aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/Analysis/UniformityAnalysis
AgeCommit message (Expand)AuthorFilesLines
2 days[AMDGPU] Mark address space cast from private to flat as divergent if target ...Shilei Tian2-0/+49
4 days[AMDGPU] gfx1250 v_wmma_scale[16]_f32_16x16x128_f8f6f4 codegen (#152036)Stanislav Mekhanoshin1-0/+18
7 days[AMDGPU] gfx1250 v_permlane_* instructions (#151749)Stanislav Mekhanoshin1-0/+35
2025-07-21AMDGPU: Support v_wmma_f32_16x16x128_f8f6f4 on gfx1250 (#149684)Changpeng Fang1-0/+9
2025-07-15AMDGPU: Remove a non-existent wmma instruction from gfx1250 (#148989)Changpeng Fang1-8/+0
2025-07-15AMDGPU: Support intrinsic selection for gfx1250 wmma instructions (#148957)Changpeng Fang1-0/+240
2025-06-29AMDGPU: Implement intrinsic/builtins for gfx1250 load transpose instructions ...Changpeng Fang1-0/+72
2025-05-29[Uniformity] Fixed control-div early stop (#139667)Junjie Gu6-2/+392
2025-05-08[AMDGPU] Add missing intrinsic declaration to intrinsics.ll. NFC. (#138954)Stanislav Mekhanoshin1-0/+1
2025-04-30[CodeGen] Port MachineUniformityAnalysis to new pass manager (#137578)paperchalice18-45/+63
2025-02-26[AMDGPU] Do not allow M0 as v_readfirstlane_b32 dst (#128851)Pierre van Houtryve2-5/+5
2025-02-20[AMDGPU] Add llvm.amdgcn.dead intrinsic (#123190)Diana Picus1-1/+8
2025-01-24MachineUniformityAnalysis: Improve isConstantOrUndefValuePhi (#112866)Petar Avramovic3-20/+20
2025-01-07[NVPTX] Switch front-ends and tests to ptx_kernel cc (#120806)Alex MacLean4-22/+8
2024-12-02AMDGPU: Allow f16/bf16 for DS_READ_TR16_B64 gfx950 builtins (#118297)Matt Arsenault1-0/+22
2024-11-25AMDGPU: Add support for load transpose instructions for gfx950 (#117378)Matt Arsenault1-0/+44
2024-11-22AMDGPU: Add v_permlane16_swap_b32 and v_permlane32_swap_b32 for gfx950 (#117260)Matt Arsenault1-0/+16
2024-11-22AMDGPU: Add v_smfmac_f32_32x32x64_fp8_fp8 for gfx950 (#117259)Matt Arsenault1-0/+9
2024-11-22AMDGPU: Add v_smfmac_f32_32x32x32x64_fp8_bf8 for gfx950 (#117258)Matt Arsenault1-0/+9
2024-11-22AMDGPU: Add v_smfmac_f32_32x32x64_bf8_fp8 for gfx950 (#117257)Matt Arsenault1-0/+9
2024-11-22AMDGPU: Add v_smfmac_f32_32x32x64_bf8_bf8 for gfx950 (#117256)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_smfmac_f32_16x16x128_fp8_fp8 for gfx950 (#117235)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_smfmac_f32_16x16x128_fp8_bf8 for gfx950 (#117234)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_smfmac_f32_16x16x128_bf8_fp8 for gfx950 (#117233)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_smfmac_f32_16x16x128_bf8_bf8 for gfx950 (#117232)Matt Arsenault1-0/+8
2024-11-21AMDGPU: Add v_smfmac_i32_32x32x64_i8 for gfx950 (#117214)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_smfmac_f32_16x16x64_bf16 for gfx950 (#117211)Matt Arsenault1-0/+10
2024-11-21AMDGPU: Add v_smfmac_f32_32x32x32_f16 for gfx950 (#117205)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_smfmac_f32_16x16x64_f16 for gfx950 (#117202)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_mfma_f32_16x16x32_bf16 for gfx950 (#117053)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_mfma_i32_32x32x32_i8 for gfx950 (#117052)Matt Arsenault1-0/+9
2024-11-21AMDGPU: Add v_mfma_i32_16x16x64_i8 for gfx950 (#116728)Matt Arsenault1-0/+8
2024-11-21AMDGPU: Define v_mfma_f32_{16x16x128|32x32x64}_f8f6f4 instructions (#116723)Matt Arsenault1-0/+20
2024-11-18AMDGPU: Define v_mfma_f32_32x32x16_bf16 for gfx950 (#116679)Matt Arsenault1-0/+8
2024-11-18AMDGPU: Add first gfx950 mfma instructions (#116312)Matt Arsenault1-0/+17
2024-10-12[LLVM] New NoDivergenceSource function attribute (#111832)Tim Renouf1-0/+16
2024-09-27[AMDGPU] Overload resource descriptor in image intrinsics. (#107255)sstipano1-43/+43
2024-08-06AMDGPU: Add some leaf intrinsics to isAlwaysUniform (#101925)Matt Arsenault1-0/+33
2024-08-05[AMDGPU] Mark workgroup_id intrinsics always uniform (#102042)Stanislav Mekhanoshin1-0/+27
2024-07-18AMDGPU: Add back half and bfloat support for global_load_tr16 pats (#99540)Changpeng Fang1-0/+36
2024-06-26[AMDGPU] Extend permlane16, permlanex16 and permlane64 intrinsic lowering for...Vikram Hegde1-6/+6
2024-06-25[AMDGPU] Extend readlane, writelane and readfirstlane intrinsic lowering for ...Vikram Hegde1-3/+3
2024-06-18AMDGPU: Support local atomicrmw fmin/fmax for float/double (#95590)Matt Arsenault1-4/+5
2024-06-10[RFC][AMDGPU] Remove old llvm.amdgcn.buffer.* and tbuffer intrinsics (#93801)Jay Foad1-100/+0
2024-05-29[AMDGPU] Fix filecheck annotation typosJay Foad1-1/+1
2024-05-06[AMDGPU] don't mark control-flow intrinsics as convergent (#90026)Sameer Sahasrabuddhe3-26/+26
2024-03-25AMDGPU: Rename intrinsics and remove f16/bf16 versions for load transpose (#8...Changpeng Fang1-57/+13
2024-02-05[Analysis] Convert tests to opaque pointers (NFC)Nikita Popov3-6/+6
2024-01-30[AMDGPU]: Fix type signatures for wmma intrinsics, NFC (#80087)Changpeng Fang1-18/+18
2024-01-24[AMDGPU] Add GFX12 WMMA and SWMMAC instructions (#77795)Mirko BrkuĊĦanin1-18/+117
generated by cgit v1.1 at 2025-08-09 01:59:57 +0000