[llvm] [AMDGPU] Support merging 16-bit TBUFFER load/store instruction (PR #145078)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 20 10:28:58 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Harrison Hao (harrisonGPU)
<details>
<summary>Changes</summary>
SILoadStoreOptimizer can now recognise consecutive 16-bit
`TBUFFER_LOAD`/`TBUFFER_STORE` instructions that each write
* a single component (`X`), or
* two components (`XY`),
and fold them into the wider native variants:
```
X + X --> XY
X + X + X + X --> XYZW
XY + XY --> XYZW
```
The optimisation cuts the number of TBUFFER instructions, shrinking code
size and improving memory throughput.
---
Patch is 39.91 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/145078.diff
2 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp (+32-6)
- (modified) llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir (+455)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
index b0d6fd95cd271..83dbad9a1ba20 100644
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -1040,8 +1040,21 @@ bool SILoadStoreOptimizer::offsetsCanBeCombined(CombineInfo &CI,
if (CI.Offset == Paired.Offset)
return false;
+ // Use 2-byte element size if both tbuffer formats are 16-bit.
+ unsigned EltSize = CI.EltSize;
+ auto Has16BitComponents = [&](unsigned Format) -> bool {
+ const auto *Info = AMDGPU::getGcnBufferFormatInfo(Format, STI);
+ return Info && Info->BitsPerComp == 16;
+ };
+
+ if ((CI.InstClass == TBUFFER_LOAD || CI.InstClass == TBUFFER_STORE)) {
+ // TODO: Support merging 8-bit tbuffer load/store instructions
+ if (Has16BitComponents(CI.Format) && Has16BitComponents(Paired.Format))
+ EltSize = 2;
+ }
+
// This won't be valid if the offset isn't aligned.
- if ((CI.Offset % CI.EltSize != 0) || (Paired.Offset % CI.EltSize != 0))
+ if ((CI.Offset % EltSize != 0) || (Paired.Offset % EltSize != 0))
return false;
if (CI.InstClass == TBUFFER_LOAD || CI.InstClass == TBUFFER_STORE) {
@@ -1059,13 +1072,26 @@ bool SILoadStoreOptimizer::offsetsCanBeCombined(CombineInfo &CI,
Info0->NumFormat != Info1->NumFormat)
return false;
- // TODO: Should be possible to support more formats, but if format loads
- // are not dword-aligned, the merged load might not be valid.
- if (Info0->BitsPerComp != 32)
+ // Buffer instructions support up to 4 components per access (e.g., x, xy,
+ // xyz, xyzw).
+ unsigned NumCombinedComponents = CI.Width + Paired.Width;
+ if (NumCombinedComponents > 4)
return false;
- if (getBufferFormatWithCompCount(CI.Format, CI.Width + Paired.Width, STI) == 0)
+ if (getBufferFormatWithCompCount(CI.Format, NumCombinedComponents, STI) ==
+ 0)
return false;
+
+ // Merge only when the two access ranges are strictly back-to-back,
+ // any gap or overlap can over-write data or leave holes.
+ unsigned BytePerComp = Info0->BitsPerComp / 8;
+ unsigned ElemIndex0 = CI.Offset / BytePerComp;
+ unsigned ElemIndex1 = Paired.Offset / BytePerComp;
+ if (!(ElemIndex0 + CI.Width == ElemIndex1 ||
+ ElemIndex1 + Paired.Width == ElemIndex0))
+ return false;
+
+ return true;
}
uint32_t EltOffset0 = CI.Offset / CI.EltSize;
@@ -1076,7 +1102,7 @@ bool SILoadStoreOptimizer::offsetsCanBeCombined(CombineInfo &CI,
// Handle all non-DS instructions.
if ((CI.InstClass != DS_READ) && (CI.InstClass != DS_WRITE)) {
if (EltOffset0 + CI.Width != EltOffset1 &&
- EltOffset1 + Paired.Width != EltOffset0)
+ EltOffset1 + Paired.Width != EltOffset0)
return false;
if (CI.CPol != Paired.CPol)
return false;
diff --git a/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir b/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir
index 9766b427b4325..4a604513e9bbe 100644
--- a/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir
+++ b/llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir
@@ -8706,3 +8706,458 @@ body: |
%8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN_exact %4, %5:sgpr_128, 0, 8, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
%9:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN_exact %4, %5:sgpr_128, 0, 12, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
...
+---
+
+name: gfx11_tbuffer_load_x_x_x_idxen_16bit
+body: |
+ bb.0.entry:
+ liveins: $sgpr0,$sgpr1,$sgpr2,$sgpr3,$vgpr0
+ ; GFX9-LABEL: name: gfx11_tbuffer_load_x_x_x_idxen_16bit
+ ; GFX9: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX9-NEXT: {{ $}}
+ ; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GFX9-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX9-NEXT: %x0:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY]], %rsrc, 0, 0, 13, 0, 0, implicit $exec :: (dereferenceable load (s16), addrspace 8)
+ ; GFX9-NEXT: %x1:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY]], %rsrc, 0, 2, 13, 0, 0, implicit $exec :: (dereferenceable load (s16), addrspace 8)
+ ; GFX9-NEXT: %x2:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY]], %rsrc, 0, 4, 13, 0, 0, implicit $exec :: (dereferenceable load (s16), addrspace 8)
+ ;
+ ; GFX10-LABEL: name: gfx11_tbuffer_load_x_x_x_idxen_16bit
+ ; GFX10: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GFX10-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XY_IDXEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_IDXEN [[COPY]], %rsrc, 0, 0, 29, 0, 0, implicit $exec :: (dereferenceable load (s32), align 2, addrspace 8)
+ ; GFX10-NEXT: %x0:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_IDXEN]].sub0
+ ; GFX10-NEXT: %x1:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_IDXEN]].sub1
+ ; GFX10-NEXT: %x2:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY]], %rsrc, 0, 4, 13, 0, 0, implicit $exec :: (dereferenceable load (s16), addrspace 8)
+ ;
+ ; GFX11-LABEL: name: gfx11_tbuffer_load_x_x_x_idxen_16bit
+ ; GFX11: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GFX11-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX11-NEXT: [[TBUFFER_LOAD_FORMAT_XY_IDXEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_IDXEN [[COPY]], %rsrc, 0, 0, 29, 0, 0, implicit $exec :: (dereferenceable load (s32), align 2, addrspace 8)
+ ; GFX11-NEXT: %x0:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_IDXEN]].sub0
+ ; GFX11-NEXT: %x1:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_IDXEN]].sub1
+ ; GFX11-NEXT: %x2:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY]], %rsrc, 0, 4, 13, 0, 0, implicit $exec :: (dereferenceable load (s16), addrspace 8)
+ %0:vgpr_32 = COPY $vgpr0
+ %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0,%subreg.sub0,$sgpr1,%subreg.sub1,$sgpr2,%subreg.sub2,$sgpr3,%subreg.sub3
+ %x0:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %0, %rsrc, 0, 0, 13, 0, 0, implicit $exec :: (dereferenceable load (s16),align 2,addrspace 8)
+ %x1:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %0, %rsrc, 0, 2, 13, 0, 0, implicit $exec :: (dereferenceable load (s16),align 2,addrspace 8)
+ %x2:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %0, %rsrc, 0, 4, 13, 0, 0, implicit $exec :: (dereferenceable load (s16),align 2,addrspace 8)
+...
+---
+
+name: gfx11_tbuffer_load_idxen_16_bit
+body: |
+ bb.0.entry:
+ liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4
+ ; GFX9-LABEL: name: gfx11_tbuffer_load_idxen_16_bit
+ ; GFX9: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4
+ ; GFX9-NEXT: {{ $}}
+ ; GFX9-NEXT: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; GFX9-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX9-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX9-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX9-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX9-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY1]], %subreg.sub3
+ ; GFX9-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[COPY]]
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 0, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN1:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 2, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN2:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 4, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN3:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 6, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN4:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 16, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN5:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 18, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN6:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 20, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN7:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 22, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN8:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 24, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ;
+ ; GFX10-LABEL: name: gfx11_tbuffer_load_idxen_16_bit
+ ; GFX10: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY1]], %subreg.sub3
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[COPY]]
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 0, 71, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 8)
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub0_sub1
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub2_sub3
+ ; GFX10-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[COPY6]].sub0
+ ; GFX10-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY killed [[COPY6]].sub1
+ ; GFX10-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[COPY7]].sub0
+ ; GFX10-NEXT: [[COPY11:%[0-9]+]]:vgpr_32 = COPY killed [[COPY7]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN1:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 16, 71, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 8)
+ ; GFX10-NEXT: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN1]].sub0_sub1
+ ; GFX10-NEXT: [[COPY13:%[0-9]+]]:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN1]].sub2_sub3
+ ; GFX10-NEXT: [[COPY14:%[0-9]+]]:vgpr_32 = COPY [[COPY12]].sub0
+ ; GFX10-NEXT: [[COPY15:%[0-9]+]]:vgpr_32 = COPY killed [[COPY12]].sub1
+ ; GFX10-NEXT: [[COPY16:%[0-9]+]]:vgpr_32 = COPY [[COPY13]].sub0
+ ; GFX10-NEXT: [[COPY17:%[0-9]+]]:vgpr_32 = COPY killed [[COPY13]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 24, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ ;
+ ; GFX11-LABEL: name: gfx11_tbuffer_load_idxen_16_bit
+ ; GFX11: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr4
+ ; GFX11-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX11-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX11-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX11-NEXT: [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX11-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY1]], %subreg.sub3
+ ; GFX11-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[COPY]]
+ ; GFX11-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 0, 57, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 8)
+ ; GFX11-NEXT: [[COPY6:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub0_sub1
+ ; GFX11-NEXT: [[COPY7:%[0-9]+]]:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub2_sub3
+ ; GFX11-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[COPY6]].sub0
+ ; GFX11-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY killed [[COPY6]].sub1
+ ; GFX11-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[COPY7]].sub0
+ ; GFX11-NEXT: [[COPY11:%[0-9]+]]:vgpr_32 = COPY killed [[COPY7]].sub1
+ ; GFX11-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN1:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 16, 57, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 8)
+ ; GFX11-NEXT: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN1]].sub0_sub1
+ ; GFX11-NEXT: [[COPY13:%[0-9]+]]:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN1]].sub2_sub3
+ ; GFX11-NEXT: [[COPY14:%[0-9]+]]:vgpr_32 = COPY [[COPY12]].sub0
+ ; GFX11-NEXT: [[COPY15:%[0-9]+]]:vgpr_32 = COPY killed [[COPY12]].sub1
+ ; GFX11-NEXT: [[COPY16:%[0-9]+]]:vgpr_32 = COPY [[COPY13]].sub0
+ ; GFX11-NEXT: [[COPY17:%[0-9]+]]:vgpr_32 = COPY killed [[COPY13]].sub1
+ ; GFX11-NEXT: [[TBUFFER_LOAD_FORMAT_X_IDXEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN [[COPY5]], [[REG_SEQUENCE]], 0, 24, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %4:sgpr_32 = COPY $sgpr4
+ %3:sgpr_32 = COPY $sgpr3
+ %2:sgpr_32 = COPY $sgpr2
+ %1:sgpr_32 = COPY $sgpr1
+ %0:sgpr_32 = COPY $sgpr0
+ %5:sgpr_128 = REG_SEQUENCE %0:sgpr_32, %subreg.sub0, %1:sgpr_32, %subreg.sub1, %2:sgpr_32, %subreg.sub2, %3:sgpr_32, %subreg.sub3
+ %8:vgpr_32 = COPY %4:sgpr_32
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 0, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %9:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 2, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %11:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 4, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %13:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 6, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %15:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 16, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %17:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 18, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %19:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 20, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %21:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 22, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+ %22:vgpr_32 = TBUFFER_LOAD_FORMAT_X_IDXEN %8:vgpr_32, %5:sgpr_128, 0, 24, 13, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 8)
+...
+---
+
+name: gfx11_tbuffer_load_xy_xy_idxen_uint_16_bit
+body: |
+ bb.0.entry:
+ liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX9-LABEL: name: gfx11_tbuffer_load_xy_xy_idxen_uint_16_bit
+ ; GFX9: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX9-NEXT: {{ $}}
+ ; GFX9-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX9-NEXT: %idx:vgpr_32 = COPY $vgpr0
+ ; GFX9-NEXT: %v0:vreg_64 = TBUFFER_LOAD_FORMAT_XY_IDXEN %idx, %rsrc, 0, 0, 27, 0, 0, implicit $exec :: (dereferenceable load (s32), align 2, addrspace 4)
+ ; GFX9-NEXT: %v1:vreg_64 = TBUFFER_LOAD_FORMAT_XY_IDXEN %idx, %rsrc, 0, 4, 27, 0, 0, implicit $exec :: (dereferenceable load (s32), align 2, addrspace 4)
+ ;
+ ; GFX10-LABEL: name: gfx11_tbuffer_load_xy_xy_idxen_uint_16_bit
+ ; GFX10: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX10-NEXT: %idx:vgpr_32 = COPY $vgpr0
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN %idx, %rsrc, 0, 0, 69, 0, 0, implicit $exec :: (dereferenceable load (s64), align 2, addrspace 4)
+ ; GFX10-NEXT: %v0:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub0_sub1
+ ; GFX10-NEXT: %v1:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub2_sub3
+ ;
+ ; GFX11-LABEL: name: gfx11_tbuffer_load_xy_xy_idxen_uint_16_bit
+ ; GFX11: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX11-NEXT: %idx:vgpr_32 = COPY $vgpr0
+ ; GFX11-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN %idx, %rsrc, 0, 0, 55, 0, 0, implicit $exec :: (dereferenceable load (s64), align 2, addrspace 4)
+ ; GFX11-NEXT: %v0:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub0_sub1
+ ; GFX11-NEXT: %v1:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub2_sub3
+ %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1,%subreg.sub1, $sgpr2,%subreg.sub2, $sgpr3,%subreg.sub3
+ %idx:vgpr_32 = COPY $vgpr0
+ %v0:vreg_64 = TBUFFER_LOAD_FORMAT_XY_IDXEN %idx, %rsrc, 0, 0, 27, 0, 0, implicit $exec :: (dereferenceable load (s32),align 2,addrspace 4)
+ %v1:vreg_64 = TBUFFER_LOAD_FORMAT_XY_IDXEN %idx, %rsrc, 0, 4, 27, 0, 0, implicit $exec :: (dereferenceable load (s32),align 2,addrspace 4)
+...
+---
+
+name: gfx11_tbuffer_load_xy_xy_idxen_sint_16_bit
+body: |
+ bb.0.entry:
+ liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX9-LABEL: name: gfx11_tbuffer_load_xy_xy_idxen_sint_16_bit
+ ; GFX9: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX9-NEXT: {{ $}}
+ ; GFX9-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX9-NEXT: %idx:vgpr_32 = COPY $vgpr0
+ ; GFX9-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN %idx, %rsrc, 0, 0, 28, 0, 0, implicit $exec :: (dereferenceable load (s64), align 2, addrspace 4)
+ ; GFX9-NEXT: %v0:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub0_sub1
+ ; GFX9-NEXT: %v1:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub2_sub3
+ ;
+ ; GFX10-LABEL: name: gfx11_tbuffer_load_xy_xy_idxen_sint_16_bit
+ ; GFX10: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX10-NEXT: {{ $}}
+ ; GFX10-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX10-NEXT: %idx:vgpr_32 = COPY $vgpr0
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN %idx, %rsrc, 0, 0, 70, 0, 0, implicit $exec :: (dereferenceable load (s64), align 2, addrspace 4)
+ ; GFX10-NEXT: %v0:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub0_sub1
+ ; GFX10-NEXT: %v1:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN]].sub2_sub3
+ ;
+ ; GFX11-LABEL: name: gfx11_tbuffer_load_xy_xy_idxen_sint_16_bit
+ ; GFX11: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $vgpr0
+ ; GFX11-NEXT: {{ $}}
+ ; GFX11-NEXT: %rsrc:sgpr_128 = REG_SEQUENCE $sgpr0, %subreg.sub0, $sgpr1, %subreg.sub1, $sgpr2, %subreg.sub2, $sgpr3, %subreg.sub3
+ ; GFX11-NEXT: %idx:vgpr_32 = COPY $vgpr0
+ ; GFX11-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_IDXEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_IDXEN %idx, %rsrc, 0, ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/145078
More information about the llvm-commits
mailing list