Merging r295990:

------------------------------------------------------------------------
r295990 | jvesely | 2017-02-23 08:12:21 -0800 (Thu, 23 Feb 2017) | 5 lines

AMDGPU/SI: Fix trunc i16 pattern

Hit on ASICs that support 16bit instructions.

Differential Revision: https://reviews.llvm.org/D30281
------------------------------------------------------------------------


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_40@296158 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 65 insertions, 37 deletions

diff --git a/lib/Target/AMDGPU/SIInstructions.td b/lib/Target/AMDGPU/SIInstructions.td
index b86c0419118..38e31e75ee6 100644
--- a/lib/Target/AMDGPU/SIInstructions.td
+++ b/lib/Target/AMDGPU/SIInstructions.td
@@ -997,6 +997,11 @@ def : Pat <
 >;
 
 def : Pat <
+  (i1 (trunc i16:$a)),
+  (V_CMP_EQ_U32_e64 (S_AND_B32 (i32 1), $a), (i32 1))
+>;
+
+def : Pat <
   (i1 (trunc i64:$a)),
   (V_CMP_EQ_U32_e64 (S_AND_B32 (i32 1),
                     (i32 (EXTRACT_SUBREG $a, sub0))), (i32 1))
diff --git a/lib/Target/AMDGPU/VOP1Instructions.td b/lib/Target/AMDGPU/VOP1Instructions.td
index a15b9ceff2f..8cae83cd9d1 100644
--- a/lib/Target/AMDGPU/VOP1Instructions.td
+++ b/lib/Target/AMDGPU/VOP1Instructions.td
@@ -607,12 +607,6 @@ def : Pat<
   (COPY $src)
 >;
 
-def : Pat<
-  (i1 (trunc i16:$src)),
-  (COPY $src)
->;
-
-
 def : Pat <
   (i16 (trunc i64:$src)),
   (EXTRACT_SUBREG $src, sub0)
diff --git a/test/CodeGen/AMDGPU/trunc.ll b/test/CodeGen/AMDGPU/trunc.ll
index 63bb447df2f..2c2ce4c5d35 100644
--- a/test/CodeGen/AMDGPU/trunc.ll
+++ b/test/CodeGen/AMDGPU/trunc.ll
@@ -1,13 +1,15 @@
-; RUN: llc -march=amdgcn -verify-machineinstrs< %s | FileCheck -check-prefix=SI %s
+; RUN: llc -march=amdgcn -verify-machineinstrs< %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
+; RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs< %s | FileCheck -check-prefix=GCN -check-prefix=VI  %s
 ; RUN: llc -march=r600 -mcpu=cypress < %s | FileCheck -check-prefix=EG %s
 
 declare i32 @llvm.r600.read.tidig.x() nounwind readnone
 
 define void @trunc_i64_to_i32_store(i32 addrspace(1)* %out, i64 %in) {
-; SI-LABEL: {{^}}trunc_i64_to_i32_store:
-; SI: s_load_dword [[SLOAD:s[0-9]+]], s[0:1], 0xb
-; SI: v_mov_b32_e32 [[VLOAD:v[0-9]+]], [[SLOAD]]
+; GCN-LABEL: {{^}}trunc_i64_to_i32_store:
+; GCN: s_load_dword [[SLOAD:s[0-9]+]], s[0:1],
+; GCN: v_mov_b32_e32 [[VLOAD:v[0-9]+]], [[SLOAD]]
 ; SI: buffer_store_dword [[VLOAD]]
+; VI: flat_store_dword v[{{[0-9:]+}}], [[VLOAD]]
 
 ; EG-LABEL: {{^}}trunc_i64_to_i32_store:
 ; EG: MEM_RAT_CACHELESS STORE_RAW T0.X, T1.X, 1
@@ -18,12 +20,14 @@ define void @trunc_i64_to_i32_store(i32 addrspace(1)* %out, i64 %in) {
   ret void
 }
 
-; SI-LABEL: {{^}}trunc_load_shl_i64:
-; SI-DAG: s_load_dwordx2
-; SI-DAG: s_load_dword [[SREG:s[0-9]+]],
-; SI: s_lshl_b32 [[SHL:s[0-9]+]], [[SREG]], 2
-; SI: v_mov_b32_e32 [[VSHL:v[0-9]+]], [[SHL]]
-; SI: buffer_store_dword [[VSHL]],
+; GCN-LABEL: {{^}}trunc_load_shl_i64:
+; GCN-DAG: s_load_dwordx2
+; GCN-DAG: s_load_dword [[SREG:s[0-9]+]],
+; GCN: s_lshl_b32 [[SHL:s[0-9]+]], [[SREG]], 2
+; GCN: v_mov_b32_e32 [[VSHL:v[0-9]+]], [[SHL]]
+; SI: buffer_store_dword [[VSHL]]
+; VI: flat_store_dword v[{{[0-9:]+}}], [[VSHL]]
+
 define void @trunc_load_shl_i64(i32 addrspace(1)* %out, i64 %a) {
   %b = shl i64 %a, 2
   %result = trunc i64 %b to i32
@@ -31,15 +35,17 @@ define void @trunc_load_shl_i64(i32 addrspace(1)* %out, i64 %a) {
   ret void
 }
 
-; SI-LABEL: {{^}}trunc_shl_i64:
+; GCN-LABEL: {{^}}trunc_shl_i64:
 ; SI: s_load_dwordx2 s{{\[}}[[LO_SREG:[0-9]+]]:{{[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0xd
-; SI: s_lshl_b64 s{{\[}}[[LO_SHL:[0-9]+]]:{{[0-9]+\]}}, s{{\[}}[[LO_SREG]]:{{[0-9]+\]}}, 2
-; SI: s_add_u32 s[[LO_SREG2:[0-9]+]], s[[LO_SHL]],
-; SI: v_mov_b32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG2]]
-; SI: s_addc_u32
+; VI: s_load_dwordx2 s{{\[}}[[LO_SREG:[0-9]+]]:{{[0-9]+\]}}, s{{\[[0-9]+:[0-9]+\]}}, 0x34
+; GCN: s_lshl_b64 s{{\[}}[[LO_SHL:[0-9]+]]:{{[0-9]+\]}}, s{{\[}}[[LO_SREG]]:{{[0-9]+\]}}, 2
+; GCN: s_add_u32 s[[LO_SREG2:[0-9]+]], s[[LO_SHL]],
+; GCN: v_mov_b32_e32 v[[LO_VREG:[0-9]+]], s[[LO_SREG2]]
+; GCN: s_addc_u32
 ; SI: buffer_store_dword v[[LO_VREG]],
-; SI: v_mov_b32_e32
-; SI: v_mov_b32_e32
+; VI: flat_store_dword v[{{[0-9:]+}}], v[[LO_VREG]]
+; GCN: v_mov_b32_e32
+; GCN: v_mov_b32_e32
 define void @trunc_shl_i64(i64 addrspace(1)* %out2, i32 addrspace(1)* %out, i64 %a) {
   %aa = add i64 %a, 234 ; Prevent shrinking store.
   %b = shl i64 %aa, 2
@@ -49,9 +55,9 @@ define void @trunc_shl_i64(i64 addrspace(1)* %out2, i32 addrspace(1)* %out, i64
   ret void
 }
 
-; SI-LABEL: {{^}}trunc_i32_to_i1:
-; SI: v_and_b32_e32 v{{[0-9]+}}, 1, v{{[0-9]+}}
-; SI: v_cmp_eq_u32
+; GCN-LABEL: {{^}}trunc_i32_to_i1:
+; GCN: v_and_b32_e32 v{{[0-9]+}}, 1, v{{[0-9]+}}
+; GCN: v_cmp_eq_u32
 define void @trunc_i32_to_i1(i32 addrspace(1)* %out, i32 addrspace(1)* %ptr) {
   %a = load i32, i32 addrspace(1)* %ptr, align 4
   %trunc = trunc i32 %a to i1
@@ -60,9 +66,30 @@ define void @trunc_i32_to_i1(i32 addrspace(1)* %out, i32 addrspace(1)* %ptr) {
   ret void
 }
 
-; SI-LABEL: {{^}}sgpr_trunc_i32_to_i1:
-; SI: s_and_b32 s{{[0-9]+}}, 1, s{{[0-9]+}}
-; SI: v_cmp_eq_u32
+; GCN-LABEL: {{^}}trunc_i8_to_i1:
+; GCN: v_and_b32_e32 v{{[0-9]+}}, 1, v{{[0-9]+}}
+; GCN: v_cmp_eq_u32
+define void @trunc_i8_to_i1(i8 addrspace(1)* %out, i8 addrspace(1)* %ptr) {
+  %a = load i8, i8 addrspace(1)* %ptr, align 4
+  %trunc = trunc i8 %a to i1
+  %result = select i1 %trunc, i8 1, i8 0
+  store i8 %result, i8 addrspace(1)* %out, align 4
+  ret void
+}
+
+; GCN-LABEL: {{^}}sgpr_trunc_i16_to_i1:
+; GCN: s_and_b32 s{{[0-9]+}}, 1, s{{[0-9]+}}
+; GCN: v_cmp_eq_u32
+define void @sgpr_trunc_i16_to_i1(i16 addrspace(1)* %out, i16 %a) {
+  %trunc = trunc i16 %a to i1
+  %result = select i1 %trunc, i16 1, i16 0
+  store i16 %result, i16 addrspace(1)* %out, align 4
+  ret void
+}
+
+; GCN-LABEL: {{^}}sgpr_trunc_i32_to_i1:
+; GCN: s_and_b32 s{{[0-9]+}}, 1, s{{[0-9]+}}
+; GCN: v_cmp_eq_u32
 define void @sgpr_trunc_i32_to_i1(i32 addrspace(1)* %out, i32 %a) {
   %trunc = trunc i32 %a to i1
   %result = select i1 %trunc, i32 1, i32 0
@@ -70,11 +97,12 @@ define void @sgpr_trunc_i32_to_i1(i32 addrspace(1)* %out, i32 %a) {
   ret void
 }
 
-; SI-LABEL: {{^}}s_trunc_i64_to_i1:
+; GCN-LABEL: {{^}}s_trunc_i64_to_i1:
 ; SI: s_load_dwordx2 s{{\[}}[[SLO:[0-9]+]]:{{[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0xb
-; SI: s_and_b32 [[MASKED:s[0-9]+]], 1, s[[SLO]]
-; SI: v_cmp_eq_u32_e64 s{{\[}}[[VLO:[0-9]+]]:[[VHI:[0-9]+]]], [[MASKED]], 1{{$}}
-; SI: v_cndmask_b32_e64 {{v[0-9]+}}, -12, 63, s{{\[}}[[VLO]]:[[VHI]]]
+; VI: s_load_dwordx2 s{{\[}}[[SLO:[0-9]+]]:{{[0-9]+\]}}, {{s\[[0-9]+:[0-9]+\]}}, 0x2c
+; GCN: s_and_b32 [[MASKED:s[0-9]+]], 1, s[[SLO]]
+; GCN: v_cmp_eq_u32_e64 s{{\[}}[[VLO:[0-9]+]]:[[VHI:[0-9]+]]], [[MASKED]], 1{{$}}
+; GCN: v_cndmask_b32_e64 {{v[0-9]+}}, -12, 63, s{{\[}}[[VLO]]:[[VHI]]]
 define void @s_trunc_i64_to_i1(i32 addrspace(1)* %out, i64 %x) {
   %trunc = trunc i64 %x to i1
   %sel = select i1 %trunc, i32 63, i32 -12
@@ -82,11 +110,12 @@ define void @s_trunc_i64_to_i1(i32 addrspace(1)* %out, i64 %x) {
   ret void
 }
 
-; SI-LABEL: {{^}}v_trunc_i64_to_i1:
+; GCN-LABEL: {{^}}v_trunc_i64_to_i1:
 ; SI: buffer_load_dwordx2 v{{\[}}[[VLO:[0-9]+]]:{{[0-9]+\]}}
-; SI: v_and_b32_e32 [[MASKED:v[0-9]+]], 1, v[[VLO]]
-; SI: v_cmp_eq_u32_e32 vcc, 1, [[MASKED]]
-; SI: v_cndmask_b32_e64 {{v[0-9]+}}, -12, 63, vcc
+; VI: flat_load_dwordx2 v{{\[}}[[VLO:[0-9]+]]:{{[0-9]+\]}}
+; GCN: v_and_b32_e32 [[MASKED:v[0-9]+]], 1, v[[VLO]]
+; GCN: v_cmp_eq_u32_e32 vcc, 1, [[MASKED]]
+; GCN: v_cndmask_b32_e64 {{v[0-9]+}}, -12, 63, vcc
 define void @v_trunc_i64_to_i1(i32 addrspace(1)* %out, i64 addrspace(1)* %in) {
   %tid = call i32 @llvm.r600.read.tidig.x() nounwind readnone
   %gep = getelementptr i64, i64 addrspace(1)* %in, i32 %tid