forked from OSchip/llvm-project
[AMDGPU] Add some more GFX10 GlobalISel test coverage
This commit is contained in:
Jay Foad
parent
ed8c63115e
commit
b29b6f92af
File diff suppressed because it is too large
Load Diff
|
|
@ -1,7 +1,8 @@
|
|||
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
||||
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=SI %s
|
||||
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=VI %s
|
||||
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=GFX9 %s
|
||||
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=GFX9PLUS %s
|
||||
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=GFX9PLUS %s
|
||||
|
||||
---
|
||||
name: test_fmul_s32
|
||||
|
|
@ -19,11 +20,11 @@ body: |
|
|||
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
||||
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; VI: $vgpr0 = COPY [[FMUL]](s32)
|
||||
; GFX9-LABEL: name: test_fmul_s32
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; GFX9: $vgpr0 = COPY [[FMUL]](s32)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_s32
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; GFX9PLUS: $vgpr0 = COPY [[FMUL]](s32)
|
||||
%0:_(s32) = COPY $vgpr0
|
||||
%1:_(s32) = COPY $vgpr1
|
||||
%2:_(s32) = G_FMUL %0, %1
|
||||
|
|
@ -45,11 +46,11 @@ body: |
|
|||
; VI: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
||||
; VI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; VI: $vgpr0_vgpr1 = COPY [[FMUL]](s64)
|
||||
; GFX9-LABEL: name: test_fmul_s64
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[FMUL]](s64)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_s64
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; GFX9PLUS: $vgpr0_vgpr1 = COPY [[FMUL]](s64)
|
||||
%0:_(s64) = COPY $vgpr0_vgpr1
|
||||
%1:_(s64) = COPY $vgpr2_vgpr3
|
||||
%2:_(s64) = G_FMUL %0, %1
|
||||
|
|
@ -81,14 +82,14 @@ body: |
|
|||
; VI: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[TRUNC1]]
|
||||
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
||||
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
|
||||
; GFX9-LABEL: name: test_fmul_s16
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
||||
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
||||
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[TRUNC1]]
|
||||
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
||||
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_s16
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
||||
; GFX9PLUS: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
||||
; GFX9PLUS: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[TRUNC1]]
|
||||
; GFX9PLUS: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
||||
; GFX9PLUS: $vgpr0 = COPY [[ANYEXT]](s32)
|
||||
%0:_(s32) = COPY $vgpr0
|
||||
%1:_(s32) = COPY $vgpr1
|
||||
%2:_(s16) = G_TRUNC %0
|
||||
|
|
@ -123,15 +124,15 @@ body: |
|
|||
; VI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
|
||||
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
||||
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
||||
; GFX9-LABEL: name: test_fmul_v2s32
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
||||
; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v2s32
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
||||
; GFX9PLUS: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
||||
; GFX9PLUS: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9PLUS: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9PLUS: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
||||
; GFX9PLUS: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
||||
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
||||
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
||||
%2:_(<2 x s32>) = G_FMUL %0, %1
|
||||
|
|
@ -162,15 +163,15 @@ body: |
|
|||
; VI: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV1]], [[UV3]]
|
||||
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
||||
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
||||
; GFX9-LABEL: name: test_fmul_v2s32_flags
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
||||
; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v2s32_flags
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
||||
; GFX9PLUS: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
||||
; GFX9PLUS: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9PLUS: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9PLUS: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
||||
; GFX9PLUS: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
||||
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
||||
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
||||
%2:_(<2 x s32>) = nnan G_FMUL %0, %1
|
||||
|
|
@ -203,16 +204,16 @@ body: |
|
|||
; VI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
|
||||
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32), [[FMUL2]](s32)
|
||||
; VI: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
||||
; GFX9-LABEL: name: test_fmul_v3s32
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
||||
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
||||
; GFX9: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
|
||||
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
|
||||
; GFX9: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
|
||||
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32), [[FMUL2]](s32)
|
||||
; GFX9: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v3s32
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
||||
; GFX9PLUS: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
||||
; GFX9PLUS: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
|
||||
; GFX9PLUS: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
|
||||
; GFX9PLUS: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
|
||||
; GFX9PLUS: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32), [[FMUL2]](s32)
|
||||
; GFX9PLUS: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
||||
%0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
||||
%1:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
||||
%2:_(<3 x s32>) = G_FMUL %0, %1
|
||||
|
|
@ -243,15 +244,15 @@ body: |
|
|||
; VI: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[UV1]], [[UV3]]
|
||||
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FMUL]](s64), [[FMUL1]](s64)
|
||||
; VI: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
||||
; GFX9-LABEL: name: test_fmul_v2s64
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
||||
; GFX9: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
||||
; GFX9: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FMUL]](s64), [[FMUL1]](s64)
|
||||
; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v2s64
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
||||
; GFX9PLUS: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
||||
; GFX9PLUS: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9PLUS: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9PLUS: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FMUL]](s64), [[FMUL1]](s64)
|
||||
; GFX9PLUS: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
||||
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
||||
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
||||
%2:_(<2 x s64>) = G_FMUL %0, %1
|
||||
|
|
@ -310,11 +311,11 @@ body: |
|
|||
; VI: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
|
||||
; VI: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
|
||||
; VI: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
|
||||
; GFX9-LABEL: name: test_fmul_v2s16
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; GFX9: $vgpr0 = COPY [[FMUL]](<2 x s16>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v2s16
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[COPY]], [[COPY1]]
|
||||
; GFX9PLUS: $vgpr0 = COPY [[FMUL]](<2 x s16>)
|
||||
%0:_(<2 x s16>) = COPY $vgpr0
|
||||
%1:_(<2 x s16>) = COPY $vgpr1
|
||||
%2:_(<2 x s16>) = G_FMUL %0, %1
|
||||
|
|
@ -424,38 +425,38 @@ body: |
|
|||
; VI: [[BITCAST8:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR2]](s32)
|
||||
; VI: [[CONCAT_VECTORS:%[0-9]+]]:_(<6 x s16>) = G_CONCAT_VECTORS [[BITCAST6]](<2 x s16>), [[BITCAST7]](<2 x s16>), [[BITCAST8]](<2 x s16>)
|
||||
; VI: $vgpr0_vgpr1_vgpr2 = COPY [[CONCAT_VECTORS]](<6 x s16>)
|
||||
; GFX9-LABEL: name: test_fmul_v3s16
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<6 x s16>) = COPY $vgpr0_vgpr1_vgpr2
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<6 x s16>) = COPY $vgpr3_vgpr4_vgpr5
|
||||
; GFX9: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>), [[UV2:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<6 x s16>)
|
||||
; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
||||
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
||||
; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
||||
; GFX9: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST]](s32), [[LSHR]](s32)
|
||||
; GFX9: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST1]](s32), [[DEF]](s32)
|
||||
; GFX9: [[UV3:%[0-9]+]]:_(<2 x s16>), [[UV4:%[0-9]+]]:_(<2 x s16>), [[UV5:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<6 x s16>)
|
||||
; GFX9: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
||||
; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
||||
; GFX9: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV4]](<2 x s16>)
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC2:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST2]](s32), [[LSHR1]](s32)
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC3:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST3]](s32), [[DEF]](s32)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[BUILD_VECTOR_TRUNC]], [[BUILD_VECTOR_TRUNC2]]
|
||||
; GFX9: [[FMUL1:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[BUILD_VECTOR_TRUNC1]], [[BUILD_VECTOR_TRUNC3]]
|
||||
; GFX9: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
||||
; GFX9: [[BITCAST4:%[0-9]+]]:_(s32) = G_BITCAST [[FMUL]](<2 x s16>)
|
||||
; GFX9: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST4]], [[C]](s32)
|
||||
; GFX9: [[BITCAST5:%[0-9]+]]:_(s32) = G_BITCAST [[FMUL1]](<2 x s16>)
|
||||
; GFX9: [[UV6:%[0-9]+]]:_(<2 x s16>), [[UV7:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF1]](<4 x s16>)
|
||||
; GFX9: [[BITCAST6:%[0-9]+]]:_(s32) = G_BITCAST [[UV6]](<2 x s16>)
|
||||
; GFX9: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST6]], [[C]](s32)
|
||||
; GFX9: [[BITCAST7:%[0-9]+]]:_(s32) = G_BITCAST [[UV7]](<2 x s16>)
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC4:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST4]](s32), [[LSHR2]](s32)
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC5:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST5]](s32), [[BITCAST6]](s32)
|
||||
; GFX9: [[BUILD_VECTOR_TRUNC6:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[LSHR3]](s32), [[BITCAST7]](s32)
|
||||
; GFX9: [[CONCAT_VECTORS:%[0-9]+]]:_(<6 x s16>) = G_CONCAT_VECTORS [[BUILD_VECTOR_TRUNC4]](<2 x s16>), [[BUILD_VECTOR_TRUNC5]](<2 x s16>), [[BUILD_VECTOR_TRUNC6]](<2 x s16>)
|
||||
; GFX9: $vgpr0_vgpr1_vgpr2 = COPY [[CONCAT_VECTORS]](<6 x s16>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v3s16
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<6 x s16>) = COPY $vgpr0_vgpr1_vgpr2
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<6 x s16>) = COPY $vgpr3_vgpr4_vgpr5
|
||||
; GFX9PLUS: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>), [[UV2:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<6 x s16>)
|
||||
; GFX9PLUS: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
||||
; GFX9PLUS: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
||||
; GFX9PLUS: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
||||
; GFX9PLUS: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST]](s32), [[LSHR]](s32)
|
||||
; GFX9PLUS: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST1]](s32), [[DEF]](s32)
|
||||
; GFX9PLUS: [[UV3:%[0-9]+]]:_(<2 x s16>), [[UV4:%[0-9]+]]:_(<2 x s16>), [[UV5:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<6 x s16>)
|
||||
; GFX9PLUS: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
||||
; GFX9PLUS: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
||||
; GFX9PLUS: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV4]](<2 x s16>)
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC2:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST2]](s32), [[LSHR1]](s32)
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC3:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST3]](s32), [[DEF]](s32)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[BUILD_VECTOR_TRUNC]], [[BUILD_VECTOR_TRUNC2]]
|
||||
; GFX9PLUS: [[FMUL1:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[BUILD_VECTOR_TRUNC1]], [[BUILD_VECTOR_TRUNC3]]
|
||||
; GFX9PLUS: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
||||
; GFX9PLUS: [[BITCAST4:%[0-9]+]]:_(s32) = G_BITCAST [[FMUL]](<2 x s16>)
|
||||
; GFX9PLUS: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST4]], [[C]](s32)
|
||||
; GFX9PLUS: [[BITCAST5:%[0-9]+]]:_(s32) = G_BITCAST [[FMUL1]](<2 x s16>)
|
||||
; GFX9PLUS: [[UV6:%[0-9]+]]:_(<2 x s16>), [[UV7:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF1]](<4 x s16>)
|
||||
; GFX9PLUS: [[BITCAST6:%[0-9]+]]:_(s32) = G_BITCAST [[UV6]](<2 x s16>)
|
||||
; GFX9PLUS: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST6]], [[C]](s32)
|
||||
; GFX9PLUS: [[BITCAST7:%[0-9]+]]:_(s32) = G_BITCAST [[UV7]](<2 x s16>)
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC4:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST4]](s32), [[LSHR2]](s32)
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC5:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[BITCAST5]](s32), [[BITCAST6]](s32)
|
||||
; GFX9PLUS: [[BUILD_VECTOR_TRUNC6:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[LSHR3]](s32), [[BITCAST7]](s32)
|
||||
; GFX9PLUS: [[CONCAT_VECTORS:%[0-9]+]]:_(<6 x s16>) = G_CONCAT_VECTORS [[BUILD_VECTOR_TRUNC4]](<2 x s16>), [[BUILD_VECTOR_TRUNC5]](<2 x s16>), [[BUILD_VECTOR_TRUNC6]](<2 x s16>)
|
||||
; GFX9PLUS: $vgpr0_vgpr1_vgpr2 = COPY [[CONCAT_VECTORS]](<6 x s16>)
|
||||
%0:_(<6 x s16>) = COPY $vgpr0_vgpr1_vgpr2
|
||||
%1:_(<6 x s16>) = COPY $vgpr3_vgpr4_vgpr5
|
||||
%2:_(<3 x s16>), %3:_(<3 x s16>) = G_UNMERGE_VALUES %0
|
||||
|
|
@ -561,15 +562,15 @@ body: |
|
|||
; VI: [[BITCAST5:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
|
||||
; VI: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BITCAST4]](<2 x s16>), [[BITCAST5]](<2 x s16>)
|
||||
; VI: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
||||
; GFX9-LABEL: name: test_fmul_v4s16
|
||||
; GFX9: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
||||
; GFX9: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
||||
; GFX9: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
||||
; GFX9: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
||||
; GFX9: [[FMUL:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9: [[FMUL1:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[FMUL]](<2 x s16>), [[FMUL1]](<2 x s16>)
|
||||
; GFX9: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
||||
; GFX9PLUS-LABEL: name: test_fmul_v4s16
|
||||
; GFX9PLUS: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
||||
; GFX9PLUS: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
||||
; GFX9PLUS: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
||||
; GFX9PLUS: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
||||
; GFX9PLUS: [[FMUL:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[UV]], [[UV2]]
|
||||
; GFX9PLUS: [[FMUL1:%[0-9]+]]:_(<2 x s16>) = G_FMUL [[UV1]], [[UV3]]
|
||||
; GFX9PLUS: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[FMUL]](<2 x s16>), [[FMUL1]](<2 x s16>)
|
||||
; GFX9PLUS: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
||||
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
||||
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
||||
%2:_(<4 x s16>) = G_FMUL %0, %1
|
||||
|
|
|
|||
|
|
@ -1,2 +1,3 @@
|
|||
; Runs original SDAG test with -global-isel
|
||||
; RUN: llc -march=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs < %S/../llvm.amdgcn.init.exec.wave32.ll | FileCheck -check-prefixes=GCN,GFX1032 %S/../llvm.amdgcn.init.exec.wave32.ll
|
||||
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -verify-machineinstrs < %S/../llvm.amdgcn.init.exec.wave32.ll | FileCheck -check-prefixes=GCN,GFX1032 %S/../llvm.amdgcn.init.exec.wave32.ll
|
||||
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 -verify-machineinstrs < %S/../llvm.amdgcn.init.exec.wave32.ll | FileCheck -check-prefixes=GCN,GFX1064 %S/../llvm.amdgcn.init.exec.wave32.ll
|
||||
|
|
|
|||
Loading…
Reference in New Issue