[AMDGPU] Fix build failure in raw.atomic.buffer.load tests #99912
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This fixes the failing tests due to different register numbers.
|
@llvm/pr-subscribers-backend-amdgpu Author: Jessica Del (OutOfCache) ChangesThis fixes the failing tests due to different Full diff: https://github.com/llvm/llvm-project/pull/99912.diff 2 Files Affected:
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll
index 03f94d6e853f0..419e19083f85e 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.atomic.buffer.load.ll
@@ -5,7 +5,8 @@
define amdgpu_kernel void @raw_atomic_buffer_load_i32(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_i32:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB0_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -33,7 +34,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_i32_off(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_i32_off:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB1_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -60,7 +62,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_i32_soff(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_i32_soff:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB2_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -87,7 +90,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_i32_dlc(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_i32_dlc:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB3_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -115,7 +119,8 @@ bb2:
define amdgpu_kernel void @raw_nonatomic_buffer_load_i32(<4 x i32> %addr) {
; CHECK-LABEL: raw_nonatomic_buffer_load_i32:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 offset:4 glc
; CHECK-NEXT: s_mov_b32 s0, 0
@@ -144,8 +149,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_i64(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_i64:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
-; CHECK-NEXT: v_mov_b32_e32 v1, 0
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_and_b32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB5_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -174,7 +179,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_v2i16(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_v2i16:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB6_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -203,7 +209,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_v4i16(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_v4i16:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB7_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -236,7 +243,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_v4i32(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_v4i32:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB8_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -265,7 +273,8 @@ bb2:
define amdgpu_kernel void @raw_atomic_buffer_load_ptr(<4 x i32> %addr) {
; CHECK-LABEL: raw_atomic_buffer_load_ptr:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB9_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll
index 3228335073d07..6541ac9553231 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.atomic.buffer.load.ll
@@ -5,7 +5,8 @@
define amdgpu_kernel void @raw_ptr_atomic_buffer_ptr_load_i32(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_ptr_load_i32:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB0_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -33,7 +34,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i32_off(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i32_off:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB1_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -60,7 +62,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i32_soff(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i32_soff:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB2_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -87,7 +90,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i32_dlc(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i32_dlc:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB3_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -115,7 +119,8 @@ bb2:
define amdgpu_kernel void @raw_nonptr_atomic_buffer_load_i32(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_nonptr_atomic_buffer_load_i32:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_waitcnt lgkmcnt(0)
; CHECK-NEXT: buffer_load_b32 v1, off, s[0:3], 0 offset:4 glc
; CHECK-NEXT: s_mov_b32 s0, 0
@@ -144,8 +149,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_i64(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_i64:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
-; CHECK-NEXT: v_mov_b32_e32 v1, 0
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_dual_mov_b32 v1, 0 :: v_dual_and_b32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB5_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -174,7 +179,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_v2i16(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_v2i16:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB6_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -203,7 +209,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_v4i16(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_v4i16:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB7_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -236,7 +243,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_v4i32(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_v4i32:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB8_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
@@ -265,7 +273,8 @@ bb2:
define amdgpu_kernel void @raw_ptr_atomic_buffer_load_ptr(ptr addrspace(8) %ptr) {
; CHECK-LABEL: raw_ptr_atomic_buffer_load_ptr:
; CHECK: ; %bb.0: ; %bb
-; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24
+; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24
+; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0
; CHECK-NEXT: s_mov_b32 s4, 0
; CHECK-NEXT: .LBB9_1: ; %bb1
; CHECK-NEXT: ; =>This Inner Loop Header: Depth=1
|
arsenm
approved these changes
Jul 22, 2024
| @@ -5,7 +5,8 @@ | |||
| define amdgpu_kernel void @raw_atomic_buffer_load_i32(<4 x i32> %addr) { | |||
| ; CHECK-LABEL: raw_atomic_buffer_load_i32: | |||
| ; CHECK: ; %bb.0: ; %bb | |||
| ; CHECK-NEXT: s_load_b128 s[0:3], s[0:1], 0x24 | |||
| ; CHECK-NEXT: s_load_b128 s[0:3], s[2:3], 0x24 | |||
| ; CHECK-NEXT: v_and_b32_e32 v0, 0x3ff, v0 | |||
There was a problem hiding this comment.
Oh, this probably wasn't rebased over the attributor move
There was a problem hiding this comment.
Ah, that explains it. Thanks!
yuxuanchen1997
pushed a commit
that referenced
this pull request
Jul 25, 2024
This fixes the failing tests after rebasing over the attributor move.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This fixes the failing tests after rebasing
over the attributor move.