Skip to content

Pull requests: llvm/llvm-project

New pull request New
Clear current search query, filters, and sorts
167 Open 1,697 Closed
167 Open 1,697 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[LoadStoreVectorizer] Fill gaps in load/store chains to enable vectorization backend:NVPTX llvm:analysis Includes value tracking, cost tables and constant folding llvm:transforms vectorizers
#159388 opened Sep 17, 2025 by dakersnar Loading… updated Dec 2, 2025
100
VectorCombine: Improve the insert/extract fold in the narrowing case backend:AMDGPU llvm:transforms llvm:vectorcombine vectorizers
#168820 opened Nov 20, 2025 by nhaehnle Loading… updated Dec 2, 2025
6
VectorCombine: Fold chains of shuffles fed by length-changing shuffles backend:AMDGPU llvm:transforms llvm:vectorcombine vectorizers
#168819 opened Nov 20, 2025 by nhaehnle Loading… updated Dec 1, 2025
7
[LV] Support argmin/argmax with strict predicates. llvm:analysis Includes value tracking, cost tables and constant folding llvm:transforms vectorizers
#170223 opened Dec 1, 2025 by fhahn Loading… updated Dec 1, 2025
2
[VPlan] Combine LiveIns fields into MapVector (NFC) llvm:transforms vectorizers
#170220 opened Dec 1, 2025 by artagnon Loading… updated Dec 1, 2025
2
[VPlan] Explicitly unoll replicate-regions without live-outs by VF. backend:RISC-V backend:SystemZ llvm:transforms vectorizers
#170212 opened Dec 1, 2025 by fhahn Loading… updated Dec 1, 2025
1
[VPlan] Replicate VPScalarIVStepsRecipe by VF outside replicate regions. backend:RISC-V backend:SystemZ llvm:transforms vectorizers
#170053 opened Nov 30, 2025 by fhahn Loading… updated Dec 1, 2025
1
[VectorCombine] Fold permute of intrinsics into intrinsic of permutes: shuffle(intrinsic, poison/undef) -> intrinsic(shuffle) llvm:transforms llvm:vectorcombine vectorizers
#170052 opened Nov 30, 2025 by kuroyukiasuna Loading… updated Dec 1, 2025
1
5
[VPlan] Replace ExtractLast(Elem|LanePerPart) with ExtractLast(Lane/Part) backend:RISC-V llvm:transforms vectorizers
#164124 opened Oct 18, 2025 by fhahn Loading… updated Dec 1, 2025
70
[VPlan] Extract reverse operation for reverse accesses backend:PowerPC backend:RISC-V llvm:transforms vectorizers
#146525 opened Jul 1, 2025 by Mel-Chen Loading… updated Dec 1, 2025
116
[LV][NFC] Remove unnecessary multiply in expandVPWidenIntOrFpInduction backend:RISC-V llvm:transforms vectorizers
#170159 opened Dec 1, 2025 by david-arm Loading… updated Dec 1, 2025
3
[VPlan] Sink predicated stores with complementary masks. llvm:transforms vectorizers
#168771 opened Nov 19, 2025 by fhahn Loading… updated Dec 1, 2025
7
[LV] Convert gather loads with invariant stride into strided loads backend:RISC-V llvm:transforms vectorizers
#147297 opened Jul 7, 2025 by Mel-Chen Loading… updated Dec 1, 2025
66
[LV] Use forced cost once for whole interleave group in legacy costmodel llvm:transforms vectorizers
#168270 opened Nov 16, 2025 by fhahn Loading… updated Dec 1, 2025
3
[NFC][LV]: Differentiate between Pred and Unpred masked operations. llvm:transforms vectorizers
#169509 opened Nov 25, 2025 by hassnaaHamdi Loading… updated Dec 1, 2025
8
[VPlan] Use BlockFrequencyInfo in getPredBlockCostDivisor backend:RISC-V llvm:transforms vectorizers
#158690 opened Sep 15, 2025 by lukel97 Loading… updated Dec 1, 2025
52
[VPlan] Create header phis once, after constructing VPlan0 (NFC). llvm:transforms vectorizers
#168291 opened Nov 16, 2025 by fhahn Loading… updated Nov 30, 2025
4
[LoadStoreVectorizer] Allow redundant stores backend:AMDGPU llvm:globalisel llvm:transforms vectorizers
#169946 opened Nov 28, 2025 by cmc-rep Loading… updated Nov 30, 2025
4
[SLP] Loop aware cost model/tree building backend:AMDGPU backend:RISC-V backend:SystemZ llvm:transforms vectorizers
#150450 opened Jul 24, 2025 by alexey-bataev Loading… updated Nov 30, 2025
4
[SLP] Support for copyables in the reduced values backend:RISC-V llvm:transforms vectorizers
#153589 opened Aug 14, 2025 by alexey-bataev Loading… updated Nov 28, 2025
5
[SLP]Exclude non-profitable subtrees. backend:NVPTX backend:RISC-V llvm:transforms vectorizers
#162018 opened Oct 5, 2025 by alexey-bataev Loading… updated Nov 28, 2025
8
[LV] Transform to handle exits in the scalar loop llvm:transforms vectorizers
#148626 opened Jul 14, 2025 by huntergr-arm Loading… updated Nov 28, 2025
47
[SLP]Enable float point math ops as copyables elements. llvm:transforms vectorizers
#169857 opened Nov 27, 2025 by alexey-bataev Loading… updated Nov 28, 2025
5
[LV] Decide early between partial reduce and a regular reduction based on cost-model llvm:transforms vectorizers
#169898 opened Nov 28, 2025 by sushgokh Loading… updated Nov 28, 2025
2
[VPlan] Support struct return types for widen intrinsics (NFC). llvm:analysis Includes value tracking, cost tables and constant folding llvm:ir llvm:transforms vectorizers
#165218 opened Oct 27, 2025 by arcbbb Loading… updated Nov 28, 2025
15
ProTip! Add no:assignee to see everything that’s not assigned.