[llvm] [NFC][AMDGPU] Split merge-tbuffer.mir into separate tests for gfx9, gfx10, and gfx11 (PR #148786)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 14 23:49:54 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Harrison Hao (harrisonGPU)
<details>
<summary>Changes</summary>
For https://github.com/llvm/llvm-project/pull/145078
---
Patch is 1.04 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/148786.diff
4 Files Affected:
- (added) llvm/test/CodeGen/AMDGPU/merge-tbuffer-gfx10.mir (+1526)
- (added) llvm/test/CodeGen/AMDGPU/merge-tbuffer-gfx11.mir (+1527)
- (added) llvm/test/CodeGen/AMDGPU/merge-tbuffer-gfx9.mir (+1553)
- (removed) llvm/test/CodeGen/AMDGPU/merge-tbuffer.mir (-8708)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/merge-tbuffer-gfx10.mir b/llvm/test/CodeGen/AMDGPU/merge-tbuffer-gfx10.mir
new file mode 100644
index 0000000000000..402c00298c8da
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/merge-tbuffer-gfx10.mir
@@ -0,0 +1,1526 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck -check-prefix=GFX10 %s
+
+---
+name: gfx10_tbuffer_load_x_xyz
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_x_xyz
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFSET [[REG_SEQUENCE]], 0, 4, 77, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vreg_96 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub1_sub2_sub3
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET %5:sgpr_128, 0, 8, 74, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_xyz_x
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_xyz_x
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFSET [[REG_SEQUENCE]], 0, 4, 77, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vreg_96 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub0_sub1_sub2
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub3
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET %5:sgpr_128, 0, 4, 74, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 16, 22, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_xy_xy
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_xy_xy
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFSET [[REG_SEQUENCE]], 0, 4, 77, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub0_sub1
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub2_sub3
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET %5:sgpr_128, 0, 4, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ %8:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET %5:sgpr_128, 0, 12, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_x_xy
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_x_xy
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET [[REG_SEQUENCE]], 0, 4, 74, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vreg_64 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub1_sub2
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET %5:sgpr_128, 0, 8, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_xy_x
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_xy_x
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET [[REG_SEQUENCE]], 0, 4, 74, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub0_sub1
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub2
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET %5:sgpr_128, 0, 4, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 12, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_x_x
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_x_x
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XY_OFFSET:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET [[REG_SEQUENCE]], 0, 4, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub1
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 8, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_x_x_format_32_32_32_32
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_x_x_format_32_32_32_32
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XY_OFFSET:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET [[REG_SEQUENCE]], 0, 4, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub1
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 77, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 8, 77, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_float_32
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_float_32
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XY_OFFSET:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET [[REG_SEQUENCE]], 0, 4, 64, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFSET [[REG_SEQUENCE]], 0, 16, 77, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:vreg_96 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub0_sub1_sub2
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub3
+ ; GFX10-NEXT: [[COPY8:%[0-9]+]]:vreg_64 = COPY [[COPY6]].sub0_sub1
+ ; GFX10-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY killed [[COPY6]].sub2
+ ; GFX10-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[COPY8]].sub0
+ ; GFX10-NEXT: [[COPY11:%[0-9]+]]:vgpr_32 = COPY killed [[COPY8]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET [[REG_SEQUENCE]], 0, 36, 74, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub0_sub1
+ ; GFX10-NEXT: [[COPY13:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub2
+ ; GFX10-NEXT: [[COPY14:%[0-9]+]]:vgpr_32 = COPY [[COPY12]].sub0
+ ; GFX10-NEXT: [[COPY15:%[0-9]+]]:vgpr_32 = COPY killed [[COPY12]].sub1
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 8, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %9:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 16, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %10:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 20, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %11:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 24, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %12:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 28, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %13:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 36, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %14:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 40, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %15:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 44, 22, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_sint_32
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_sint_32
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XY_OFFSET:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET [[REG_SEQUENCE]], 0, 4, 63, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFSET [[REG_SEQUENCE]], 0, 16, 76, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:vreg_96 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub0_sub1_sub2
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub3
+ ; GFX10-NEXT: [[COPY8:%[0-9]+]]:vreg_64 = COPY [[COPY6]].sub0_sub1
+ ; GFX10-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY killed [[COPY6]].sub2
+ ; GFX10-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[COPY8]].sub0
+ ; GFX10-NEXT: [[COPY11:%[0-9]+]]:vgpr_32 = COPY killed [[COPY8]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET [[REG_SEQUENCE]], 0, 36, 73, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub0_sub1
+ ; GFX10-NEXT: [[COPY13:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub2
+ ; GFX10-NEXT: [[COPY14:%[0-9]+]]:vgpr_32 = COPY [[COPY12]].sub0
+ ; GFX10-NEXT: [[COPY15:%[0-9]+]]:vgpr_32 = COPY killed [[COPY12]].sub1
+ %0:sgpr_32 = COPY $sgpr0
+ %1:sgpr_32 = COPY $sgpr1
+ %2:sgpr_32 = COPY $sgpr2
+ %3:sgpr_32 = COPY $sgpr3
+ %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
+ %7:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 4, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %8:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 8, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %9:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 16, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %10:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 20, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %11:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 24, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %12:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 28, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %13:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 36, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %14:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 40, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+ %15:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFSET %5:sgpr_128, 0, 44, 21, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
+...
+---
+
+name: gfx10_tbuffer_load_uint_32
+body: |
+ bb.0.entry:
+ ; GFX10-LABEL: name: gfx10_tbuffer_load_uint_32
+ ; GFX10: [[COPY:%[0-9]+]]:sgpr_32 = COPY $sgpr0
+ ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr1
+ ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sgpr_32 = COPY $sgpr2
+ ; GFX10-NEXT: [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr3
+ ; GFX10-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XY_OFFSET:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFSET [[REG_SEQUENCE]], 0, 4, 62, 0, 0, implicit $exec :: (dereferenceable load (s64), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub0
+ ; GFX10-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XY_OFFSET]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFSET [[REG_SEQUENCE]], 0, 16, 75, 0, 0, implicit $exec :: (dereferenceable load (s128), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY6:%[0-9]+]]:vreg_96 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub0_sub1_sub2
+ ; GFX10-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZW_OFFSET]].sub3
+ ; GFX10-NEXT: [[COPY8:%[0-9]+]]:vreg_64 = COPY [[COPY6]].sub0_sub1
+ ; GFX10-NEXT: [[COPY9:%[0-9]+]]:vgpr_32 = COPY killed [[COPY6]].sub2
+ ; GFX10-NEXT: [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[COPY8]].sub0
+ ; GFX10-NEXT: [[COPY11:%[0-9]+]]:vgpr_32 = COPY killed [[COPY8]].sub1
+ ; GFX10-NEXT: [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFSET [[REG_SEQUENCE]], 0, 36, 72, 0, 0, implicit $exec :: (dereferenceable load (s96), align 1, addrspace 4)
+ ; GFX10-NEXT: [[COPY12:%[0-9]+]]:vreg_64 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub0_sub1
+ ; GFX10-NEXT: [[COPY13:%[0-9]+]]:vgpr_32 = COPY killed [[TBUFFER_LOAD_FORMAT_XYZ_OFFSET]].sub2
+ ; GFX10-NEXT: [[COPY14:%[0-9]+]]:vgpr_32 = COPY [[COPY12]].sub0
+ ; GFX10-NEXT: ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/148786
More information about the llvm-commits
mailing list