git
/
gcc
mirror of git://gcc.gnu.org/git/gcc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update ChangeLog.*

This commit is contained in:
Michael Meissner 2025-10-17 13:06:29 -04:00
parent 5fc9771c32
commit 6f8a483024
1 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
gcc/ChangeLog.float
View File

@ -1,3 +1,38 @@
==================== Branch work222-float, patch #338 ====================
Add unary, fma 16-bit floating point vector optimization.
2025-10-17 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/float16.cc (bfloat16_operation_as_v4sf): Add support for
vectorizing unary and fma 16-bit floating point.
(fp16_vectorization): Likewise.
* config/rs6000/float16.md (neg<mode>2, VFP16_HW iterator): Likewise.
(xor<mode>2, VFP16_HW iterator): Likewise.
(abs<mode>2, VFP16_HW iterator): Likewise.
(andc<mode>2, VFP16_HW iterator): Likewise.
(neg_<fp16_names><mode>2): Likewise.
(abs_<fp16_names><mode>2): Likewise.
(fma<fp16_names><mode>4): Likewise.
(fms<fp16_names><mode>4): Likewise.
(nfma<fp16_names><mode>4): Likewise.
(nfms<fp16_names><mode>4): Likewise.
* config/rs6000/rs6000-protos.h (FP16_ABS_BINARY): Likewise.
(FP16_NEG_BINARY,): Likewise.
==================== Branch work222-float, patch #338 ====================
Fix 16-bit floating point vector ordering.
2025-10-17 Michael Meissner <meissner@linux.ibm.com>
gcc/
* config/rs6000/float16.cd (fp16_vectorization): Fix 16-bit floating
point ordering.
==================== Branch work222-float, patch #337 was reverted ==================== ==================== Branch work222-float, patch #337 was reverted ====================
==================== Branch work222-float, patch #336 ==================== ==================== Branch work222-float, patch #336 ====================