[llvm] quick fix for test failure (PR #128784)
Brox Chen via llvm-commits
llvm-commits at lists.llvm.org
Tue Feb 25 14:57:19 PST 2025
https://github.com/broxigarchen created https://github.com/llvm/llvm-project/pull/128784
None
>From ea9fdf8352fdcf59f732274dc6cfeaeb6f15c8d9 Mon Sep 17 00:00:00 2001
From: guochen2 <guochen2 at amd.com>
Date: Tue, 25 Feb 2025 17:56:56 -0500
Subject: [PATCH] quick fix for test failure
---
llvm/test/CodeGen/AMDGPU/fmed3.ll | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/llvm/test/CodeGen/AMDGPU/fmed3.ll b/llvm/test/CodeGen/AMDGPU/fmed3.ll
index 57c692621c121..c70b921c97999 100644
--- a/llvm/test/CodeGen/AMDGPU/fmed3.ll
+++ b/llvm/test/CodeGen/AMDGPU/fmed3.ll
@@ -7582,7 +7582,7 @@ define amdgpu_kernel void @v_test_nnan_input_fmed3_r_i_i_f16(ptr addrspace(1) %o
; GFX11-GISEL-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_4) | instid1(VALU_DEP_1)
; GFX11-GISEL-TRUE16-NEXT: v_lshlrev_b32_e32 v1, 1, v0
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt lgkmcnt(0)
-; GFX11-GISEL-TRUE16-NEXT: global_load_u16 v0, v1, s[2:3]
+; GFX11-GISEL-TRUE16-NEXT: global_load_d16_b16 v0, v1, s[2:3]
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0)
; GFX11-GISEL-TRUE16-NEXT: v_add_f16_e32 v0.l, 1.0, v0.l
; GFX11-GISEL-TRUE16-NEXT: v_med3_f16 v0.l, v0.l, 2.0, 4.0
@@ -7837,16 +7837,13 @@ define amdgpu_kernel void @v_nnan_inputs_med3_f16_pat0(ptr addrspace(1) %out, pt
; GFX11-GISEL-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GFX11-GISEL-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 1, v0
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt lgkmcnt(0)
-; GFX11-GISEL-TRUE16-NEXT: global_load_u16 v0, v2, s[2:3] glc dlc
+; GFX11-GISEL-TRUE16-NEXT: global_load_d16_b16 v0, v2, s[2:3] glc dlc
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0)
-; GFX11-GISEL-TRUE16-NEXT: global_load_u16 v1, v2, s[4:5] glc dlc
+; GFX11-GISEL-TRUE16-NEXT: global_load_d16_hi_b16 v0, v2, s[4:5] glc dlc
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0)
-; GFX11-GISEL-TRUE16-NEXT: global_load_u16 v3, v2, s[6:7] glc dlc
+; GFX11-GISEL-TRUE16-NEXT: global_load_d16_b16 v1, v2, s[6:7] glc dlc
; GFX11-GISEL-TRUE16-NEXT: s_waitcnt vmcnt(0)
; GFX11-GISEL-TRUE16-NEXT: v_add_f16_e32 v0.l, 1.0, v0.l
-; GFX11-GISEL-TRUE16-NEXT: v_mov_b16_e32 v0.h, v1.l
-; GFX11-GISEL-TRUE16-NEXT: v_mov_b16_e32 v1.l, v3.l
-; GFX11-GISEL-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
; GFX11-GISEL-TRUE16-NEXT: v_add_f16_e32 v0.h, 2.0, v0.h
; GFX11-GISEL-TRUE16-NEXT: v_add_f16_e32 v1.l, 4.0, v1.l
; GFX11-GISEL-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
More information about the llvm-commits
mailing list