summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen/AMDGPU
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU')
-rw-r--r--llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll35
-rw-r--r--llvm/test/CodeGen/AMDGPU/vector-alloca.ll119
2 files changed, 120 insertions, 34 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll b/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
index 7b515862909..bd0817d3041 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
@@ -417,12 +417,6 @@ entry:
ret void
}
-; HSAOPT: !0 = !{}
-; HSAOPT: !1 = !{i32 0, i32 2048}
-
-; NOHSAOPT: !0 = !{i32 0, i32 2048}
-
-
; FUNC-LABEL: v16i32_stack:
; R600: MOVA_INT
@@ -527,4 +521,33 @@ define void @v2float_stack(<2 x float> addrspace(1)* %out, i32 %a) {
ret void
}
+; OPT-LABEL: @direct_alloca_read_0xi32(
+; OPT: store [0 x i32] undef, [0 x i32] addrspace(3)*
+; OPT: load [0 x i32], [0 x i32] addrspace(3)*
+define void @direct_alloca_read_0xi32([0 x i32] addrspace(1)* %out, i32 %index) {
+entry:
+ %tmp = alloca [0 x i32]
+ store [0 x i32] [], [0 x i32]* %tmp
+ %load = load [0 x i32], [0 x i32]* %tmp
+ store [0 x i32] %load, [0 x i32] addrspace(1)* %out
+ ret void
+}
+
+; OPT-LABEL: @direct_alloca_read_1xi32(
+; OPT: store [1 x i32] zeroinitializer, [1 x i32] addrspace(3)*
+; OPT: load [1 x i32], [1 x i32] addrspace(3)*
+define void @direct_alloca_read_1xi32([1 x i32] addrspace(1)* %out, i32 %index) {
+entry:
+ %tmp = alloca [1 x i32]
+ store [1 x i32] [i32 0], [1 x i32]* %tmp
+ %load = load [1 x i32], [1 x i32]* %tmp
+ store [1 x i32] %load, [1 x i32] addrspace(1)* %out
+ ret void
+}
+
attributes #0 = { nounwind "amdgpu-max-waves-per-eu"="2" }
+
+; HSAOPT: !0 = !{}
+; HSAOPT: !1 = !{i32 0, i32 2048}
+
+; NOHSAOPT: !0 = !{i32 0, i32 2048}
diff --git a/llvm/test/CodeGen/AMDGPU/vector-alloca.ll b/llvm/test/CodeGen/AMDGPU/vector-alloca.ll
index c151ca9ef9b..7dcf36f144a 100644
--- a/llvm/test/CodeGen/AMDGPU/vector-alloca.ll
+++ b/llvm/test/CodeGen/AMDGPU/vector-alloca.ll
@@ -3,6 +3,11 @@
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=+promote-alloca -verify-machineinstrs < %s | FileCheck -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck --check-prefix=EG -check-prefix=FUNC %s
+; RUN: opt -S -mtriple=amdgcn-- -amdgpu-promote-alloca -sroa -instcombine < %s | FileCheck -check-prefix=OPT %s
+
+; OPT-LABEL: @vector_read(
+; OPT: %0 = extractelement <4 x i32> <i32 0, i32 1, i32 2, i32 3>, i32 %index
+; OPT: store i32 %0, i32 addrspace(1)* %out, align 4
; FUNC-LABEL: {{^}}vector_read:
; EG: MOV
@@ -12,21 +17,26 @@
; EG: MOVA_INT
define void @vector_read(i32 addrspace(1)* %out, i32 %index) {
entry:
- %0 = alloca [4 x i32]
- %x = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 0
- %y = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 1
- %z = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 2
- %w = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 3
+ %tmp = alloca [4 x i32]
+ %x = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 0
+ %y = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 1
+ %z = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 2
+ %w = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 3
store i32 0, i32* %x
store i32 1, i32* %y
store i32 2, i32* %z
store i32 3, i32* %w
- %1 = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 %index
- %2 = load i32, i32* %1
- store i32 %2, i32 addrspace(1)* %out
+ %tmp1 = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 %index
+ %tmp2 = load i32, i32* %tmp1
+ store i32 %tmp2, i32 addrspace(1)* %out
ret void
}
+; OPT-LABEL: @vector_write(
+; OPT: %0 = insertelement <4 x i32> zeroinitializer, i32 1, i32 %w_index
+; OPT: %1 = extractelement <4 x i32> %0, i32 %r_index
+; OPT: store i32 %1, i32 addrspace(1)* %out, align 4
+
; FUNC-LABEL: {{^}}vector_write:
; EG: MOV
; EG: MOV
@@ -36,42 +46,95 @@ entry:
; EG: MOVA_INT
define void @vector_write(i32 addrspace(1)* %out, i32 %w_index, i32 %r_index) {
entry:
- %0 = alloca [4 x i32]
- %x = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 0
- %y = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 1
- %z = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 2
- %w = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 3
+ %tmp = alloca [4 x i32]
+ %x = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 0
+ %y = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 1
+ %z = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 2
+ %w = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 3
store i32 0, i32* %x
store i32 0, i32* %y
store i32 0, i32* %z
store i32 0, i32* %w
- %1 = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 %w_index
- store i32 1, i32* %1
- %2 = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 %r_index
- %3 = load i32, i32* %2
- store i32 %3, i32 addrspace(1)* %out
+ %tmp1 = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 %w_index
+ store i32 1, i32* %tmp1
+ %tmp2 = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 %r_index
+ %tmp3 = load i32, i32* %tmp2
+ store i32 %tmp3, i32 addrspace(1)* %out
ret void
}
; This test should be optimize to:
; store i32 0, i32 addrspace(1)* %out
+
+; OPT-LABEL: @bitcast_gep(
+; OPT-LABEL: store i32 0, i32 addrspace(1)* %out, align 4
+
; FUNC-LABEL: {{^}}bitcast_gep:
; EG: STORE_RAW
define void @bitcast_gep(i32 addrspace(1)* %out, i32 %w_index, i32 %r_index) {
entry:
- %0 = alloca [4 x i32]
- %x = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 0
- %y = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 1
- %z = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 2
- %w = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 3
+ %tmp = alloca [4 x i32]
+ %x = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 0
+ %y = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 1
+ %z = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 2
+ %w = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 3
store i32 0, i32* %x
store i32 0, i32* %y
store i32 0, i32* %z
store i32 0, i32* %w
- %1 = getelementptr [4 x i32], [4 x i32]* %0, i32 0, i32 1
- %2 = bitcast i32* %1 to [4 x i32]*
- %3 = getelementptr [4 x i32], [4 x i32]* %2, i32 0, i32 0
- %4 = load i32, i32* %3
- store i32 %4, i32 addrspace(1)* %out
+ %tmp1 = getelementptr [4 x i32], [4 x i32]* %tmp, i32 0, i32 1
+ %tmp2 = bitcast i32* %tmp1 to [4 x i32]*
+ %tmp3 = getelementptr [4 x i32], [4 x i32]* %tmp2, i32 0, i32 0
+ %tmp4 = load i32, i32* %tmp3
+ store i32 %tmp4, i32 addrspace(1)* %out
+ ret void
+}
+
+; OPT-LABEL: @vector_read_bitcast_gep(
+; OPT: %0 = extractelement <4 x i32> <i32 1065353216, i32 1, i32 2, i32 3>, i32 %index
+; OPT: store i32 %0, i32 addrspace(1)* %out, align 4
+define void @vector_read_bitcast_gep(i32 addrspace(1)* %out, i32 %index) {
+entry:
+ %tmp = alloca [4 x i32]
+ %x = getelementptr inbounds [4 x i32], [4 x i32]* %tmp, i32 0, i32 0
+ %y = getelementptr inbounds [4 x i32], [4 x i32]* %tmp, i32 0, i32 1
+ %z = getelementptr inbounds [4 x i32], [4 x i32]* %tmp, i32 0, i32 2
+ %w = getelementptr inbounds [4 x i32], [4 x i32]* %tmp, i32 0, i32 3
+ %bc = bitcast i32* %x to float*
+ store float 1.0, float* %bc
+ store i32 1, i32* %y
+ store i32 2, i32* %z
+ store i32 3, i32* %w
+ %tmp1 = getelementptr inbounds [4 x i32], [4 x i32]* %tmp, i32 0, i32 %index
+ %tmp2 = load i32, i32* %tmp1
+ store i32 %tmp2, i32 addrspace(1)* %out
+ ret void
+}
+
+; FIXME: Should be able to promote this. Instcombine should fold the
+; cast in the hasOneUse case so it might not matter in practice
+
+; OPT-LABEL: @vector_read_bitcast_alloca(
+; OPT: alloca [4 x float]
+; OPT: store float
+; OPT: store float
+; OPT: store float
+; OPT: store float
+; OPT: load float
+define void @vector_read_bitcast_alloca(float addrspace(1)* %out, i32 %index) {
+entry:
+ %tmp = alloca [4 x i32]
+ %tmp.bc = bitcast [4 x i32]* %tmp to [4 x float]*
+ %x = getelementptr inbounds [4 x float], [4 x float]* %tmp.bc, i32 0, i32 0
+ %y = getelementptr inbounds [4 x float], [4 x float]* %tmp.bc, i32 0, i32 1
+ %z = getelementptr inbounds [4 x float], [4 x float]* %tmp.bc, i32 0, i32 2
+ %w = getelementptr inbounds [4 x float], [4 x float]* %tmp.bc, i32 0, i32 3
+ store float 0.0, float* %x
+ store float 1.0, float* %y
+ store float 2.0, float* %z
+ store float 4.0, float* %w
+ %tmp1 = getelementptr inbounds [4 x float], [4 x float]* %tmp.bc, i32 0, i32 %index
+ %tmp2 = load float, float* %tmp1
+ store float %tmp2, float addrspace(1)* %out
ret void
}
OpenPOWER on IntegriCloud