-
Notifications
You must be signed in to change notification settings - Fork 4.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Optimize scalar conversions with AVX512 #84384
Optimize scalar conversions with AVX512 #84384
Commits on Jun 18, 2023
-
fixing the JITDbl2Ulng helper function. The new AVX512 instruction vc…
…vtsd2usi uses ulong.max_value to show FPE for negative, NAN and ulong_max + 1 values.
Configuration menu - View commit details
-
Copy full SHA for 7d764be - Browse repository at this point
Copy the full SHA 7d764beView commit details -
Making changes to the library test case expected output based on the …
…architecture. This is because we have changed the JITDbl2Ulng helper function to mimic the new IEEE compliant AVX512 instruction vcvtsd2usi. In the process, we needed to update the library test case because the default Floating Point Error (FPE) value for the new instruction is different from the default MSVC FPE value i.e. 0.
Configuration menu - View commit details
-
Copy full SHA for f50408b - Browse repository at this point
Copy the full SHA f50408bView commit details -
Fixing the JITDbl2Ulng helper function. Also making sure that we are …
…not changing the library test case but the API to make sure NaN cases are handled.
Configuration menu - View commit details
-
Copy full SHA for f018095 - Browse repository at this point
Copy the full SHA f018095View commit details -
Configuration menu - View commit details
-
Copy full SHA for ffe97cd - Browse repository at this point
Copy the full SHA ffe97cdView commit details -
Adding a truncate function to the Dbl2Ulng helper to make sure we avo…
…id handling edge cases (-1,0) separately inside the helper.
Configuration menu - View commit details
-
Copy full SHA for a8ee861 - Browse repository at this point
Copy the full SHA a8ee861View commit details -
Configuration menu - View commit details
-
Copy full SHA for bbd8a8b - Browse repository at this point
Copy the full SHA bbd8a8bView commit details -
Configuration menu - View commit details
-
Copy full SHA for a21a077 - Browse repository at this point
Copy the full SHA a21a077View commit details -
Configuration menu - View commit details
-
Copy full SHA for 1e3415a - Browse repository at this point
Copy the full SHA 1e3415aView commit details -
Configuration menu - View commit details
-
Copy full SHA for c788c67 - Browse repository at this point
Copy the full SHA c788c67View commit details -
merging with main. Picking up hwintrinsiclistxarh from main
trying to return EA_4BYTE for INS_vcvttss2usi to make sure that we read dword and not qword for float to ulong
Configuration menu - View commit details
-
Copy full SHA for fbb2a90 - Browse repository at this point
Copy the full SHA fbb2a90View commit details -
Configuration menu - View commit details
-
Copy full SHA for 9fece01 - Browse repository at this point
Copy the full SHA 9fece01View commit details -
Splitting vcvttss2usi to vcvttss2usi32 and vcvttss2usi64. Also adding…
… a special handling for vcvttss2usi64 to make sure we read only dword instead of qword for float to ulong conversion
Configuration menu - View commit details
-
Copy full SHA for b40cd8e - Browse repository at this point
Copy the full SHA b40cd8eView commit details -
Configuration menu - View commit details
-
Copy full SHA for 710026e - Browse repository at this point
Copy the full SHA 710026eView commit details -
removing unused code and correcting throughput and latency informatio…
…n for vcvttsd2usi, vcvttusi2sd32/64
Configuration menu - View commit details
-
Copy full SHA for 75e6acf - Browse repository at this point
Copy the full SHA 75e6acfView commit details -
correcting throughput and latency for vcvttss2usi32 and placing it wi…
…th other similar instructions
Configuration menu - View commit details
-
Copy full SHA for e15be4b - Browse repository at this point
Copy the full SHA e15be4bView commit details -
Configuration menu - View commit details
-
Copy full SHA for 10e2876 - Browse repository at this point
Copy the full SHA 10e2876View commit details -
Configuration menu - View commit details
-
Copy full SHA for 9463173 - Browse repository at this point
Copy the full SHA 9463173View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4f7bb67 - Browse repository at this point
Copy the full SHA 4f7bb67View commit details -
updating code for github comments. Using compIsaSupportedDebugOnly fo…
…r nowayasserts and also checking for float and doubel both in lowercast for overflow and conversion to ulong
Configuration menu - View commit details
-
Copy full SHA for a99725c - Browse repository at this point
Copy the full SHA a99725cView commit details -
reverting to original checks for ISA supported Debug only because the…
…y are not available in release mode
Configuration menu - View commit details
-
Copy full SHA for 44390b2 - Browse repository at this point
Copy the full SHA 44390b2View commit details -
Configuration menu - View commit details
-
Copy full SHA for 2f20ef3 - Browse repository at this point
Copy the full SHA 2f20ef3View commit details -
Configuration menu - View commit details
-
Copy full SHA for b7dff8a - Browse repository at this point
Copy the full SHA b7dff8aView commit details -
combine the 2 nodes GT_CAST(GT_CAST(TYP_ULONG, TYP_DOUBLE), TYP_FLOAT…
…) into a single node i.e. GT_CAST(TYP_ULONG, TYP_FLOAT)
Configuration menu - View commit details
-
Copy full SHA for 9622f78 - Browse repository at this point
Copy the full SHA 9622f78View commit details -
merging with main and updating hwintrinsiclistxarch to take into cons…
…ideration 32bit and 64 bit version of vcvttss2usi.
Configuration menu - View commit details
-
Copy full SHA for d3b542f - Browse repository at this point
Copy the full SHA d3b542fView commit details
Commits on Jun 19, 2023
-
Changing noway_assert to assert to make sure compOpportunisticallyDep…
…endsOn only runs in debug mode.
Configuration menu - View commit details
-
Copy full SHA for 8343e18 - Browse repository at this point
Copy the full SHA 8343e18View commit details -
Configuration menu - View commit details
-
Copy full SHA for e456763 - Browse repository at this point
Copy the full SHA e456763View commit details
Commits on Jun 20, 2023
-
Changing compOpportunisticallyDependsOn to compIsaSupportedDebugOnly …
…in asserts aka code review changes
Configuration menu - View commit details
-
Copy full SHA for fdb28c6 - Browse repository at this point
Copy the full SHA fdb28c6View commit details
Commits on Jun 22, 2023
-
Making code review changes. Moving around the comOpportunisticallyDep…
…endsOn checks to make sure they are ran only if we need AVX512. These checks being costly, moving them to the innermost checks in nested if checks.
Configuration menu - View commit details
-
Copy full SHA for e9ff179 - Browse repository at this point
Copy the full SHA e9ff179View commit details
Commits on Jun 23, 2023
-
Configuration menu - View commit details
-
Copy full SHA for db2a0cb - Browse repository at this point
Copy the full SHA db2a0cbView commit details -
Configuration menu - View commit details
-
Copy full SHA for 167b563 - Browse repository at this point
Copy the full SHA 167b563View commit details -
Configuration menu - View commit details
-
Copy full SHA for b02a96c - Browse repository at this point
Copy the full SHA b02a96cView commit details
Commits on Jun 30, 2023
-
Configuration menu - View commit details
-
Copy full SHA for fc0d127 - Browse repository at this point
Copy the full SHA fc0d127View commit details -
Configuration menu - View commit details
-
Copy full SHA for 9b56b86 - Browse repository at this point
Copy the full SHA 9b56b86View commit details -
Configuration menu - View commit details
-
Copy full SHA for 930c473 - Browse repository at this point
Copy the full SHA 930c473View commit details -
Configuration menu - View commit details
-
Copy full SHA for b2ae110 - Browse repository at this point
Copy the full SHA b2ae110View commit details -
Configuration menu - View commit details
-
Copy full SHA for 0439e28 - Browse repository at this point
Copy the full SHA 0439e28View commit details -
Configuration menu - View commit details
-
Copy full SHA for 2166ae5 - Browse repository at this point
Copy the full SHA 2166ae5View commit details
Commits on Jul 5, 2023
-
Configuration menu - View commit details
-
Copy full SHA for e2a6029 - Browse repository at this point
Copy the full SHA e2a6029View commit details
Commits on Jul 14, 2023
-
Configuration menu - View commit details
-
Copy full SHA for 715fc7e - Browse repository at this point
Copy the full SHA 715fc7eView commit details
Commits on Jul 15, 2023
-
Configuration menu - View commit details
-
Copy full SHA for dc6e41a - Browse repository at this point
Copy the full SHA dc6e41aView commit details
Commits on Jul 16, 2023
-
Configuration menu - View commit details
-
Copy full SHA for b1a31aa - Browse repository at this point
Copy the full SHA b1a31aaView commit details