aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/Transforms/InstCombine/AMDGPU
AgeCommit message (Expand)AuthorFilesLines
31 hours[AMDGPU] Add dereferenceable retAttr to a call to llvm.amdgcn.implicitarg.ptr...Yoonseo Choi1-0/+78
3 daysValueTracking/AMDGPU: handle mbcnt in computeKnownBitsFromOperator (#183229)Ruiling, Song3-18/+97
12 days[AMDGPU] Use a general form of intrinsic for tensor load/store (#182334)Changpeng Fang1-185/+0
13 daysAMDGPU: Strip sign bit operations on llvm.amdgcn.trig.preop uses (#179712)Matt Arsenault1-0/+64
2026-02-17[NFC][AMDGPU] Use `zeroinitializer` instead of `null` for `ptr addrspace(2/3/...Shilei Tian2-2/+2
2026-02-10InstCombine: Use SimplifyDemandedFPClass on fmul (#177490)Matt Arsenault1-2/+2
2026-02-06[AMDGPU] Add DPP16 Row Share optimization for llvm.amdgcn.wave.shuffle (#177470)Domenic Nutile1-0/+250
2026-02-04AMDGPU: Fix incorrect fold of undef for llvm.amdgcn.trig.preop (#179025)Matt Arsenault1-28/+29
2026-01-12AMDGPU: Move test to correct placeMatt Arsenault3-0/+380
2025-12-15[AMDGPU] tensor_{load_to/store_from}_lds => ..._d2 simplification (#171540)Krzysztof Drewniak1-0/+185
2025-10-07[InstSimplify] Optimize maximumnum and minimumnum (#139581)Lewis Crawford1-28/+11
2025-09-25InstCombine: Check GEP operand is available (#160438)Matt Arsenault1-0/+19
2025-09-24[AMDGPU] Add the support for 45-bit buffer resource (#159702)Shilei Tian1-3/+3
2025-09-01[InstCombine] Strip leading zero indices from GEP (#155415)Nikita Popov1-10/+10
2025-08-04[AMDGPU] gfx1250 v_wmma_scale[16]_f32_16x16x128_f8f6f4 codegen (#152036)Stanislav Mekhanoshin1-0/+312
2025-07-21AMDGPU: Support v_wmma_f32_16x16x128_f8f6f4 on gfx1250 (#149684)Changpeng Fang1-0/+158
2025-07-16[InstCombine]PtrReplacer: Correctly handle select with unavailable operands (...Pierre van Houtryve1-0/+33
2025-06-24[AMDGPU] Fold fmed3 when inputs include infinity (#144824)Darren Wihandi1-0/+90
2025-06-24[ValueTracking] Return true for AddrSpaceCast in canCreateUndefOrPoison (#144...Wenju He1-0/+25
2025-06-23[Reland][InstCombine] Iterative replacement in PtrReplacer (#145410)Anshil Gandhi1-0/+79
2025-06-20Revert "[Reland][InstCombine] Iterative replacement in PtrReplacer" (#145137)Anshil Gandhi1-79/+0
2025-06-20[Reland][InstCombine] Iterative replacement in PtrReplacer (#144626)Anshil Gandhi1-0/+79
2025-06-18[AMDGPU] Support D16 folding for image.sample with multiple extractelement an...Harrison Hao1-0/+118
2025-06-16Revert "[InstCombine] Iterative replacement in PtrReplacer" (#144394)Anshil Gandhi1-79/+0
2025-06-16[InstCombine] Iterative replacement in PtrReplacer (#137215)Anshil Gandhi1-0/+79
2025-06-09[AMDGPU] Update failing test after #129897Jay Foad1-3/+3
2025-06-09[AMDGPU] Detect trivially uniform arguments in InstCombine (#129897)Jay Foad2-7/+168
2025-05-29AMDGPU: Make llvm.amdgcn.make.buffer.rsrc propagate poison (#141913)Matt Arsenault1-0/+21
2025-05-13[AMDGPU] Hoist readlane/readfirstlane through unary/binary operands (#129037)Pierre van Houtryve2-0/+907
2025-05-12AMDGPU: Use minimumnum/maximumnum for fmed3 with amdgpu-ieee=0Matt Arsenault1-109/+294
2025-05-12AMDGPU: Use minnum instead of maxnum for fmed3 src2-nan fold (#139531)Matt Arsenault1-8/+8
2025-05-12AMDGPU: Disable most fmed3 folds for strictfp (#139530)Matt Arsenault1-6/+6
2025-05-12AMDGPU: Add more tests for fmed3 instcombine folds (#139529)Matt Arsenault2-5/+289
2025-05-12AMDGPU: Reorganize fmed3 intrinsic instcombine tests (#139498)Matt Arsenault3-823/+861
2025-04-30[AMDGPU] Remove explicit datalayout from tests where not neededAlexander Richardson1-2/+0
2025-04-25AMDGPU: Add range to wavefrontsize intrinsic declaration (#136303)Matt Arsenault1-2/+2
2025-04-10[AMDGPU] InstCombine llvm.amdgcn.ds.bpermute with uniform arguments (#130133)Jay Foad2-0/+51
2025-04-02[Clang][AMDGPU] Add __builtin_amdgcn_cvt_off_f32_i4 (#133741)Juan Manuel Martinez Caamaño1-0/+183
2025-03-18AMDGPU: Replace unused permlane inputs with poison instead of undef (#131288)Matt Arsenault1-4/+4
2025-03-18AMDGPU: Replace unused update.dpp inputs with poison instead of undef (#131287)Matt Arsenault1-2/+2
2025-03-18AMDGPU: Replace unused export inputs with poison instead of undef (#131286)Matt Arsenault1-21/+21
2025-03-14AMDGPU: Make fma_legacy intrinsic propagate poison (#131063)Matt Arsenault1-0/+24
2025-03-14AMDGPU: Make fmul_legacy intrinsic propagate poison (#131062)Matt Arsenault1-0/+16
2025-03-14AMDGPU: Make ballot intrinsic propagate poison (#131061)Matt Arsenault1-0/+16
2025-03-14AMDGPU: Make fmed3 intrinsic propagate poison (#131060)Matt Arsenault1-0/+24
2025-03-14AMDGPU: Make cvt_pknorm and cvt_pk intrinsics propagate poison (#131059)Matt Arsenault1-0/+104
2025-03-13AMDGPU: Make frexp_exp and frexp_mant intrinsics propagate poison (#130915)Matt Arsenault1-0/+16
2025-03-13AMDGPU: Make sqrt and rsq intrinsics propagate poison (#130914)Matt Arsenault1-0/+24
2025-03-13AMDGPU: Make rcp intrinsic propagate poison (#130913)Matt Arsenault1-0/+8
2025-03-09InstCombine: Fix a crash in `PointerReplacer` when constructing a new PHI (#1...Changpeng Fang1-0/+42
generated by cgit v1.1 at 2026-03-05 03:40:52 +0000