| # RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass si-load-store-opt -o - %s | FileCheck -check-prefix=GFX10 %s |
| |
| # GFX10-LABEL: name: image_sample_l_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_l_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| # GFX10-LABEL: name: image_sample_l_merged_v1v3_reversed |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub3 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub0_sub1_sub2 |
| |
| name: image_sample_l_merged_v1v3_reversed |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_merged_v2v2 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_64 = COPY %8.sub0_sub1 |
| # GFX10: %{{[0-9]+}}:vreg_64 = COPY killed %8.sub2_sub3 |
| |
| name: image_sample_l_merged_v2v2 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 3, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s64), align 16, addrspace 4) |
| %7:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 12, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s64), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_merged_v2v2_reversed |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_64 = COPY %8.sub2_sub3 |
| # GFX10: %{{[0-9]+}}:vreg_64 = COPY killed %8.sub0_sub1 |
| |
| name: image_sample_l_merged_v2v2_reversed |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 12, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s64), align 16, addrspace 4) |
| %7:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 3, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s64), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_merged_v3v1 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY %8.sub0_sub1_sub2 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY killed %8.sub3 |
| |
| name: image_sample_l_merged_v3v1 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_merged_v3v1_reversed |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY %8.sub1_sub2_sub3 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY killed %8.sub0 |
| |
| name: image_sample_l_merged_v3v1_reversed |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_divided_merged |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), addrspace 4) |
| |
| name: image_sample_l_divided_merged |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %8:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %9:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %7:vgpr_32, %7:vgpr_32, %7:vgpr_32, %3:sgpr_256, %2:sgpr_128, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| %10:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %11:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_divided_not_merged |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_divided_not_merged |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vreg_128 = COPY %2 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| IMAGE_STORE_V4_V2_nsa_gfx10 %4:vreg_128, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store (s128)) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_dmask_overlapped_not_merged |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 4, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_dmask_overlapped_not_merged |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 4, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_dmask_not_disjoint_not_merged |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 4, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 11, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_dmask_not_disjoint_not_merged |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 4, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 11, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_0 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %6, %6, %6, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_0 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 1, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %8:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %6, %6, %6, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_1 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %6, %6, %6, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %6, %6, %6, %4, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_1 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %5:vgpr_32 = COPY %2.sub3 |
| %6:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %6, %6, %6, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %8:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %6, %6, %6, %4, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_2 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %6, %6, %6, %4, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %6, %6, %6, %4, %3, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_2 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_128 = COPY $sgpr92_sgpr93_sgpr94_sgpr95 |
| %4:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %5:vgpr_32 = COPY %2.sub3 |
| %6:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %6, %6, %6, %4, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %8:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %6, %6, %6, %4, %3, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_3 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 1, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 1, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_4 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 1, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_4 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 1, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_5 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 1, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_5 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 1, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_6 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 1, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_6 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 1, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_7 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V2_nsa_gfx10 %5, %5, %3, %2, 8, 1, -1, 0, 0, 1, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_7 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V2_nsa_gfx10 %5, %5, %3, %2, 8, 1, -1, 0, 0, 1, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_8 |
| # GFX10: %{{[0-9]+}}:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s64), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_8 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s64), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_9 |
| # GFX10: %{{[0-9]+}}:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 1, 0, implicit $exec :: (dereferenceable load (s64), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_9 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vreg_64 = IMAGE_SAMPLE_L_V2_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 1, 0, implicit $exec :: (dereferenceable load (s64), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| # GFX10-LABEL: name: image_sample_l_not_merged_10 |
| # GFX10: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| # GFX10: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 1, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| |
| name: image_sample_l_not_merged_10 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V3_nsa_gfx10 %5, %5, %5, %3, %2, 8, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_V3_V3_nsa_gfx10 %5, %5, %5, %3, %2, 7, 1, -1, 0, 0, 0, 0, 0, 1, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| |
| |
| # GFX10-LABEL: name: image_sample_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_V4_V2_nsa_gfx10 %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_V1_V2_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_V3_V2_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_b_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_b_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_B_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_B_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_b_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_CL_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_b_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_B_CL_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_B_CL_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_b_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_CL_O_V4_V5_nsa_gfx10 %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_b_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_B_CL_O_V1_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_B_CL_O_V3_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_b_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_O_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_b_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_B_O_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_B_O_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_cd_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_V4_V6_nsa_gfx10 %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_cd_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_CD_V1_V6_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_CD_V3_V6_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_cd_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_CL_V4_V7_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_cd_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_CD_CL_V1_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_CD_CL_V3_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_cd_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_CL_O_V4_V8_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_cd_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_CD_CL_O_V1_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_CD_CL_O_V3_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_cd_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_O_V4_V7_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_cd_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_CD_O_V1_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_CD_O_V3_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CL_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_CL_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_CL_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CL_O_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_CL_O_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_CL_O_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_b_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_b_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_B_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_B_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_b_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_CL_V4_V5_nsa_gfx10 %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_b_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_B_CL_V1_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_B_CL_V3_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_b_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_CL_O_V4_V6_nsa_gfx10 %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_b_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_B_CL_O_V1_V6_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_B_CL_O_V3_V6_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_b_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_O_V4_V5_nsa_gfx10 %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_b_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_B_O_V1_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_B_O_V3_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_cd_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_V4_V7_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_cd_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_CD_V1_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_CD_V3_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_cd_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_CL_V4_V8_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_cd_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_CD_CL_V1_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_CD_CL_V3_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_cd_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_CL_O_V4_V9_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_cd_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_CD_CL_O_V1_V9_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_CD_CL_O_V3_V9_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_cd_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_O_V4_V8_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_cd_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_CD_O_V1_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_CD_O_V3_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CL_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_CL_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_CL_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CL_O_V4_V5_nsa_gfx10 %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_CL_O_V1_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_CL_O_V3_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_d_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_V4_V7_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_d_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_D_V1_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_D_V3_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_d_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_CL_V4_V8_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_d_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_D_CL_V1_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_D_CL_V3_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_d_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_CL_O_V4_V9_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_d_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_D_CL_O_V1_V9_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_D_CL_O_V3_V9_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_d_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_O_V4_V8_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_d_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_D_O_V1_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_D_O_V3_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_l_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_L_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_l_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_L_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_L_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_lz_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_LZ_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_lz_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_LZ_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_LZ_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_lz_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_LZ_O_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_lz_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_LZ_O_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_LZ_O_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_l_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_L_O_V4_V5_nsa_gfx10 %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_l_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_L_O_V1_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_L_O_V3_V5_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_c_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_O_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_c_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_C_O_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_C_O_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_d_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_V4_V6_nsa_gfx10 %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_d_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_D_V1_V6_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_D_V3_V6_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_d_cl_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_CL_V4_V7_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_d_cl_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_D_CL_V1_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_D_CL_V3_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_d_cl_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_CL_O_V4_V8_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_d_cl_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_D_CL_O_V1_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_D_CL_O_V3_V8_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_d_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_O_V4_V7_nsa_gfx10 %5, %5, %5, %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_d_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_D_O_V1_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_D_O_V3_V7_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_lz_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2_nsa_gfx10 %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_lz_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_LZ_V1_V2_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_LZ_V3_V2_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_lz_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_LZ_O_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_lz_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_LZ_O_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_LZ_O_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_l_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_O_V4_V4_nsa_gfx10 %5, %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_l_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_L_O_V1_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_L_O_V3_V4_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
| |
| |
| # GFX10-LABEL: name: image_sample_o_merged_v1v3 |
| # GFX10: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_O_V4_V3_nsa_gfx10 %5, %5, %5, %3, %2, 15, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec, implicit $exec :: (dereferenceable load (s128), align 4, addrspace 4) |
| # GFX10: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0 |
| # GFX10: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3 |
| |
| name: image_sample_o_merged_v1v3 |
| body: | |
| bb.0.entry: |
| %0:sgpr_64 = COPY $sgpr0_sgpr1 |
| %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0 |
| %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99 |
| %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 |
| %4:vgpr_32 = COPY %2.sub3 |
| %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) |
| %6:vgpr_32 = IMAGE_SAMPLE_O_V1_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 1, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) |
| %7:vreg_96 = IMAGE_SAMPLE_O_V3_V3_nsa_gfx10 %5:vgpr_32, %5:vgpr_32, %5:vgpr_32, %3:sgpr_256, %2:sgpr_128, 14, 1, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) |
| ... |
| --- |
