NVBit-igprofile; index: 0; kernel_name: voidcudnn::cnn::im2col4d_kernel<float,long>(cudnn::cnn::im2col4d_params,cudnnConvolutionStruct,cudnnTensorStruct,floatconst*,float*); ctas: 1; instrs: 86776; FADD: 7008, FADD32I: 0, FCHK: 0, FCMP: 0, FFMA: 0, FFMA32I: 0, FMNMX: 0, FMUL: 0, FMUL32I: 0, FSEL: 0, FSET: 0, FSETP: 0, FSWZADD: 0, IPA: 0, MUFU: 620, RRO: 0, DADD: 0, DFMA: 0, DMNMX: 0, DMUL: 0, DSET: 0, DSETP: 0, HADD2: 0, HADD2_32I: 0, HFMA2: 0, HFMA2_32I: 0, HMUL2: 0, HMUL2_32I: 0, HSET2: 0, HSETP2: 0, IDP: 0, IDP4A: 0, BFE: 0, BFI: 0, BMSK: 0, BREV: 0, FLO: 0, IADD: 0, IADD3: 12248, IADD32I: 0, ICMP: 0, IMAD: 29676, IMAD32I: 0, IMADSP: 0, IMNMX: 0, IMUL: 0, IMUL32I: 0, ISCADD: 0, ISCADD32I: 0, ISET: 0, ISETP: 10788, LEA: 11592, LOP: 0, LOP3: 764, LOP32I: 0, PLOP3: 0, POPC: 0, SHF: 468, SHL: 0, SHR: 0, XMAD: 0, IMMA: 0, HMMA: 0, VABSDIFF: 0, VADD: 0, VMAD: 0, VMNMX: 0, VSET: 0, VSETP: 0, VSHL: 0, VSHR: 0, VABSDIFF4: 0, F2F: 0, F2I: 620, I2F: 620, I2I: 0, I2IP: 0, FRND: 0, MOV: 36, MOV32I: 0, PRMT: 0, SEL: 828, SGXT: 0, SHFL: 0, CSET: 0, CSETP: 0, PSET: 0, PSETP: 0, P2R: 0, R2P: 0, TEX: 0, TLD: 0, TLD4: 0, TMML: 0, TXA: 0, TXD: 0, TXQ: 0, TEXS: 0, TLD4S: 0, TLDS: 0, STP: 0, LD: 0, LDC: 0, LDG: 2268, LDL: 0, LDS: 0, ST: 0, STG: 2268, STL: 0, STS: 0, MATCH: 0, QSPC: 0, ATOM: 0, ATOMS: 0, RED: 0, CCTL: 0, CCTLL: 0, ERRBAR: 0, MEMBAR: 0, CCTLT: 0, SUATOM: 0, SULD: 0, SURED: 0, SUST: 0, BRA: 5184, BRX: 0, JMP: 0, JMX: 0, SSY: 0, SYNC: 0, CAL: 0, JCAL: 0, PRET: 0, RET: 0, BRK: 0, PBK: 0, CONT: 0, PCNT: 0, EXIT: 548, PEXIT: 0, LONGJMP: 0, PLONGJMP: 0, KIL: 0, BSSY: 108, BSYNC: 108, BREAK: 0, BMOV: 0, BPT: 0, IDE: 0, RAM: 0, RTT: 0, SAM: 0, RPCMOV: 0, WARPSYNC: 0, YIELD: 0, NANOSLEEP: 0, NOP: 0, CS2R: 0, S2R: 1024, LEPC: 0, B2R: 0, BAR: 0, R2B: 0, VOTE: 0, DEPBAR: 0, GETCRSPTR: 0, GETLMEMBASE: 0, SETCRSPTR: 0, SETLMEMBASE: 0, PMTRIG: 0, SETCTAID: 0, fp64: 0, fp32: 7008, fp16: 0, mma: 0, ld: 2268, pr: 10788, nodest: 8216, others: 58496, gppr: 78560, gp: 67772,
NVBit-igprofile; index: 1; kernel_name: voidexplicit_convolve_sgemm<float,int,128,6,7,3,3,5,0,false>(int,int,int,floatconst*,int,floatconst*,int,float*,kernel_conv_params,unsignedlonglong,int,unsignedlonglong,int,float,float,int,bool,floatconst*,floatconst*); ctas: 1; instrs: 785940; FADD: 4872, FADD32I: 0, FCHK: 0, FCMP: 0, FFMA: 524288, FFMA32I: 0, FMNMX: 0, FMUL: 3492, FMUL32I: 0, FSEL: 0, FSET: 0, FSETP: 1152, FSWZADD: 0, IPA: 0, MUFU: 0, RRO: 0, DADD: 0, DFMA: 0, DMNMX: 0, DMUL: 0, DSET: 0, DSETP: 0, HADD2: 0, HADD2_32I: 0, HFMA2: 0, HFMA2_32I: 0, HMUL2: 0, HMUL2_32I: 0, HSET2: 0, HSETP2: 0, IDP: 0, IDP4A: 0, BFE: 0, BFI: 0, BMSK: 0, BREV: 0, FLO: 0, IADD: 0, IADD3: 35952, IADD32I: 0, ICMP: 0, IMAD: 50096, IMAD32I: 0, IMADSP: 0, IMNMX: 256, IMUL: 0, IMUL32I: 0, ISCADD: 0, ISCADD32I: 0, ISET: 0, ISETP: 23584, LEA: 11232, LOP: 0, LOP3: 1536, LOP32I: 0, PLOP3: 0, POPC: 0, SHF: 12224, SHL: 0, SHR: 0, XMAD: 0, IMMA: 0, HMMA: 0, VABSDIFF: 0, VADD: 0, VMAD: 0, VMNMX: 0, VSET: 0, VSETP: 0, VSHL: 0, VSHR: 0, VABSDIFF4: 0, F2F: 0, F2I: 0, I2F: 0, I2I: 0, I2IP: 0, FRND: 0, MOV: 16672, MOV32I: 0, PRMT: 0, SEL: 512, SGXT: 0, SHFL: 0, CSET: 0, CSETP: 0, PSET: 0, PSETP: 0, P2R: 0, R2P: 0, TEX: 0, TLD: 0, TLD4: 0, TMML: 0, TXA: 0, TXD: 0, TXQ: 0, TEXS: 0, TLD4S: 0, TLDS: 0, STP: 0, LD: 0, LDC: 0, LDG: 11936, LDL: 0, LDS: 49152, ST: 0, STG: 3492, STL: 0, STS: 12288, MATCH: 0, QSPC: 0, ATOM: 0, ATOMS: 0, RED: 0, CCTL: 0, CCTLL: 0, ERRBAR: 0, MEMBAR: 0, CCTLT: 0, SUATOM: 0, SULD: 0, SURED: 0, SUST: 0, BRA: 9347, BRX: 0, JMP: 0, JMX: 0, SSY: 0, SYNC: 0, CAL: 0, JCAL: 0, PRET: 0, RET: 0, BRK: 0, PBK: 0, CONT: 0, PCNT: 0, EXIT: 289, PEXIT: 0, LONGJMP: 0, PLONGJMP: 0, KIL: 0, BSSY: 2304, BSYNC: 2304, BREAK: 0, BMOV: 0, BPT: 0, IDE: 0, RAM: 0, RTT: 0, SAM: 0, RPCMOV: 0, WARPSYNC: 0, YIELD: 0, NANOSLEEP: 0, NOP: 0, CS2R: 3328, S2R: 1792, LEPC: 0, B2R: 0, BAR: 3840, R2B: 0, VOTE: 0, DEPBAR: 0, GETCRSPTR: 0, GETLMEMBASE: 0, SETCRSPTR: 0, SETLMEMBASE: 0, PMTRIG: 0, SETCTAID: 0, fp64: 0, fp32: 532652, fp16: 0, mma: 0, ld: 61088, pr: 24736, nodest: 33864, others: 133600, gppr: 752076, gp: 727340,
