[llvm-branch-commits] [clang] [llvm] [AMDGPU] Introduce a new generic target `gfx9-4-generic` (PR #115190)

2024-11-06 Thread Shilei Tian via llvm-branch-commits
@@ -775,6 +775,11 @@ let SubtargetPredicate = HasFP8Insts, is_gfx940_xdl = 1 in { defm V_MFMA_F32_32X32X16_FP8_FP8 : MAIInst<"v_mfma_f32_32x32x16_fp8_fp8", "F32_I64_X16",int_amdgcn_mfma_f32_32x32x16_fp8_fp8>; } // End SubtargetPredicate = HasFP8Insts, is_gfx940_xdl = 1

[llvm-branch-commits] [clang] [llvm] [AMDGPU] Introduce a new generic target `gfx9-4-generic` (PR #115190)

2024-11-06 Thread Shilei Tian via llvm-branch-commits
@@ -466,6 +470,7 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T, case GK_GFX942: case GK_GFX941: case GK_GFX940: +case GK_GFX9_4_GENERIC: shiltian wrote: This needs to be updated as well https://github.com/llvm/llvm-proje

[llvm-branch-commits] [llvm] AMDGPU: Handle gfx950 valu write vdst + permlane read hazard (PR #117287)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117287 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle gfx950 valu write vdst + permlane read hazard (PR #117287)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117287 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for load transpose instructions for gfx950 (PR #117378)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117378 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for load transpose instructions for gfx950 (PR #117378)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117378 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scale_[f16|f32]_fp8 of gfx950. (PR #117380)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117380 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add MC support for gfx950 V_BITOP3_B32/B16 (PR #117379)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117379 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scale_[f16|f32]_fp8 of gfx950. (PR #117380)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117380 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add MC support for gfx950 V_BITOP3_B32/B16 (PR #117379)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117379 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{fp8|bf8}_f32 of gfx950. (PR #117382)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117382 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk32_{bf|f}16_{bf|fp}6 of gfx950. (PR #117591)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117591 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk32_f32_[fp|bf]6 of gfx950 (PR #117590)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
@@ -1552,7 +1558,9 @@ def FeatureISAVersion9_5_Common : FeatureSet< FeatureBitOp3Insts, FeatureFP8ConversionScaleInsts, FeatureBF8ConversionScaleInsts, - FeatureFP4ConversionScaleInsts + FeatureFP4ConversionScaleInsts, + FeatureFP6BF6ConversionScaleInsts, + Fea

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk32_{bf|f}16_{bf|fp}6 of gfx950. (PR #117591)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117591 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support v_cvt_scalef32_pk32_{bf|f}6_{bf|fp}16 for gfx950 (PR #117592)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
@@ -408,11 +408,23 @@ def FeatureFP6BF6ConversionScaleInsts : SubtargetFeature<"fp6bf6-cvt-scale-insts "Has fp6 and bf6 conversion scale instructions" >; +def FeatureF16BF16ToFP6BF6ConversionScaleInsts : SubtargetFeature<"f16bf16-to-fp6bf6-cvt-scale-insts", + "HasF16BF16T

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support v_cvt_scalef32_pk32_{bf|f}6_{bf|fp}16 for gfx950 (PR #117592)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117592 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support v_cvt_scalef32_pk32_{bf|f}6_{bf|fp}16 for gfx950 (PR #117592)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117592 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_fp4_{f|bf}16 on gfx950. (PR #117594)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117594 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{bf|f}16_{bf|fp}8 of gfx950. (PR #117593)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117593 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_fp4_{f|bf}16 on gfx950. (PR #117594)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117594 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{bf|f}16_{bf|fp}8 of gfx950. (PR #117593)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117593 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for v_ashr_pk_i8/u8_i32 instructions for gfx950 (PR #117596)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117596 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for v_ashr_pk_i8/u8_i32 instructions for gfx950 (PR #117596)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117596 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for v_dot2_f32_bf16 instruction for gfx950 (PR #117597)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117597 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for v_dot2_f32_bf16 instruction for gfx950 (PR #117597)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117597 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for v_dot2c_f32_bf16 instruction for gfx950 (PR #117598)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117598 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support v_cvt_scalef32_2xpk16_{bf|fp}6_f32 for gfx950. (PR #117595)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117595 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support v_cvt_scalef32_2xpk16_{bf|fp}6_f32 for gfx950. (PR #117595)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117595 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support buffer_atomic_pk_add_bf16 for gfx950 (PR #117599)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add minimum3/maximum3 pkf16 for gfx950 encodings (PR #117601)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117601 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add encodings for minimum3/maximum3 f32 for gfx950 (PR #117600)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add encodings for minimum3/maximum3 f32 for gfx950 (PR #117600)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117600 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Support buffer_atomic_pk_add_bf16 for gfx950 (PR #117599)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117599 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add minimum3/maximum3 pkf16 for gfx950 encodings (PR #117601)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117601 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle vcmpx+permalane gfx950 hazard (PR #117286)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117286 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle vcmpx+permalane gfx950 hazard (PR #117286)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117286 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle gfx950 valu write vdst + permlane read hazard (PR #117287)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
@@ -2551,8 +2551,34 @@ int GCNHazardRecognizer::checkPermlaneHazards(MachineInstr *MI) { return isVCmpXWritesExec(*TII, *TRI, MI); }; - const int NumWaitStates = 4; - return NumWaitStates - getWaitStatesSince(IsVCmpXWritesExecFn, NumWaitStates); + auto IsVALUFn = []

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_f32_[fp|bf]8 of gfx950. (PR #117383)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117383 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_f32_[fp|bf]8 of gfx950. (PR #117383)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117383 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{fp8|bf8}_f32 of gfx950. (PR #117382)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117382 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_f32_[fp|bf]8 of gfx950. (PR #117383)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117383 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{fp|bf}8_{f|bf}16 of gfx950. (PR #117384)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117384 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_f32_[fp|bf]8 of gfx950. (PR #117383)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117383 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{f|bf}16_fp4 of gfx950. (PR #117418)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117418 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scale_fp4<->f32 of gfx950. (PR #117417)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117417 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scale_fp4<->f32 of gfx950. (PR #117417)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117417 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{fp|bf}8_{f|bf}16 of gfx950. (PR #117384)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117384 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_pk_{f|bf}16_fp4 of gfx950. (PR #117418)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117418 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add support for v_dot2c_f32_bf16 instruction for gfx950 (PR #117598)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117598 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Legalize fminimum and fmaximum f32 for gfx950 (PR #117634)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117634 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Legalize fminimum and fmaximum f32 for gfx950 (PR #117634)

2024-11-25 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117634 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_mfma_f32_16x16x32_bf16 for gfx950 (PR #117053)

2024-11-20 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117053 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_mfma_i32_32x32x32_i8 for gfx950 (PR #117052)

2024-11-20 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117052 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_mfma_f32_16x16x32_bf16 for gfx950 (PR #117053)

2024-11-20 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117053 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_mfma_i32_32x32x32_i8 for gfx950 (PR #117052)

2024-11-20 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117052 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Simplify demanded bits on readlane/writeline index arguments (PR #117963)

2024-11-27 Thread Shilei Tian via llvm-branch-commits
@@ -450,6 +450,37 @@ static bool isTriviallyUniform(const Use &U) { return false; } +/// Simplify a lane index operand (e.g. llvm.amdgcn.readlane src1). +/// +/// The instruction only reads the low 5 bits for wave32, and 6 bits for wave64. +bool GCNTTIImpl::simplifyDemanded

[llvm-branch-commits] [clang] [llvm] AMDGPU: Define v_mfma_f32_32x32x16_bf16 for gfx950 (PR #116679)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
@@ -437,6 +437,8 @@ TARGET_BUILTIN(__builtin_amdgcn_cvt_sr_fp8_f32, "ifiiIi", "nc", "fp8-conversion- TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_16x16x32_f16, "V4fV8hV8hV4fIiIiIi", "nc", "gfx950-insts") TARGET_BUILTIN(__builtin_amdgcn_mfma_f32_32x32x16_f16, "V16fV8hV8hV16fIiIiIi"

[llvm-branch-commits] [clang] [llvm] AMDGPU: Define v_mfma_f32_32x32x16_bf16 for gfx950 (PR #116679)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116679 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Define v_mfma_f32_32x32x16_bf16 for gfx950 (PR #116679)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
@@ -3117,6 +3117,8 @@ def int_amdgcn_cvt_sr_fp8_f32 : ClangBuiltin<"__builtin_amdgcn_cvt_sr_fp8_f32">, defset list AMDGPUMFMAIntrinsics950 = { def int_amdgcn_mfma_f32_16x16x32_f16 : AMDGPUMfmaIntrinsic; def int_amdgcn_mfma_f32_32x32x16_f16 : AMDGPUMfmaIntrinsic; +

[llvm-branch-commits] [llvm] AMDGPU: Define v_mfma_f32_{16x16x128|32x32x64}_f8f6f4 instructions (PR #116723)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
@@ -1397,6 +1397,19 @@ The AMDGPU backend implements the following LLVM IR intrinsics. used by hardware to control active lanes when used in EXEC register. For example, ballot

[llvm-branch-commits] [llvm] AMDGPU: Handle gfx950 global_load_lds_* instructions (PR #116680)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
@@ -1980,6 +1985,10 @@ defm GLOBAL_LOAD_LDS_USHORT : FLAT_Real_AllAddr_LDS <0x028, 0x12>; defm GLOBAL_LOAD_LDS_SSHORT : FLAT_Real_AllAddr_LDS <0x029, 0x13>; defm GLOBAL_LOAD_LDS_DWORD : FLAT_Real_AllAddr_LDS <0x02a, 0x14>; +defm GLOBAL_LOAD_LDS_DWORDX3 : FLAT_Real_AllAddr_LD

[llvm-branch-commits] [llvm] AMDGPU: Handle gfx950 global_load_lds_* instructions (PR #116680)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116680 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle gfx950 global_load_lds_* instructions (PR #116680)

2024-11-18 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116680 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Optimize mfma_scale intrinsics with 0 inputs (PR #116724)

2024-11-19 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116724 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_mfma_i32_16x16x64_i8 for gfx950 (PR #116728)

2024-11-19 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116728 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Optimize mfma_scale intrinsics with 0 inputs (PR #116724)

2024-11-19 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116724 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_mfma_i32_16x16x64_i8 for gfx950 (PR #116728)

2024-11-19 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116728 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add subtarget features for minimum3/maximum3 instructions (PR #116308)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116308 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add subtarget features for minimum3/maximum3 instructions (PR #116308)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116308 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_prng_b32 instruction for gfx950 (PR #116310)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116310 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Increase the LDS size to support to 160 KB for gfx950 (PR #116309)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116309 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Increase the LDS size to support to 160 KB for gfx950 (PR #116309)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116309 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add V_CVT_F32_BF16 for gfx950 (PR #116311)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/116311 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Add V_CVT_F32_BF16 for gfx950 (PR #116311)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116311 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Add v_prng_b32 instruction for gfx950 (PR #116310)

2024-11-14 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/116310 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & CodeGen support for v_cvt_scalef32_pk_{bf|f}16_{bf|fp}8 for gfx950 (PR #117793)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117793 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtin & CodeGen support for v_cvt_scalef32_pk_fp4_{f|bf}16 for gfx950 (PR #117794)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117794 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_sr_{f16|bf16}_f32 instructions (PR #117796)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117796 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for V_CVT_SCALE_SR_FP4 instructions (PR #117795)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117795 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for V_CVT_SCALE_SR_FP4 instructions (PR #117795)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117795 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & CodeGen support for v_cvt_scalef32_pk_{bf|f}16_{bf|fp}8 for gfx950 (PR #117793)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117793 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtin & CodeGen support for v_cvt_scalef32_pk_fp4_{f|bf}16 for gfx950 (PR #117794)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117794 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_sr_{f16|bf16}_f32 instructions (PR #117796)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117796 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtin & CodeGen support for v_cvt_scalef32_sr_pk_fp4 instructions (PR #117798)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117798 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtin & CodeGen support for v_cvt_scalef32_sr_pk_fp4 instructions (PR #117798)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117798 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_sr_{bf8|fp8}_{f16|bf16|f32} (PR #117797)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117797 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: MC support for v_cvt_scalef32_sr_{bf8|fp8}_{f16|bf16|f32} (PR #117797)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117797 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scale_fp4<->f32 for gfx950 (PR #117743)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117743 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scalef32_pk_{fp8|bf8}_f32 for gfx950 (PR #117740)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117740 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle f32 minimum3/maximum3 pattern for gfx950 (PR #117737)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117737 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Handle f32 minimum3/maximum3 pattern for gfx950 (PR #117737)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. wonder why it is called `v_maximum3`. https://github.com/llvm/llvm-project/pull/117737 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailma

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for: v_cvt_scalef32_[f16|f32]_[bf8|fp8] (PR #117739)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117739 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for: v_cvt_scalef32_[f16|f32]_[bf8|fp8] (PR #117739)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117739 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [llvm] AMDGPU: Make v2f16 minimum/maximum legal for gfx950 (PR #117738)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117738 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scalef32_pk_{fp8|bf8}_f32 for gfx950 (PR #117740)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117740 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] Builtins & Codegen support for v_cvt_scalef32_pk_{fp|bf}8_{f|bf}16 for gfx950 (PR #117742)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
@@ -15,9 +15,10 @@ typedef unsigned int uint2 __attribute__((ext_vector_type(2))); typedef half __attribute__((ext_vector_type(2))) half2; typedef short __attribute__((ext_vector_type(2))) short2; typedef float __attribute__((ext_vector_type(2))) float2; +typedef __bf16 __attr

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scalef32_pk_f32_{fp8|bf8} for gfx950 (PR #117741)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117741 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] AMDGPU: Builtins & Codegen support for v_cvt_scalef32_pk_f32_{fp8|bf8} for gfx950 (PR #117741)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
@@ -14,8 +14,10 @@ typedef unsigned int uint; typedef unsigned int uint2 __attribute__((ext_vector_type(2))); typedef half __attribute__((ext_vector_type(2))) half2; typedef short __attribute__((ext_vector_type(2))) short2; +typedef float __attribute__((ext_vector_type(2))) flo

[llvm-branch-commits] [clang] [llvm] Builtins & Codegen support for v_cvt_scalef32_pk_{fp|bf}8_{f|bf}16 for gfx950 (PR #117742)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian approved this pull request. https://github.com/llvm/llvm-project/pull/117742 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

[llvm-branch-commits] [clang] [llvm] Builtins & Codegen support for v_cvt_scalef32_pk_{fp|bf}8_{f|bf}16 for gfx950 (PR #117742)

2024-11-26 Thread Shilei Tian via llvm-branch-commits
https://github.com/shiltian edited https://github.com/llvm/llvm-project/pull/117742 ___ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits

<    1   2   3   4   5   6   >