=compute_35,code=\"sm_35,compute_35\"
|
|
|
|
|
#nvcc_ARCH += -gencode=arch=compute_30,code=\"sm_30,compute_30\"
|
|
|
|
|
#nvcc_ARCH += -gencode=arch=compute_20,code=\"sm_21,compute_20\"
|
|
|
|
|
|
|
|
|
|
nvcc_FLAGS = $(nvcc_ARCH) @CUDA_INCLUDES@ -I. @CUDA_CFLAGS@
|
|
|
|
|
nvcc_FLAGS += $(JANSSON_INCLUDES) --ptxas-options="-v"
|
|
|
|
|
|
|
|
|
|
# we're now targeting all major compute architectures within one binary.
|
|
|
|
|
.cu.o:
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=128 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
Algo256/blake256.o: Algo256/blake256.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=64 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
Algo256/cuda_bmw.o: Algo256/cuda_bmw.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=76 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
crypto/cryptonight-core.o: crypto/cryptonight-core.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=64 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
crypto/cryptonight-extra.o: crypto/cryptonight-extra.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
heavy/cuda_hefty1.o: heavy/cuda_hefty1.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
qubit/qubit_luffa512.o: qubit/qubit_luffa512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
# Luffa and Echo are faster with 80 registers than 128
|
|
|
|
|
x11/cuda_x11_luffa512.o: x11/cuda_x11_luffa512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
x11/cuda_x11_luffa512_Cubehash.o: x11/cuda_x11_luffa512_Cubehash.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=76 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
x11/cuda_x11_simd512.o: x11/cuda_x11_simd512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) -Xcompiler -Wno-unused-variable -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
x13/cuda_x13_hamsi512.o: x13/cuda_x13_hamsi512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=72 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
x17/cuda_x17_sha512.o: x17/cuda_x17_sha512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
quark/cuda_quark_blake512.o: quark/cuda_quark_blake512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
improve jh512 with vectors (nist5,quark,sib,x11+,zr5)
the main improvement is to reduce asm calls to read global mem
but, a few more regs are used (68 mini vs 64 on SM 5.2)
so reduce the forced launch bounds to allow 80 or 128 regs per thread
Note: cuda 6.5 seems not able to store with v4.u32... (7.5 is fine)
st.global.v4.u32 [%rd2], {%r3783, %r3824, %r3823, %r3822};
st.global.v2.u32 [%rd2+16], {%r3821, %r3820};
st.global.u32 [%rd2+24], %r3819;
st.global.u32 [%rd2+28], %r3818;
st.global.u32 [%rd2+44], %r3814;
st.global.u32 [%rd2+40], %r3815;
...
todo, check alexis variant.. but wanted to keep this code before in git...
8 years ago
|
|
|
quark/cuda_jh512.o: quark/cuda_jh512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
quark/cuda_quark_keccak512.o: quark/cuda_quark_keccak512.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=88 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
quark/cuda_quark_compactionTest.o: quark/cuda_quark_compactionTest.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
JHA/cuda_jha_compactionTest.o: JHA/cuda_jha_compactionTest.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=80 -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
# This object does not use cuda device code but call the different kernels (autotune)
|
|
|
|
|
scrypt/salsa_kernel.o: scrypt/salsa_kernel.cu
|
|
|
|
|
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_21,compute_20\" -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
# These kernels are for older devices (SM)
|
|
|
|
|
|
|
|
|
|
scrypt/test_kernel.o: scrypt/test_kernel.cu
|
|
|
|
|
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_20,compute_20\" -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
scrypt/fermi_kernel.o: scrypt/fermi_kernel.cu
|
|
|
|
|
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_20,code=\"sm_21,compute_20\" -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
scrypt/kepler_kernel.o: scrypt/kepler_kernel.cu
|
|
|
|
|
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_30,code=\"sm_30,compute_30\" -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
scrypt/nv_kernel.o: scrypt/nv_kernel.cu
|
|
|
|
|
$(NVCC) $(JANSSON_INCLUDES) -I. @CUDA_INCLUDES@ @CUDA_CFLAGS@ -gencode=arch=compute_30,code=\"sm_30,compute_30\" -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
scrypt/titan_kernel.o: scrypt/titan_kernel.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) -gencode=arch=compute_35,code=\"sm_35,compute_35\" -o $@ -c $<
|
|
|
|
|
|
|
|
|
|
skein.o: skein.cu
|
|
|
|
|
$(NVCC) $(nvcc_FLAGS) --maxrregcount=64 -o $@ -c $<
|
|
|
|
|
|
