[llvm] [AMDGPU][True16][CodeGen] update test fmax3/fmin3 test with true16 mode (PR #140752)
via llvm-commits
llvm-commits at lists.llvm.org
Tue May 20 09:19:55 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Brox Chen (broxigarchen)
<details>
<summary>Changes</summary>
This is a NFC patch.
This patch duplicate GFX11plus runlines and apply them with "+mattr=+real-true16" and "+mattr=-real-true16" on fmax3/fmin3 tests. And then update the test with the update script
---
Patch is 163.06 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/140752.diff
2 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/fmax3-maximumnum.ll (+680-453)
- (modified) llvm/test/CodeGen/AMDGPU/fmin3-minimumnum.ll (+943-453)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/fmax3-maximumnum.ll b/llvm/test/CodeGen/AMDGPU/fmax3-maximumnum.ll
index d458bb2492f23..67040c729a581 100644
--- a/llvm/test/CodeGen/AMDGPU/fmax3-maximumnum.ll
+++ b/llvm/test/CodeGen/AMDGPU/fmax3-maximumnum.ll
@@ -5,8 +5,10 @@
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9,GFX950,GFX9-SDAG,GFX900-SDAG %s
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX9,GFX950,GFX9-SDAG,GFX950-SDAG %s
; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GFX10,GFX10-SDAG %s
-; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 < %s | FileCheck -check-prefixes=GFX11,GFX11-SDAG %s
-; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-SDAG,GFX11-SDAG-TRUE16 %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-SDAG,GFX11-SDAG-FAKE16 %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=+real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG,GFX12-SDAG-TRUE16 %s
+; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-SDAG,GFX12-SDAG-TRUE16 %s
; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx600 < %s | FileCheck -check-prefixes=GFX6,GFX6-GISEL %s
; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx700 < %s | FileCheck -check-prefixes=GFX7,GFX7-GISEL %s
@@ -14,8 +16,8 @@
; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 < %s | FileCheck -check-prefixes=GFX9,GFX950,GFX9-GISEL,GFX900-GISEL %s
; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx950 < %s | FileCheck -check-prefixes=GFX9,GFX950,GFX9-GISEL,GFX950-GISEL %s
; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GFX10,GFX10-GISEL %s
-; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 < %s | FileCheck -check-prefixes=GFX11,GFX11-GISEL %s
-; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL %s
+; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX11,GFX11-GISEL %s
+; xUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -mattr=-real-true16 < %s | FileCheck -check-prefixes=GFX12,GFX12-GISEL %s
define float @v_max3_f32_maximumnum_maximumnum__v_v_v_0(float %a, float %b, float %c) {
; GFX6-LABEL: v_max3_f32_maximumnum_maximumnum__v_v_v_0:
@@ -1080,21 +1082,26 @@ define half @v_max3_f16_maximumnum_maximumnum__v_v_v_0(half %a, half %b, half %c
; GFX10-NEXT: v_max3_f16 v0, v0, v1, v2
; GFX10-NEXT: s_setpc_b64 s[30:31]
;
-; GFX11-LABEL: v_max3_f16_maximumnum_maximumnum__v_v_v_0:
-; GFX11: ; %bb.0:
-; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX11-NEXT: v_max3_f16 v0, v0, v1, v2
-; GFX11-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX12-LABEL: v_max3_f16_maximumnum_maximumnum__v_v_v_0:
-; GFX12: ; %bb.0:
-; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
-; GFX12-NEXT: s_wait_expcnt 0x0
-; GFX12-NEXT: s_wait_samplecnt 0x0
-; GFX12-NEXT: s_wait_bvhcnt 0x0
-; GFX12-NEXT: s_wait_kmcnt 0x0
-; GFX12-NEXT: v_max3_num_f16 v0, v0, v1, v2
-; GFX12-NEXT: s_setpc_b64 s[30:31]
+; GFX11-SDAG-TRUE16-LABEL: v_max3_f16_maximumnum_maximumnum__v_v_v_0:
+; GFX11-SDAG-TRUE16: ; %bb.0:
+; GFX11-SDAG-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-SDAG-TRUE16-NEXT: v_max3_f16 v0.l, v0.l, v1.l, v2.l
+; GFX11-SDAG-TRUE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-SDAG-FAKE16-LABEL: v_max3_f16_maximumnum_maximumnum__v_v_v_0:
+; GFX11-SDAG-FAKE16: ; %bb.0:
+; GFX11-SDAG-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-SDAG-FAKE16-NEXT: v_max3_f16 v0, v0, v1, v2
+; GFX11-SDAG-FAKE16-NEXT: s_setpc_b64 s[30:31]
+; GFX12-SDAG-FAKE16-LABEL: v_max3_f16_maximumnum_maximumnum__v_v_v_0:
+; GFX12-SDAG-FAKE16: ; %bb.0:
+; GFX12-SDAG-FAKE16-NEXT: s_wait_loadcnt_dscnt 0x0
+; GFX12-SDAG-FAKE16-NEXT: s_wait_expcnt 0x0
+; GFX12-SDAG-FAKE16-NEXT: s_wait_samplecnt 0x0
+; GFX12-SDAG-FAKE16-NEXT: s_wait_bvhcnt 0x0
+; GFX12-SDAG-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX12-SDAG-FAKE16-NEXT: v_max3_num_f16 v0, v0, v1, v2
+; GFX12-SDAG-FAKE16-NEXT: s_setpc_b64 s[30:31]
%tmp0 = call half @llvm.maximumnum.f16(half %a, half %b)
%max3 = call half @llvm.maximumnum.f16(half %tmp0, half %c)
ret half %max3
@@ -1908,162 +1915,239 @@ define bfloat @v_max3_bf16_maximumnum_maximumnum__v_v_v_0(bfloat %a, bfloat %b,
; GFX10-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
; GFX10-NEXT: s_setpc_b64 s[30:31]
;
-; GFX11-LABEL: v_max3_bf16_maximumnum_maximumnum__v_v_v_0:
-; GFX11: ; %bb.0:
-; GFX11-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX11-NEXT: v_lshlrev_b32_e32 v3, 16, v0
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v4, 16, v1
-; GFX11-NEXT: v_cmp_u_f32_e32 vcc_lo, v4, v4
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX11-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v3, 16, v0
-; GFX11-NEXT: v_lshlrev_b32_e32 v4, 16, v1
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_cmp_gt_f32_e32 vcc_lo, v3, v4
-; GFX11-NEXT: v_cndmask_b32_e32 v3, v1, v0, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v3, 16, v3
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_max_f32_e32 v3, v3, v3
-; GFX11-NEXT: v_bfe_u32 v4, v3, 16, 1
-; GFX11-NEXT: v_or_b32_e32 v5, 0x400000, v3
-; GFX11-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_add3_u32 v4, v4, v3, 0x7fff
-; GFX11-NEXT: v_cndmask_b32_e32 v3, v4, v5, vcc_lo
-; GFX11-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_lshrrev_b32_e32 v4, 16, v3
-; GFX11-NEXT: v_dual_cndmask_b32 v0, v4, v0 :: v_dual_and_b32 v3, 0xffff0000, v3
-; GFX11-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_3)
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
-; GFX11-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v3
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v4, v0, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v1, 16, v0
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_cmp_u_f32_e32 vcc_lo, v1, v1
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v3, 16, v2
-; GFX11-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX11-NEXT: v_cndmask_b32_e32 v1, v2, v0, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v2, 16, v0
-; GFX11-NEXT: v_lshlrev_b32_e32 v3, 16, v1
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
-; GFX11-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc_lo
-; GFX11-NEXT: v_lshlrev_b32_e32 v2, 16, v2
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_max_f32_e32 v2, v2, v2
-; GFX11-NEXT: v_bfe_u32 v3, v2, 16, 1
-; GFX11-NEXT: v_or_b32_e32 v4, 0x400000, v2
-; GFX11-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
-; GFX11-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc_lo
-; GFX11-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX11-NEXT: v_lshrrev_b32_e32 v3, 16, v2
-; GFX11-NEXT: v_and_b32_e32 v2, 0xffff0000, v2
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
-; GFX11-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_4)
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
-; GFX11-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v2
-; GFX11-NEXT: s_delay_alu instid0(VALU_DEP_2)
-; GFX11-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
-; GFX11-NEXT: s_setpc_b64 s[30:31]
-;
-; GFX12-LABEL: v_max3_bf16_maximumnum_maximumnum__v_v_v_0:
-; GFX12: ; %bb.0:
-; GFX12-NEXT: s_wait_loadcnt_dscnt 0x0
-; GFX12-NEXT: s_wait_expcnt 0x0
-; GFX12-NEXT: s_wait_samplecnt 0x0
-; GFX12-NEXT: s_wait_bvhcnt 0x0
-; GFX12-NEXT: s_wait_kmcnt 0x0
-; GFX12-NEXT: v_lshlrev_b32_e32 v3, 16, v0
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_3) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v4, 16, v1
-; GFX12-NEXT: v_cmp_u_f32_e32 vcc_lo, v4, v4
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX12-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v3, 16, v0
-; GFX12-NEXT: v_lshlrev_b32_e32 v4, 16, v1
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_cmp_gt_f32_e32 vcc_lo, v3, v4
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v3, v1, v0, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v3, 16, v3
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_max_num_f32_e32 v3, v3, v3
-; GFX12-NEXT: v_bfe_u32 v4, v3, 16, 1
-; GFX12-NEXT: v_or_b32_e32 v5, 0x400000, v3
-; GFX12-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_add3_u32 v4, v4, v3, 0x7fff
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v3, v4, v5, vcc_lo
-; GFX12-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_lshrrev_b32_e32 v4, 16, v3
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_dual_cndmask_b32 v0, v4, v0 :: v_dual_and_b32 v3, 0xffff0000, v3
-; GFX12-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_3)
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
-; GFX12-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v3
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v4, v0, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v1, 16, v0
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_3) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_cmp_u_f32_e32 vcc_lo, v1, v1
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v0, v2, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v3, 16, v2
-; GFX12-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX12-NEXT: v_cndmask_b32_e32 v1, v2, v0, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v2, 16, v0
-; GFX12-NEXT: v_lshlrev_b32_e32 v3, 16, v1
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v2, v1, v0, vcc_lo
-; GFX12-NEXT: v_lshlrev_b32_e32 v2, 16, v2
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_max_num_f32_e32 v2, v2, v2
-; GFX12-NEXT: v_bfe_u32 v3, v2, 16, 1
-; GFX12-NEXT: v_or_b32_e32 v4, 0x400000, v2
-; GFX12-NEXT: v_cmp_u_f32_e32 vcc_lo, v2, v2
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_1)
-; GFX12-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v2, v3, v4, vcc_lo
-; GFX12-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_2) | instid1(VALU_DEP_2)
-; GFX12-NEXT: v_lshrrev_b32_e32 v3, 16, v2
-; GFX12-NEXT: v_and_b32_e32 v2, 0xffff0000, v2
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
-; GFX12-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v1
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_2) | instid1(VALU_DEP_2)
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
-; GFX12-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v2
-; GFX12-NEXT: s_wait_alu 0xfffd
-; GFX12-NEXT: v_cndmask_b32_e32 v0, v3, v0, vcc_lo
-; GFX12-NEXT: s_setpc_b64 s[30:31]
+; GFX11-SDAG-TRUE16-LABEL: v_max3_bf16_maximumnum_maximumnum__v_v_v_0:
+; GFX11-SDAG-TRUE16: ; %bb.0:
+; GFX11-SDAG-TRUE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v0.h, v1.l
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v1, 16, v1
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v1, v1
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v0.h, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v1.l, v0.h, v0.l, s0
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v3.l, v0.l
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v0.h, v2.l
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_4) | instskip(NEXT) | instid1(VALU_DEP_4)
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v4.l, v1.l
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v3, 16, v3
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v4, 16, v4
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v3, v4
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v3.l, v1.l, v0.l, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0.l
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v3, 16, v3
+; GFX11-SDAG-TRUE16-NEXT: v_max_f32_e32 v3, v3, v3
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_3)
+; GFX11-SDAG-TRUE16-NEXT: v_bfe_u32 v4, v3, 16, 1
+; GFX11-SDAG-TRUE16-NEXT: v_or_b32_e32 v5, 0x400000, v3
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v3, v3
+; GFX11-SDAG-TRUE16-NEXT: v_add3_u32 v4, v4, v3, 0x7fff
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b32_e64 v3, v4, v5, s0
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_eq_u16_e64 s0, 0, v1.l
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v3.h, v0.l, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_and_b32_e32 v4, 0xffff0000, v3
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v1.l, s0
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_3)
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v4
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v2, v2
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v3.h, v0.l, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v1.l, v0.l
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v1, 16, v1
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v1, v1
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v0.h, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v1.l, v0.h, v0.l, s0
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v2.l, v0.l
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_mov_b16_e32 v3.l, v1.l
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v3, 16, v3
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v2, v3
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v2.l, v1.l, v0.l, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_eq_u16_e32 vcc_lo, 0, v0.l
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-TRUE16-NEXT: v_lshlrev_b32_e32 v2, 16, v2
+; GFX11-SDAG-TRUE16-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_3)
+; GFX11-SDAG-TRUE16-NEXT: v_bfe_u32 v3, v2, 16, 1
+; GFX11-SDAG-TRUE16-NEXT: v_or_b32_e32 v4, 0x400000, v2
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_u_f32_e64 s0, v2, v2
+; GFX11-SDAG-TRUE16-NEXT: v_add3_u32 v3, v3, v2, 0x7fff
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b32_e64 v2, v3, v4, s0
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_eq_u16_e64 s0, 0, v1.l
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v2.h, v0.l, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_and_b32_e32 v3, 0xffff0000, v2
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v0.l, v1.l, s0
+; GFX11-SDAG-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(NEXT) | instid1(VALU_DEP_2)
+; GFX11-SDAG-TRUE16-NEXT: v_cmp_eq_f32_e32 vcc_lo, 0, v3
+; GFX11-SDAG-TRUE16-NEXT: v_cndmask_b16 v0.l, v2.h, v0.l, vcc_lo
+; GFX11-SDAG-TRUE16-NEXT: s_setpc_b64 s[30:31]
+;
+; GFX11-SDAG-FAKE16-LABEL: v_max3_bf16_maximumnum_maximumnum__v_v_v_0:
+; GFX11-SDAG-FAKE16: ; %bb.0:
+; GFX11-SDAG-FAKE16-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX11-SDAG-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX11-SDAG-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_2) | instid1(VALU_DEP_1)
+; GFX11-SDAG-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v3, v3
+; GFX11-SDAG-FAKE16-NEXT: v_cndmask_b32_e32 v0, v0, v1, vcc_lo
+; GFX11-SDAG-FAKE16-NEXT: v_lshlrev_b32_e32 v4, 16, v1
+; GFX11-SDAG-FAKE16-NEXT: v_cmp_u_f32_e32 vcc_lo, v4, v4
+; GFX11-SDAG-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(SKIP_1) | instid1(VALU_DEP_2)
+; GFX11-SDAG-FAKE16-NEXT: v_cndmask_b32_e32 v1, v1, v0, vcc_lo
+; GFX11-SDAG-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v0
+; GFX11-SDAG-FAKE16-NEXT: v_lshlrev_b32_e32 v4, 16, v1
+; GFX11-SDAG-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX11-SDAG-FAKE16-NEXT: v_cmp_gt_f32_e32 vcc_lo, v3, v4
+; GFX11-SDAG-FAKE16-NEXT: v_cndmask_b32_e32 v3, v1, v0, vcc_lo
+; GFX11-SDAG-FAKE16-NEXT: v_lshlrev_b32_e32 v3, 16, v3
+; GFX11-SDAG-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX11-SDAG-FAKE16-NEXT: v_max_f32_e32 v3, v3, v3
+; GFX11-SDAG-FAKE16-NEXT: v_...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/140752
More information about the llvm-commits
mailing list