[llvm] [AMDGPU][True16][CodeGen] v_s_xxx_f16 t16 mode handling in movetoVALU process (PR #141152)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Jun 4 08:29:03 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Brox Chen (broxigarchen)
<details>
<summary>Changes</summary>
Add op_sel for v_s_xxx_f16 when move them to VALU
update a few related codegen test for gfx12 in true16 mode
---
Patch is 100.66 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/141152.diff
8 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/SIInstrInfo.cpp (+23)
- (modified) llvm/test/CodeGen/AMDGPU/frem.ll (+897)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.rcp.f16.ll (+78-7)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.rsq.f16.ll (+78-7)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.sqrt.f16.ll (+50-4)
- (added) llvm/test/CodeGen/AMDGPU/move-to-valu-pseudo-scalar-trans-f16-fake16.ll (+113)
- (added) llvm/test/CodeGen/AMDGPU/move-to-valu-pseudo-scalar-trans-f16-true16.ll (+123)
- (modified) llvm/test/CodeGen/AMDGPU/move-to-valu-pseudo-scalar-trans.ll (+2-112)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
index a27d4eeee97f4..f59b3ac43d2eb 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
@@ -7736,6 +7736,29 @@ void SIInstrInfo::moveToVALUImpl(SIInstrWorklist &Worklist,
Inst.eraseFromParent();
return;
}
+ case AMDGPU::V_S_EXP_F16_e64:
+ case AMDGPU::V_S_LOG_F16_e64:
+ case AMDGPU::V_S_RCP_F16_e64:
+ case AMDGPU::V_S_RSQ_F16_e64:
+ case AMDGPU::V_S_SQRT_F16_e64: {
+ const DebugLoc &DL = Inst.getDebugLoc();
+ Register NewDst = MRI.createVirtualRegister(ST.useRealTrue16Insts()
+ ? &AMDGPU::VGPR_16RegClass
+ : &AMDGPU::VGPR_32RegClass);
+ auto NewInstr = BuildMI(*MBB, Inst, DL, get(NewOpcode), NewDst)
+ .addImm(0) // src0_modifiers
+ .add(Inst.getOperand(1))
+ .addImm(0) // clamp
+ .addImm(0); // omod
+ if (ST.useRealTrue16Insts())
+ NewInstr.addImm(0); // opsel0
+ MRI.replaceRegWith(Inst.getOperand(0).getReg(), NewDst);
+ legalizeOperandsVALUt16(*NewInstr, MRI);
+ legalizeOperands(*NewInstr, MDT);
+ addUsersToMoveToVALUWorklist(NewDst, MRI, Worklist);
+ Inst.eraseFromParent();
+ return;
+ }
}
if (NewOpcode == AMDGPU::INSTRUCTION_LIST_END) {
diff --git a/llvm/test/CodeGen/AMDGPU/frem.ll b/llvm/test/CodeGen/AMDGPU/frem.ll
index 7a1351174733b..8613691c09517 100644
--- a/llvm/test/CodeGen/AMDGPU/frem.ll
+++ b/llvm/test/CodeGen/AMDGPU/frem.ll
@@ -8,6 +8,8 @@
; RUN: llc -amdgpu-scalarize-global-loads=false -enable-misched=0 -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX11,GFX11-FAKE16 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -enable-misched=0 -mtriple=amdgcn -mcpu=gfx1150 -mattr=+real-true16 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX1150,GFX1150-TRUE16 %s
; RUN: llc -amdgpu-scalarize-global-loads=false -enable-misched=0 -mtriple=amdgcn -mcpu=gfx1150 -mattr=-real-true16 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX1150,GFX1150-FAKE16 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -enable-misched=0 -mtriple=amdgcn -mcpu=gfx1200 -mattr=+real-true16 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX1200,GFX1200-TRUE16 %s
+; RUN: llc -amdgpu-scalarize-global-loads=false -enable-misched=0 -mtriple=amdgcn -mcpu=gfx1200 -mattr=-real-true16 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX1200,GFX1200-FAKE16 %s
define amdgpu_kernel void @frem_f16(ptr addrspace(1) %out, ptr addrspace(1) %in1,
; SI-LABEL: frem_f16:
@@ -331,6 +333,82 @@ define amdgpu_kernel void @frem_f16(ptr addrspace(1) %out, ptr addrspace(1) %in1
; GFX1150-FAKE16-NEXT: v_fmac_f16_e32 v1, v3, v2
; GFX1150-FAKE16-NEXT: global_store_b16 v0, v1, s[0:1]
; GFX1150-FAKE16-NEXT: s_endpgm
+;
+; GFX1200-TRUE16-LABEL: frem_f16:
+; GFX1200-TRUE16: ; %bb.0:
+; GFX1200-TRUE16-NEXT: s_clause 0x1
+; GFX1200-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-TRUE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-TRUE16-NEXT: v_mov_b32_e32 v2, 0
+; GFX1200-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1200-TRUE16-NEXT: s_clause 0x1
+; GFX1200-TRUE16-NEXT: global_load_d16_b16 v0, v2, s[2:3]
+; GFX1200-TRUE16-NEXT: global_load_d16_b16 v1, v2, s[4:5] offset:8
+; GFX1200-TRUE16-NEXT: s_wait_loadcnt 0x1
+; GFX1200-TRUE16-NEXT: v_cvt_f32_f16_e32 v3, v0.l
+; GFX1200-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1200-TRUE16-NEXT: v_cvt_f32_f16_e32 v4, v1.l
+; GFX1200-TRUE16-NEXT: v_mov_b16_e32 v5.l, v1.l
+; GFX1200-TRUE16-NEXT: v_mov_b16_e32 v6.l, v0.l
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(TRANS32_DEP_1)
+; GFX1200-TRUE16-NEXT: v_rcp_f32_e32 v4, v4
+; GFX1200-TRUE16-NEXT: v_mul_f32_e32 v3, v3, v4
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_fma_mix_f32 v7, -v5, v3, v6 op_sel_hi:[1,0,1]
+; GFX1200-TRUE16-NEXT: v_fmac_f32_e32 v3, v7, v4
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_fma_mix_f32 v5, -v5, v3, v6 op_sel_hi:[1,0,1]
+; GFX1200-TRUE16-NEXT: v_mul_f32_e32 v4, v5, v4
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_and_b32_e32 v4, 0xff800000, v4
+; GFX1200-TRUE16-NEXT: v_add_f32_e32 v3, v4, v3
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_cvt_f16_f32_e32 v0.h, v3
+; GFX1200-TRUE16-NEXT: v_div_fixup_f16 v0.h, v0.h, v1.l, v0.l
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_trunc_f16_e32 v3.l, v0.h
+; GFX1200-TRUE16-NEXT: v_xor_b32_e32 v3, 0x8000, v3
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_fmac_f16_e32 v0.l, v3.l, v1.l
+; GFX1200-TRUE16-NEXT: global_store_b16 v2, v0, s[0:1]
+; GFX1200-TRUE16-NEXT: s_endpgm
+;
+; GFX1200-FAKE16-LABEL: frem_f16:
+; GFX1200-FAKE16: ; %bb.0:
+; GFX1200-FAKE16-NEXT: s_clause 0x1
+; GFX1200-FAKE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-FAKE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-FAKE16-NEXT: v_mov_b32_e32 v0, 0
+; GFX1200-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1200-FAKE16-NEXT: s_clause 0x1
+; GFX1200-FAKE16-NEXT: global_load_u16 v1, v0, s[2:3]
+; GFX1200-FAKE16-NEXT: global_load_u16 v2, v0, s[4:5] offset:8
+; GFX1200-FAKE16-NEXT: s_wait_loadcnt 0x1
+; GFX1200-FAKE16-NEXT: v_cvt_f32_f16_e32 v3, v1
+; GFX1200-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1200-FAKE16-NEXT: v_cvt_f32_f16_e32 v4, v2
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(TRANS32_DEP_1)
+; GFX1200-FAKE16-NEXT: v_rcp_f32_e32 v4, v4
+; GFX1200-FAKE16-NEXT: v_mul_f32_e32 v3, v3, v4
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_fma_mix_f32 v5, -v2, v3, v1 op_sel_hi:[1,0,1]
+; GFX1200-FAKE16-NEXT: v_fmac_f32_e32 v3, v5, v4
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_fma_mix_f32 v5, -v2, v3, v1 op_sel_hi:[1,0,1]
+; GFX1200-FAKE16-NEXT: v_mul_f32_e32 v4, v5, v4
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_and_b32_e32 v4, 0xff800000, v4
+; GFX1200-FAKE16-NEXT: v_add_f32_e32 v3, v4, v3
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_cvt_f16_f32_e32 v3, v3
+; GFX1200-FAKE16-NEXT: v_div_fixup_f16 v3, v3, v2, v1
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_trunc_f16_e32 v3, v3
+; GFX1200-FAKE16-NEXT: v_xor_b32_e32 v3, 0x8000, v3
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_fmac_f16_e32 v1, v3, v2
+; GFX1200-FAKE16-NEXT: global_store_b16 v0, v1, s[0:1]
+; GFX1200-FAKE16-NEXT: s_endpgm
ptr addrspace(1) %in2) #0 {
%gep2 = getelementptr half, ptr addrspace(1) %in2, i32 4
%r0 = load half, ptr addrspace(1) %in1, align 4
@@ -537,6 +615,50 @@ define amdgpu_kernel void @fast_frem_f16(ptr addrspace(1) %out, ptr addrspace(1)
; GFX1150-FAKE16-NEXT: v_fmac_f16_e32 v1, v3, v2
; GFX1150-FAKE16-NEXT: global_store_b16 v0, v1, s[0:1]
; GFX1150-FAKE16-NEXT: s_endpgm
+;
+; GFX1200-TRUE16-LABEL: fast_frem_f16:
+; GFX1200-TRUE16: ; %bb.0:
+; GFX1200-TRUE16-NEXT: s_clause 0x1
+; GFX1200-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-TRUE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-TRUE16-NEXT: v_mov_b32_e32 v2, 0
+; GFX1200-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1200-TRUE16-NEXT: s_clause 0x1
+; GFX1200-TRUE16-NEXT: global_load_d16_b16 v0, v2, s[2:3]
+; GFX1200-TRUE16-NEXT: global_load_d16_hi_b16 v0, v2, s[4:5] offset:8
+; GFX1200-TRUE16-NEXT: v_rcp_f16_e32 v1.l, 0
+; GFX1200-TRUE16-NEXT: s_wait_loadcnt 0x1
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(TRANS32_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_mul_f16_e32 v1.l, v0.l, v1.l
+; GFX1200-TRUE16-NEXT: v_trunc_f16_e32 v1.l, v1.l
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_xor_b32_e32 v1, 0x8000, v1
+; GFX1200-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1200-TRUE16-NEXT: v_fmac_f16_e32 v0.l, v1.l, v0.h
+; GFX1200-TRUE16-NEXT: global_store_b16 v2, v0, s[0:1]
+; GFX1200-TRUE16-NEXT: s_endpgm
+;
+; GFX1200-FAKE16-LABEL: fast_frem_f16:
+; GFX1200-FAKE16: ; %bb.0:
+; GFX1200-FAKE16-NEXT: s_clause 0x1
+; GFX1200-FAKE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-FAKE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-FAKE16-NEXT: v_mov_b32_e32 v0, 0
+; GFX1200-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1200-FAKE16-NEXT: s_clause 0x1
+; GFX1200-FAKE16-NEXT: global_load_u16 v1, v0, s[2:3]
+; GFX1200-FAKE16-NEXT: global_load_u16 v2, v0, s[4:5] offset:8
+; GFX1200-FAKE16-NEXT: v_rcp_f16_e32 v3, 0
+; GFX1200-FAKE16-NEXT: s_wait_loadcnt 0x1
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(TRANS32_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_mul_f16_e32 v3, v1, v3
+; GFX1200-FAKE16-NEXT: v_trunc_f16_e32 v3, v3
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_xor_b32_e32 v3, 0x8000, v3
+; GFX1200-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1200-FAKE16-NEXT: v_fmac_f16_e32 v1, v3, v2
+; GFX1200-FAKE16-NEXT: global_store_b16 v0, v1, s[0:1]
+; GFX1200-FAKE16-NEXT: s_endpgm
ptr addrspace(1) %in2) #0 {
%gep2 = getelementptr half, ptr addrspace(1) %in2, i32 4
%r0 = load half, ptr addrspace(1) %in1, align 4
@@ -743,6 +865,50 @@ define amdgpu_kernel void @unsafe_frem_f16(ptr addrspace(1) %out, ptr addrspace(
; GFX1150-FAKE16-NEXT: v_fmac_f16_e32 v1, v3, v2
; GFX1150-FAKE16-NEXT: global_store_b16 v0, v1, s[0:1]
; GFX1150-FAKE16-NEXT: s_endpgm
+;
+; GFX1200-TRUE16-LABEL: unsafe_frem_f16:
+; GFX1200-TRUE16: ; %bb.0:
+; GFX1200-TRUE16-NEXT: s_clause 0x1
+; GFX1200-TRUE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-TRUE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-TRUE16-NEXT: v_mov_b32_e32 v2, 0
+; GFX1200-TRUE16-NEXT: s_wait_kmcnt 0x0
+; GFX1200-TRUE16-NEXT: s_clause 0x1
+; GFX1200-TRUE16-NEXT: global_load_d16_b16 v0, v2, s[2:3]
+; GFX1200-TRUE16-NEXT: global_load_d16_hi_b16 v0, v2, s[4:5] offset:8
+; GFX1200-TRUE16-NEXT: v_rcp_f16_e32 v1.l, 0
+; GFX1200-TRUE16-NEXT: s_wait_loadcnt 0x1
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(TRANS32_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_mul_f16_e32 v1.l, v0.l, v1.l
+; GFX1200-TRUE16-NEXT: v_trunc_f16_e32 v1.l, v1.l
+; GFX1200-TRUE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX1200-TRUE16-NEXT: v_xor_b32_e32 v1, 0x8000, v1
+; GFX1200-TRUE16-NEXT: s_wait_loadcnt 0x0
+; GFX1200-TRUE16-NEXT: v_fmac_f16_e32 v0.l, v1.l, v0.h
+; GFX1200-TRUE16-NEXT: global_store_b16 v2, v0, s[0:1]
+; GFX1200-TRUE16-NEXT: s_endpgm
+;
+; GFX1200-FAKE16-LABEL: unsafe_frem_f16:
+; GFX1200-FAKE16: ; %bb.0:
+; GFX1200-FAKE16-NEXT: s_clause 0x1
+; GFX1200-FAKE16-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-FAKE16-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-FAKE16-NEXT: v_mov_b32_e32 v0, 0
+; GFX1200-FAKE16-NEXT: s_wait_kmcnt 0x0
+; GFX1200-FAKE16-NEXT: s_clause 0x1
+; GFX1200-FAKE16-NEXT: global_load_u16 v1, v0, s[2:3]
+; GFX1200-FAKE16-NEXT: global_load_u16 v2, v0, s[4:5] offset:8
+; GFX1200-FAKE16-NEXT: v_rcp_f16_e32 v3, 0
+; GFX1200-FAKE16-NEXT: s_wait_loadcnt 0x1
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(TRANS32_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_mul_f16_e32 v3, v1, v3
+; GFX1200-FAKE16-NEXT: v_trunc_f16_e32 v3, v3
+; GFX1200-FAKE16-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX1200-FAKE16-NEXT: v_xor_b32_e32 v3, 0x8000, v3
+; GFX1200-FAKE16-NEXT: s_wait_loadcnt 0x0
+; GFX1200-FAKE16-NEXT: v_fmac_f16_e32 v1, v3, v2
+; GFX1200-FAKE16-NEXT: global_store_b16 v0, v1, s[0:1]
+; GFX1200-FAKE16-NEXT: s_endpgm
ptr addrspace(1) %in2) #1 {
%gep2 = getelementptr half, ptr addrspace(1) %in2, i32 4
%r0 = load half, ptr addrspace(1) %in1, align 4
@@ -985,6 +1151,42 @@ define amdgpu_kernel void @frem_f32(ptr addrspace(1) %out, ptr addrspace(1) %in1
; GFX1150-NEXT: v_fmac_f32_e32 v1, v3, v2
; GFX1150-NEXT: global_store_b32 v0, v1, s[0:1]
; GFX1150-NEXT: s_endpgm
+;
+; GFX1200-LABEL: frem_f32:
+; GFX1200: ; %bb.0:
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-NEXT: v_mov_b32_e32 v0, 0
+; GFX1200-NEXT: s_wait_kmcnt 0x0
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: global_load_b32 v1, v0, s[2:3]
+; GFX1200-NEXT: global_load_b32 v2, v0, s[4:5] offset:16
+; GFX1200-NEXT: s_wait_loadcnt 0x0
+; GFX1200-NEXT: v_div_scale_f32 v4, null, v2, v2, v1
+; GFX1200-NEXT: v_div_scale_f32 v3, vcc_lo, v1, v2, v1
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(TRANS32_DEP_1)
+; GFX1200-NEXT: v_rcp_f32_e32 v5, v4
+; GFX1200-NEXT: s_denorm_mode 15
+; GFX1200-NEXT: v_fma_f32 v6, -v4, v5, 1.0
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_fmac_f32_e32 v5, v6, v5
+; GFX1200-NEXT: v_mul_f32_e32 v6, v3, v5
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_fma_f32 v7, -v4, v6, v3
+; GFX1200-NEXT: v_fmac_f32_e32 v6, v7, v5
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_fma_f32 v3, -v4, v6, v3
+; GFX1200-NEXT: s_denorm_mode 12
+; GFX1200-NEXT: v_div_fmas_f32 v3, v3, v5, v6
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_div_fixup_f32 v3, v3, v2, v1
+; GFX1200-NEXT: v_trunc_f32_e32 v3, v3
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_xor_b32_e32 v3, 0x80000000, v3
+; GFX1200-NEXT: v_fmac_f32_e32 v1, v3, v2
+; GFX1200-NEXT: global_store_b32 v0, v1, s[0:1]
+; GFX1200-NEXT: s_endpgm
ptr addrspace(1) %in2) #0 {
%gep2 = getelementptr float, ptr addrspace(1) %in2, i32 4
%r0 = load float, ptr addrspace(1) %in1, align 4
@@ -1142,6 +1344,27 @@ define amdgpu_kernel void @fast_frem_f32(ptr addrspace(1) %out, ptr addrspace(1)
; GFX1150-NEXT: v_fmac_f32_e32 v1, v3, v2
; GFX1150-NEXT: global_store_b32 v0, v1, s[0:1]
; GFX1150-NEXT: s_endpgm
+;
+; GFX1200-LABEL: fast_frem_f32:
+; GFX1200: ; %bb.0:
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-NEXT: v_mov_b32_e32 v0, 0
+; GFX1200-NEXT: s_wait_kmcnt 0x0
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: global_load_b32 v1, v0, s[2:3]
+; GFX1200-NEXT: global_load_b32 v2, v0, s[4:5] offset:16
+; GFX1200-NEXT: s_wait_loadcnt 0x0
+; GFX1200-NEXT: v_rcp_f32_e32 v3, v2
+; GFX1200-NEXT: s_delay_alu instid0(TRANS32_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_mul_f32_e32 v3, v1, v3
+; GFX1200-NEXT: v_trunc_f32_e32 v3, v3
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_xor_b32_e32 v3, 0x80000000, v3
+; GFX1200-NEXT: v_fmac_f32_e32 v1, v3, v2
+; GFX1200-NEXT: global_store_b32 v0, v1, s[0:1]
+; GFX1200-NEXT: s_endpgm
ptr addrspace(1) %in2) #0 {
%gep2 = getelementptr float, ptr addrspace(1) %in2, i32 4
%r0 = load float, ptr addrspace(1) %in1, align 4
@@ -1299,6 +1522,27 @@ define amdgpu_kernel void @unsafe_frem_f32(ptr addrspace(1) %out, ptr addrspace(
; GFX1150-NEXT: v_fmac_f32_e32 v1, v3, v2
; GFX1150-NEXT: global_store_b32 v0, v1, s[0:1]
; GFX1150-NEXT: s_endpgm
+;
+; GFX1200-LABEL: unsafe_frem_f32:
+; GFX1200: ; %bb.0:
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-NEXT: v_mov_b32_e32 v0, 0
+; GFX1200-NEXT: s_wait_kmcnt 0x0
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: global_load_b32 v1, v0, s[2:3]
+; GFX1200-NEXT: global_load_b32 v2, v0, s[4:5] offset:16
+; GFX1200-NEXT: s_wait_loadcnt 0x0
+; GFX1200-NEXT: v_rcp_f32_e32 v3, v2
+; GFX1200-NEXT: s_delay_alu instid0(TRANS32_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_mul_f32_e32 v3, v1, v3
+; GFX1200-NEXT: v_trunc_f32_e32 v3, v3
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_xor_b32_e32 v3, 0x80000000, v3
+; GFX1200-NEXT: v_fmac_f32_e32 v1, v3, v2
+; GFX1200-NEXT: global_store_b32 v0, v1, s[0:1]
+; GFX1200-NEXT: s_endpgm
ptr addrspace(1) %in2) #1 {
%gep2 = getelementptr float, ptr addrspace(1) %in2, i32 4
%r0 = load float, ptr addrspace(1) %in1, align 4
@@ -1551,6 +1795,39 @@ define amdgpu_kernel void @frem_f64(ptr addrspace(1) %out, ptr addrspace(1) %in1
; GFX1150-NEXT: v_fma_f64 v[0:1], -v[4:5], v[2:3], v[0:1]
; GFX1150-NEXT: global_store_b64 v12, v[0:1], s[0:1]
; GFX1150-NEXT: s_endpgm
+;
+; GFX1200-LABEL: frem_f64:
+; GFX1200: ; %bb.0:
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: s_load_b128 s[0:3], s[4:5], 0x24
+; GFX1200-NEXT: s_load_b64 s[4:5], s[4:5], 0x34
+; GFX1200-NEXT: v_mov_b32_e32 v12, 0
+; GFX1200-NEXT: s_wait_kmcnt 0x0
+; GFX1200-NEXT: s_clause 0x1
+; GFX1200-NEXT: global_load_b64 v[0:1], v12, s[2:3]
+; GFX1200-NEXT: global_load_b64 v[2:3], v12, s[4:5]
+; GFX1200-NEXT: s_wait_loadcnt 0x0
+; GFX1200-NEXT: v_div_scale_f64 v[4:5], null, v[2:3], v[2:3], v[0:1]
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(TRANS32_DEP_1)
+; GFX1200-NEXT: v_rcp_f64_e32 v[6:7], v[4:5]
+; GFX1200-NEXT: v_fma_f64 v[8:9], -v[4:5], v[6:7], 1.0
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_fma_f64 v[6:7], v[6:7], v[8:9], v[6:7]
+; GFX1200-NEXT: v_fma_f64 v[8:9], -v[4:5], v[6:7], 1.0
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(SKIP_1) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_fma_f64 v[6:7], v[6:7], v[8:9], v[6:7]
+; GFX1200-NEXT: v_div_scale_f64 v[8:9], vcc_lo, v[0:1], v[2:3], v[0:1]
+; GFX1200-NEXT: v_mul_f64_e32 v[10:11], v[8:9], v[6:7]
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_fma_f64 v[4:5], -v[4:5], v[10:11], v[8:9]
+; GFX1200-NEXT: v_div_fmas_f64 v[4:5], v[4:5], v[6:7], v[10:11]
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
+; GFX1200-NEXT: v_div_fixup_f64 v[4:5], v[4:5], v[2:3], v[0:1]
+; GFX1200-NEXT: v_trunc_f64_e32 v[4:5], v[4:5]
+; GFX1200-NEXT: s_delay_alu instid0(VALU_DEP_1)
+; GFX1200-NEXT: v_fma_f64 v[0:1], -v[4:5], v[2:3], v[0:1]
+; GFX1200-NEXT: global_store_b64 v12, v[0:1], s[0:1]
+; GFX1200-NEXT: s_endpgm
ptr addrspace(1) %in2) #0 {
%r0 = load double, ptr addrspace(1) %in1, align 8
%r1 = load double, ptr addrspace(1) %in2, align 8
@@ -1772,6 +2049,35 @@ define amdgpu_kernel void @fast_frem_f64(ptr addrspace(1) %out, ptr addrspace(1)
; GFX1150-NEXT: v_fma_f64 v[0:1], -v[4:5], v[2:...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/141152
More information about the llvm-commits
mailing list