| Electronic Components Datasheet Search |
|
UM0434 Datasheet(PDF) 225 Page - STMicroelectronics |
|
|
|||||||||||||||||||||||||||||
UM0434 Datasheet(HTML) 225 Page - STMicroelectronics |
|
225 / 390 page ![]() Instruction pipeline and execution timing UM0434 226/391 8.7.1 SPE and embedded Floating-Point instruction timing The tables in this section show instruction timing for SPE and embedded floating-point APU instructions. Pipelined instructions are shown with cycles of total latency and throughput cycles. Divide instructions are not pipelined and block other instructions from executing during divide execution. Instruction pipelining is affected by the possibility of a floating-point instruction generating an exception. A load or store class instruction that follows an SPE FPU instruction stalls until it can be ensured that no previous instruction can generate a floating-point exception. This determination is based on which floating-point exception enable bits are set (FINVE, FOVFE, FUNFE, FDBZE, and FINXE) and at what point in the FPU pipeline an exception can be guaranteed to not occur. Invalid input operands are detected in the first stage of the pipeline, while underflow, overflow, and inexactness are determined later in the pipeline. Best overall performance occurs when either floating-point exceptions are disabled, or when load and store class instructions are scheduled such that previous floating-point instructions have already resolved the possibility of exceptional results. SPE integer simple instructions timing Instruction timing for SPE integer simple instructions is shown in Table 159. The table is sorted by opcode. These instructions are issued as a pair of operations. stwu, e_stwu 1 None Aligned stwux 1 None Aligned stwx 1 None Aligned subfc[o][.]1 None subfe[o][.]1 None subfic, e_subfic[.], se_subi[.]1 None subfme[o][.]1 None subfze[o][.]1 None subf[o][.], se_subf, se_sub 1None tw 3None twi 3None wrtee 2 Completion wrteei 2 Completion xori, e_xori[.]1 None xoris 1None xor[.]1 None Table 158. Instruction timing by mnemonic (continued) Mnemonic Latency Serialization Comments |
|
Link URL |
| Does ALLDATASHEET help your business so far? [ DONATE ] |
About Alldatasheet | Advertisement | Contact us | Privacy Policy | Link to Datasheet | Link Exchange | Manufacturer List All Rights Reserved©Alldatasheet.com |
| Russian : Alldatasheetru.com | Korean : Alldatasheet.co.kr | Spanish : Alldatasheet.es | French : Alldatasheet.fr | Italian : Alldatasheetit.com Portuguese : Alldatasheetpt.com | Polish : Alldatasheet.pl | Vietnamese : Alldatasheet.vn Indian : Alldatasheet.in | Mexican : Alldatasheet.com.mx | British : Alldatasheet.co.uk | New Zealand : Alldatasheet.co.nz |
|
Family Site : ic2ic.com |
icmetro.com |