Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -2302,6 +2302,7 @@ int GCNHazardRecognizer::checkMAIHazards90A(MachineInstr *MI) {
const int SMFMA16x16WritesVGPROverlappedDMFMASrcCWaitStates = 9;
const int SMFMA32x32WritesVGPROverlappedDMFMASrcCWaitStates = 17;
const int DMFMA16x16WritesVGPROverlappedSrcCWaitStates = 9;
const int GFX950_DMFMA16x16WritesVGPROverlappedSrcCWaitStates = 17;
const int DMFMA4x4WritesVGPROverlappedSrcCWaitStates = 4;
const int SMFMA4x4WritesVGPROverlappedSrcABWaitStates = 5;
const int SMFMA16x16WritesVGPROverlappedSrcABWaitStates = 11;
Expand Down Expand Up @@ -2359,7 +2360,10 @@ int GCNHazardRecognizer::checkMAIHazards90A(MachineInstr *MI) {
case AMDGPU::V_MFMA_F64_16X16X4F64_mac_e64:
case AMDGPU::V_MFMA_F64_16X16X4F64_mac_vgprcd_e64:
if (!isXDL(ST, *MI))
NeedWaitStates = DMFMA16x16WritesVGPROverlappedSrcCWaitStates;
NeedWaitStates =
ST.hasGFX950Insts()
? GFX950_DMFMA16x16WritesVGPROverlappedSrcCWaitStates
: DMFMA16x16WritesVGPROverlappedSrcCWaitStates;
break;
case AMDGPU::V_MFMA_F64_4X4X4F64_e64:
case AMDGPU::V_MFMA_F64_4X4X4F64_vgprcd_e64:
Expand Down
45 changes: 33 additions & 12 deletions llvm/test/CodeGen/AMDGPU/mai-hazards-gfx940.mir
Original file line number Diff line number Diff line change
Expand Up @@ -298,8 +298,12 @@ body: |
...
# GCN-LABEL: name: dgemm16x16_mfma_write_vgpr_mfma_read_overlap
# GCN: V_MFMA
# GCN-NEXT: S_NOP 7
# GCN-NEXT: S_NOP 0
# GFX940-NEXT: S_NOP 7
# GFX940-NEXT: S_NOP 0

# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 0
# GCN-NEXT: V_MFMA
name: dgemm16x16_mfma_write_vgpr_mfma_read_overlap
body: |
Expand All @@ -319,8 +323,12 @@ body: |
...
# GCN-LABEL: name: dgemm16x16_mfma_write_vgpr_sgemm_mfma_read_overlap
# GCN: V_MFMA
# GCN-NEXT: S_NOP 7
# GCN-NEXT: S_NOP 0
# GFX940-NEXT: S_NOP 7
# GFX940-NEXT: S_NOP 0

# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 0
# GCN-NEXT: V_MFMA
name: dgemm16x16_mfma_write_vgpr_sgemm_mfma_read_overlap
body: |
Expand Down Expand Up @@ -549,8 +557,12 @@ body: |
...
# GCN-LABEL: name: dgemm16x16_mfma_write_vgpr_sgemm_mfma_srca_read_overlap
# GCN: V_MFMA
# GCN-NEXT: S_NOP 7
# GCN-NEXT: S_NOP 2
# GFX940-NEXT: S_NOP 7
# GFX940-NEXT: S_NOP 2

# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 0
# GCN-NEXT: V_MFMA
name: dgemm16x16_mfma_write_vgpr_sgemm_mfma_srca_read_overlap
body: |
Expand Down Expand Up @@ -1333,8 +1345,12 @@ body: |
...
# GCN-LABEL: name: dgemm16x16_mfma_write_agpr_mfma_read_overlap
# GCN: V_MFMA
# GCN-NEXT: S_NOP 7
# GCN-NEXT: S_NOP 0
# GFX940-NEXT: S_NOP 7
# GFX940-NEXT: S_NOP 0

# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 0
# GCN-NEXT: V_MFMA
name: dgemm16x16_mfma_write_agpr_mfma_read_overlap
body: |
Expand All @@ -1354,8 +1370,13 @@ body: |
...
# GCN-LABEL: name: dgemm16x16_mfma_write_agpr_sgemm_mfma_read_overlap
# GCN: V_MFMA
# GCN-NEXT: S_NOP 7
# GCN-NEXT: S_NOP 0
# GFX940-NEXT: S_NOP 7
# GFX940-NEXT: S_NOP 0

# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 7
# GFX950-NEXT: S_NOP 0

# GCN-NEXT: V_MFMA
name: dgemm16x16_mfma_write_agpr_sgemm_mfma_read_overlap
body: |
Expand Down Expand Up @@ -2502,8 +2523,8 @@ body: |
...
# GCN-LABEL: name: xdl_4pass_mfma_write_agpr_smfmac_read_overlap_srcc
# GCN: V_MFMA
# GFX940: S_NOP 4
# GFX950: S_NOP 5
# GFX940-NEXT: S_NOP 4
# GFX950-NEXT: S_NOP 5
# GCN-NEXT: V_SMFMAC_
name: xdl_4pass_mfma_write_agpr_smfmac_read_overlap_srcc
body: |
Expand Down
Loading