aboutsummaryrefslogtreecommitdiff
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/gfx1250-scratch-scope-se.ll95
-rw-r--r--llvm/test/CodeGen/AMDGPU/global-load-xcnt.ll88
-rw-r--r--llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll38
-rw-r--r--llvm/test/CodeGen/AMDGPU/wwm-regalloc-error.ll2
4 files changed, 162 insertions, 61 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/gfx1250-scratch-scope-se.ll b/llvm/test/CodeGen/AMDGPU/gfx1250-scratch-scope-se.ll
new file mode 100644
index 0000000..d1e82a0
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/gfx1250-scratch-scope-se.ll
@@ -0,0 +1,95 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,GCN-SDAG %s
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,GCN-GISEL %s
+
+; Test that stores that may hit scratch are correctly promoted to SCOPE_SE.
+
+define void @test_scratch_store(ptr addrspace(5) %ptr, i32 %val) {
+; GCN-LABEL: test_scratch_store:
+; GCN: ; %bb.0:
+; GCN-NEXT: s_wait_loadcnt_dscnt 0x0
+; GCN-NEXT: s_wait_kmcnt 0x0
+; GCN-NEXT: scratch_store_b32 v0, v1, off scope:SCOPE_SE
+; GCN-NEXT: s_set_pc_i64 s[30:31]
+ store i32 %val, ptr addrspace(5) %ptr
+ ret void
+}
+
+define void @test_unknown_flat_store(ptr %ptr, i32 %val) {
+; GCN-LABEL: test_unknown_flat_store:
+; GCN: ; %bb.0:
+; GCN-NEXT: s_wait_loadcnt_dscnt 0x0
+; GCN-NEXT: s_wait_kmcnt 0x0
+; GCN-NEXT: flat_store_b32 v[0:1], v2 scope:SCOPE_SE
+; GCN-NEXT: s_wait_dscnt 0x0
+; GCN-NEXT: s_set_pc_i64 s[30:31]
+ store i32 %val, ptr %ptr
+ ret void
+}
+
+define void @test_flat_store_no_scratch_alloc(ptr %ptr, i32 %val) #0 {
+; GCN-LABEL: test_flat_store_no_scratch_alloc:
+; GCN: ; %bb.0:
+; GCN-NEXT: s_wait_loadcnt_dscnt 0x0
+; GCN-NEXT: s_wait_kmcnt 0x0
+; GCN-NEXT: flat_store_b32 v[0:1], v2
+; GCN-NEXT: s_wait_dscnt 0x0
+; GCN-NEXT: s_set_pc_i64 s[30:31]
+ store i32 %val, ptr %ptr
+ ret void
+}
+
+; TODO: handle
+define void @test_flat_store_noalias_addrspace(ptr %ptr, i32 %val) {
+; GCN-LABEL: test_flat_store_noalias_addrspace:
+; GCN: ; %bb.0:
+; GCN-NEXT: s_wait_loadcnt_dscnt 0x0
+; GCN-NEXT: s_wait_kmcnt 0x0
+; GCN-NEXT: flat_store_b32 v[0:1], v2 scope:SCOPE_SE
+; GCN-NEXT: s_wait_dscnt 0x0
+; GCN-NEXT: s_set_pc_i64 s[30:31]
+ store i32 %val, ptr %ptr, !noalias.addrspace !{i32 5, i32 6}
+ ret void
+}
+
+; TODO: would be nice to handle too
+define void @test_flat_store_select(ptr addrspace(1) %a, ptr addrspace(3) %b, i1 %cond, i32 %val) {
+; GCN-SDAG-LABEL: test_flat_store_select:
+; GCN-SDAG: ; %bb.0:
+; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
+; GCN-SDAG-NEXT: s_wait_kmcnt 0x0
+; GCN-SDAG-NEXT: v_cmp_ne_u32_e32 vcc_lo, -1, v2
+; GCN-SDAG-NEXT: v_and_b32_e32 v3, 1, v3
+; GCN-SDAG-NEXT: s_mov_b64 s[0:1], src_shared_base
+; GCN-SDAG-NEXT: v_cndmask_b32_e32 v2, 0, v2, vcc_lo
+; GCN-SDAG-NEXT: v_cndmask_b32_e64 v5, 0, s1, vcc_lo
+; GCN-SDAG-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GCN-SDAG-NEXT: v_cmp_eq_u32_e32 vcc_lo, 1, v3
+; GCN-SDAG-NEXT: v_dual_cndmask_b32 v1, v5, v1 :: v_dual_cndmask_b32 v0, v2, v0
+; GCN-SDAG-NEXT: flat_store_b32 v[0:1], v4 scope:SCOPE_SE
+; GCN-SDAG-NEXT: s_wait_dscnt 0x0
+; GCN-SDAG-NEXT: s_set_pc_i64 s[30:31]
+;
+; GCN-GISEL-LABEL: test_flat_store_select:
+; GCN-GISEL: ; %bb.0:
+; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0
+; GCN-GISEL-NEXT: s_wait_kmcnt 0x0
+; GCN-GISEL-NEXT: v_cmp_ne_u32_e32 vcc_lo, -1, v2
+; GCN-GISEL-NEXT: v_and_b32_e32 v3, 1, v3
+; GCN-GISEL-NEXT: s_mov_b64 s[0:1], src_shared_base
+; GCN-GISEL-NEXT: v_cndmask_b32_e32 v2, 0, v2, vcc_lo
+; GCN-GISEL-NEXT: v_cndmask_b32_e64 v5, 0, s1, vcc_lo
+; GCN-GISEL-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GCN-GISEL-NEXT: v_cmp_ne_u32_e32 vcc_lo, 0, v3
+; GCN-GISEL-NEXT: v_dual_cndmask_b32 v0, v2, v0 :: v_dual_cndmask_b32 v1, v5, v1
+; GCN-GISEL-NEXT: flat_store_b32 v[0:1], v4 scope:SCOPE_SE
+; GCN-GISEL-NEXT: s_wait_dscnt 0x0
+; GCN-GISEL-NEXT: s_set_pc_i64 s[30:31]
+ %a.ascast = addrspacecast ptr addrspace(1) %a to ptr
+ %b.ascast = addrspacecast ptr addrspace(3) %b to ptr
+ %ptr = select i1 %cond, ptr %a.ascast, ptr %b.ascast
+ store i32 %val, ptr %ptr
+ ret void
+}
+
+attributes #0 = { "amdgpu-no-flat-scratch-init" }
diff --git a/llvm/test/CodeGen/AMDGPU/global-load-xcnt.ll b/llvm/test/CodeGen/AMDGPU/global-load-xcnt.ll
index fd644a3..3a898a9 100644
--- a/llvm/test/CodeGen/AMDGPU/global-load-xcnt.ll
+++ b/llvm/test/CodeGen/AMDGPU/global-load-xcnt.ll
@@ -124,27 +124,27 @@ define i32 @test_v64i32_load_store(ptr addrspace(1) %ptr, i32 %idx, ptr addrspac
; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
; GCN-SDAG-NEXT: s_wait_kmcnt 0x0
; GCN-SDAG-NEXT: s_clause 0xd
-; GCN-SDAG-NEXT: scratch_store_b32 off, v40, s32 offset:52
-; GCN-SDAG-NEXT: scratch_store_b32 off, v41, s32 offset:48
-; GCN-SDAG-NEXT: scratch_store_b32 off, v42, s32 offset:44
-; GCN-SDAG-NEXT: scratch_store_b32 off, v43, s32 offset:40
-; GCN-SDAG-NEXT: scratch_store_b32 off, v44, s32 offset:36
-; GCN-SDAG-NEXT: scratch_store_b32 off, v45, s32 offset:32
-; GCN-SDAG-NEXT: scratch_store_b32 off, v56, s32 offset:28
-; GCN-SDAG-NEXT: scratch_store_b32 off, v57, s32 offset:24
-; GCN-SDAG-NEXT: scratch_store_b32 off, v58, s32 offset:20
-; GCN-SDAG-NEXT: scratch_store_b32 off, v59, s32 offset:16
-; GCN-SDAG-NEXT: scratch_store_b32 off, v60, s32 offset:12
-; GCN-SDAG-NEXT: scratch_store_b32 off, v61, s32 offset:8
-; GCN-SDAG-NEXT: scratch_store_b32 off, v62, s32 offset:4
-; GCN-SDAG-NEXT: scratch_store_b32 off, v63, s32
+; GCN-SDAG-NEXT: scratch_store_b32 off, v40, s32 offset:52 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v41, s32 offset:48 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v42, s32 offset:44 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v43, s32 offset:40 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v44, s32 offset:36 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v45, s32 offset:32 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v56, s32 offset:28 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v57, s32 offset:24 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v58, s32 offset:20 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v59, s32 offset:16 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v60, s32 offset:12 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v61, s32 offset:8 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v62, s32 offset:4 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v63, s32 scope:SCOPE_SE
; GCN-SDAG-NEXT: global_load_b128 v[6:9], v[0:1], off offset:224
; GCN-SDAG-NEXT: v_dual_mov_b32 v5, v4 :: v_dual_mov_b32 v4, v3
; GCN-SDAG-NEXT: s_wait_loadcnt 0x0
-; GCN-SDAG-NEXT: scratch_store_b128 off, v[6:9], s32 offset:56 ; 16-byte Folded Spill
+; GCN-SDAG-NEXT: scratch_store_b128 off, v[6:9], s32 offset:56 scope:SCOPE_SE ; 16-byte Folded Spill
; GCN-SDAG-NEXT: global_load_b128 v[6:9], v[0:1], off offset:240
; GCN-SDAG-NEXT: s_wait_loadcnt 0x0
-; GCN-SDAG-NEXT: scratch_store_b128 off, v[6:9], s32 offset:72 ; 16-byte Folded Spill
+; GCN-SDAG-NEXT: scratch_store_b128 off, v[6:9], s32 offset:72 scope:SCOPE_SE ; 16-byte Folded Spill
; GCN-SDAG-NEXT: s_clause 0xd
; GCN-SDAG-NEXT: global_load_b128 v[10:13], v[0:1], off offset:192
; GCN-SDAG-NEXT: global_load_b128 v[14:17], v[0:1], off offset:208
@@ -206,27 +206,27 @@ define i32 @test_v64i32_load_store(ptr addrspace(1) %ptr, i32 %idx, ptr addrspac
; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0
; GCN-GISEL-NEXT: s_wait_kmcnt 0x0
; GCN-GISEL-NEXT: s_clause 0xf
-; GCN-GISEL-NEXT: scratch_store_b32 off, v40, s32 offset:60
-; GCN-GISEL-NEXT: scratch_store_b32 off, v41, s32 offset:56
-; GCN-GISEL-NEXT: scratch_store_b32 off, v42, s32 offset:52
-; GCN-GISEL-NEXT: scratch_store_b32 off, v43, s32 offset:48
-; GCN-GISEL-NEXT: scratch_store_b32 off, v44, s32 offset:44
-; GCN-GISEL-NEXT: scratch_store_b32 off, v45, s32 offset:40
-; GCN-GISEL-NEXT: scratch_store_b32 off, v46, s32 offset:36
-; GCN-GISEL-NEXT: scratch_store_b32 off, v47, s32 offset:32
-; GCN-GISEL-NEXT: scratch_store_b32 off, v56, s32 offset:28
-; GCN-GISEL-NEXT: scratch_store_b32 off, v57, s32 offset:24
-; GCN-GISEL-NEXT: scratch_store_b32 off, v58, s32 offset:20
-; GCN-GISEL-NEXT: scratch_store_b32 off, v59, s32 offset:16
-; GCN-GISEL-NEXT: scratch_store_b32 off, v60, s32 offset:12
-; GCN-GISEL-NEXT: scratch_store_b32 off, v61, s32 offset:8
-; GCN-GISEL-NEXT: scratch_store_b32 off, v62, s32 offset:4
-; GCN-GISEL-NEXT: scratch_store_b32 off, v63, s32
+; GCN-GISEL-NEXT: scratch_store_b32 off, v40, s32 offset:60 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v41, s32 offset:56 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v42, s32 offset:52 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v43, s32 offset:48 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v44, s32 offset:44 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v45, s32 offset:40 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v46, s32 offset:36 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v47, s32 offset:32 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v56, s32 offset:28 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v57, s32 offset:24 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v58, s32 offset:20 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v59, s32 offset:16 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v60, s32 offset:12 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v61, s32 offset:8 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v62, s32 offset:4 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v63, s32 scope:SCOPE_SE
; GCN-GISEL-NEXT: s_wait_xcnt 0x8
; GCN-GISEL-NEXT: v_dual_mov_b32 v46, v3 :: v_dual_mov_b32 v47, v4
; GCN-GISEL-NEXT: global_load_b128 v[2:5], v[0:1], off offset:32
; GCN-GISEL-NEXT: s_wait_loadcnt 0x0
-; GCN-GISEL-NEXT: scratch_store_b128 off, v[2:5], s32 offset:80 ; 16-byte Folded Spill
+; GCN-GISEL-NEXT: scratch_store_b128 off, v[2:5], s32 offset:80 scope:SCOPE_SE ; 16-byte Folded Spill
; GCN-GISEL-NEXT: s_clause 0xe
; GCN-GISEL-NEXT: global_load_b128 v[6:9], v[0:1], off offset:48
; GCN-GISEL-NEXT: global_load_b128 v[10:13], v[0:1], off offset:64
@@ -244,7 +244,7 @@ define i32 @test_v64i32_load_store(ptr addrspace(1) %ptr, i32 %idx, ptr addrspac
; GCN-GISEL-NEXT: global_load_b128 v[60:63], v[0:1], off offset:16
; GCN-GISEL-NEXT: global_load_b128 v[0:3], v[0:1], off offset:240
; GCN-GISEL-NEXT: s_wait_loadcnt 0x0
-; GCN-GISEL-NEXT: scratch_store_b128 off, v[0:3], s32 offset:64 ; 16-byte Folded Spill
+; GCN-GISEL-NEXT: scratch_store_b128 off, v[0:3], s32 offset:64 scope:SCOPE_SE ; 16-byte Folded Spill
; GCN-GISEL-NEXT: scratch_load_b128 v[0:3], off, s32 offset:80 th:TH_LOAD_LU ; 16-byte Folded Reload
; GCN-GISEL-NEXT: s_wait_loadcnt 0x0
; GCN-GISEL-NEXT: s_clause 0xe
@@ -299,10 +299,10 @@ define i64 @test_v16i64_load_store(ptr addrspace(1) %ptr_a, ptr addrspace(1) %pt
; GCN-SDAG-NEXT: s_wait_loadcnt_dscnt 0x0
; GCN-SDAG-NEXT: s_wait_kmcnt 0x0
; GCN-SDAG-NEXT: s_clause 0x3
-; GCN-SDAG-NEXT: scratch_store_b32 off, v40, s32 offset:12
-; GCN-SDAG-NEXT: scratch_store_b32 off, v41, s32 offset:8
-; GCN-SDAG-NEXT: scratch_store_b32 off, v42, s32 offset:4
-; GCN-SDAG-NEXT: scratch_store_b32 off, v43, s32
+; GCN-SDAG-NEXT: scratch_store_b32 off, v40, s32 offset:12 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v41, s32 offset:8 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v42, s32 offset:4 scope:SCOPE_SE
+; GCN-SDAG-NEXT: scratch_store_b32 off, v43, s32 scope:SCOPE_SE
; GCN-SDAG-NEXT: s_clause 0x7
; GCN-SDAG-NEXT: global_load_b128 v[10:13], v[0:1], off offset:112
; GCN-SDAG-NEXT: global_load_b128 v[18:21], v[0:1], off offset:96
@@ -385,12 +385,12 @@ define i64 @test_v16i64_load_store(ptr addrspace(1) %ptr_a, ptr addrspace(1) %pt
; GCN-GISEL-NEXT: s_wait_loadcnt_dscnt 0x0
; GCN-GISEL-NEXT: s_wait_kmcnt 0x0
; GCN-GISEL-NEXT: s_clause 0x5
-; GCN-GISEL-NEXT: scratch_store_b32 off, v40, s32 offset:20
-; GCN-GISEL-NEXT: scratch_store_b32 off, v41, s32 offset:16
-; GCN-GISEL-NEXT: scratch_store_b32 off, v42, s32 offset:12
-; GCN-GISEL-NEXT: scratch_store_b32 off, v43, s32 offset:8
-; GCN-GISEL-NEXT: scratch_store_b32 off, v44, s32 offset:4
-; GCN-GISEL-NEXT: scratch_store_b32 off, v45, s32
+; GCN-GISEL-NEXT: scratch_store_b32 off, v40, s32 offset:20 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v41, s32 offset:16 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v42, s32 offset:12 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v43, s32 offset:8 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v44, s32 offset:4 scope:SCOPE_SE
+; GCN-GISEL-NEXT: scratch_store_b32 off, v45, s32 scope:SCOPE_SE
; GCN-GISEL-NEXT: s_clause 0x7
; GCN-GISEL-NEXT: global_load_b128 v[6:9], v[0:1], off offset:80
; GCN-GISEL-NEXT: global_load_b128 v[10:13], v[0:1], off
diff --git a/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll b/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll
index c3164b8..f54a383 100644
--- a/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll
+++ b/llvm/test/CodeGen/AMDGPU/partial-regcopy-and-spill-missed-at-regalloc.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
-;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 --stop-after=greedy,1 < %s | FileCheck -check-prefix=REGALLOC-GFX908 %s
+;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 --stop-after=greedy,2 < %s | FileCheck -check-prefix=REGALLOC-GFX908 %s
;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 --stop-after=prologepilog < %s | FileCheck -check-prefix=PEI-GFX908 %s
-;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a --stop-after=greedy,1 < %s | FileCheck -check-prefix=REGALLOC-GFX90A %s
+;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a --stop-after=greedy,2 < %s | FileCheck -check-prefix=REGALLOC-GFX90A %s
;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a --stop-after=prologepilog < %s | FileCheck -check-prefix=PEI-GFX90A %s
; Partial reg copy and spill missed during regalloc handled later at frame lowering.
@@ -12,17 +12,21 @@ define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; REGALLOC-GFX908-NEXT: liveins: $sgpr4_sgpr5
; REGALLOC-GFX908-NEXT: {{ $}}
; REGALLOC-GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 2162697 /* reguse:AGPR_32 */, undef %6:agpr_32
- ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 6094858 /* regdef:VReg_128 */, def %7
- ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3538954 /* regdef:VReg_64 */, def %8
- ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef %15:vreg_64, %7, 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
+ ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 6094858 /* regdef:VReg_128 */, def %25
+ ; REGALLOC-GFX908-NEXT: [[COPY:%[0-9]+]]:av_128 = COPY %25
+ ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3538954 /* regdef:VReg_64 */, def %27
+ ; REGALLOC-GFX908-NEXT: SI_SPILL_AV64_SAVE %27, %stack.0, $sgpr32, 0, implicit $exec :: (store (s64) into %stack.0, align 4, addrspace 5)
+ ; REGALLOC-GFX908-NEXT: [[COPY1:%[0-9]+]]:vreg_128 = COPY [[COPY]]
+ ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef %15:vreg_64, [[COPY1]], 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
; REGALLOC-GFX908-NEXT: renamable $sgpr0_sgpr1_sgpr2_sgpr3 = S_LOAD_DWORDX4_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s128) from %ir.arg.kernarg.offset1, addrspace 4)
- ; REGALLOC-GFX908-NEXT: [[COPY:%[0-9]+]]:areg_128 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3
+ ; REGALLOC-GFX908-NEXT: [[COPY2:%[0-9]+]]:areg_128 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3
; REGALLOC-GFX908-NEXT: [[AV_MOV_:%[0-9]+]]:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 1, implicit $exec
; REGALLOC-GFX908-NEXT: [[AV_MOV_1:%[0-9]+]]:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 2, implicit $exec
- ; REGALLOC-GFX908-NEXT: [[V_MFMA_I32_4X4X4I8_e64_:%[0-9]+]]:areg_128 = V_MFMA_I32_4X4X4I8_e64 [[AV_MOV_]], [[AV_MOV_1]], [[COPY]], 0, 0, 0, implicit $mode, implicit $exec
- ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX2 undef %17:vreg_64, %8, 0, 0, implicit $exec :: (volatile store (s64) into `ptr addrspace(1) poison`, addrspace 1)
- ; REGALLOC-GFX908-NEXT: [[COPY1:%[0-9]+]]:vreg_128 = COPY [[V_MFMA_I32_4X4X4I8_e64_]]
- ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef %19:vreg_64, [[COPY1]], 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
+ ; REGALLOC-GFX908-NEXT: [[V_MFMA_I32_4X4X4I8_e64_:%[0-9]+]]:areg_128 = V_MFMA_I32_4X4X4I8_e64 [[AV_MOV_]], [[AV_MOV_1]], [[COPY2]], 0, 0, 0, implicit $mode, implicit $exec
+ ; REGALLOC-GFX908-NEXT: [[SI_SPILL_AV64_RESTORE:%[0-9]+]]:vreg_64 = SI_SPILL_AV64_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s64) from %stack.0, align 4, addrspace 5)
+ ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX2 undef %17:vreg_64, [[SI_SPILL_AV64_RESTORE]], 0, 0, implicit $exec :: (volatile store (s64) into `ptr addrspace(1) poison`, addrspace 1)
+ ; REGALLOC-GFX908-NEXT: [[COPY3:%[0-9]+]]:vreg_128 = COPY [[V_MFMA_I32_4X4X4I8_e64_]]
+ ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef %19:vreg_64, [[COPY3]], 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
; REGALLOC-GFX908-NEXT: S_ENDPGM 0
;
; PEI-GFX908-LABEL: name: partial_copy
@@ -57,15 +61,17 @@ define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; REGALLOC-GFX90A-NEXT: liveins: $sgpr4_sgpr5
; REGALLOC-GFX90A-NEXT: {{ $}}
; REGALLOC-GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 2162697 /* reguse:AGPR_32 */, undef %6:agpr_32
- ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 6422538 /* regdef:VReg_128_Align2 */, def %7
- ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3866634 /* regdef:VReg_64_Align2 */, def %8
- ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef %15:vreg_64_align2, %7, 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
+ ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 6422538 /* regdef:VReg_128_Align2 */, def %24
+ ; REGALLOC-GFX90A-NEXT: [[COPY:%[0-9]+]]:av_128_align2 = COPY %24
+ ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3866634 /* regdef:VReg_64_Align2 */, def %22
+ ; REGALLOC-GFX90A-NEXT: [[COPY1:%[0-9]+]]:av_64_align2 = COPY %22
+ ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef %15:vreg_64_align2, [[COPY]], 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
; REGALLOC-GFX90A-NEXT: renamable $sgpr0_sgpr1_sgpr2_sgpr3 = S_LOAD_DWORDX4_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s128) from %ir.arg.kernarg.offset1, addrspace 4)
- ; REGALLOC-GFX90A-NEXT: [[COPY:%[0-9]+]]:areg_128_align2 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3
+ ; REGALLOC-GFX90A-NEXT: [[COPY2:%[0-9]+]]:areg_128_align2 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3
; REGALLOC-GFX90A-NEXT: [[AV_MOV_:%[0-9]+]]:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 1, implicit $exec
; REGALLOC-GFX90A-NEXT: [[AV_MOV_1:%[0-9]+]]:vgpr_32 = AV_MOV_B32_IMM_PSEUDO 2, implicit $exec
- ; REGALLOC-GFX90A-NEXT: [[V_MFMA_I32_4X4X4I8_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_I32_4X4X4I8_e64 [[AV_MOV_]], [[AV_MOV_1]], [[COPY]], 0, 0, 0, implicit $mode, implicit $exec
- ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX2 undef %17:vreg_64_align2, %8, 0, 0, implicit $exec :: (volatile store (s64) into `ptr addrspace(1) poison`, addrspace 1)
+ ; REGALLOC-GFX90A-NEXT: [[V_MFMA_I32_4X4X4I8_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_I32_4X4X4I8_e64 [[AV_MOV_]], [[AV_MOV_1]], [[COPY2]], 0, 0, 0, implicit $mode, implicit $exec
+ ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX2 undef %17:vreg_64_align2, [[COPY1]], 0, 0, implicit $exec :: (volatile store (s64) into `ptr addrspace(1) poison`, addrspace 1)
; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef %19:vreg_64_align2, [[V_MFMA_I32_4X4X4I8_e64_]], 0, 0, implicit $exec :: (volatile store (s128) into `ptr addrspace(1) poison`, addrspace 1)
; REGALLOC-GFX90A-NEXT: S_ENDPGM 0
;
diff --git a/llvm/test/CodeGen/AMDGPU/wwm-regalloc-error.ll b/llvm/test/CodeGen/AMDGPU/wwm-regalloc-error.ll
index 145f1e4..ff18b32 100644
--- a/llvm/test/CodeGen/AMDGPU/wwm-regalloc-error.ll
+++ b/llvm/test/CodeGen/AMDGPU/wwm-regalloc-error.ll
@@ -2,7 +2,7 @@
; A negative test to capture the expected error when the VGPRs are insufficient for wwm-regalloc.
-; CHECK: error: can't find enough VGPRs for wwm-regalloc
+; CHECK: error: cannot find enough VGPRs for wwm-regalloc
define amdgpu_kernel void @test(i32 %in) {
entry: