[llvm-branch-commits] [llvm] [AMDGPU][Legalizer] Widen i16 G_SEXT_INREG (PR #131308)
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Mar 14 04:19:28 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-globalisel
@llvm/pr-subscribers-backend-amdgpu
Author: Pierre van Houtryve (Pierre-vh)
<details>
<summary>Changes</summary>
It's better to widen them to avoid it being lowered into a G_ASHR + G_SHL. With this change we just extend to i32 then trunc the result.
---
Patch is 69.78 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/131308.diff
11 Files Affected:
- (modified) llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp (+2-1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/ashr.ll (+3-4)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-abs.mir (+3-5)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ashr.mir (+8-12)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-sext-inreg.mir (+60-95)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-sext.mir (+49-52)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smax.mir (+25-8)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smin.mir (+25-8)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-smulh.mir (+59-73)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.abs.ll (+15-30)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/sext_inreg.ll (+50-80)
``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
index b3a8183beeacf..6e611ebb4b625 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
@@ -2009,7 +2009,8 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_,
// S64 is only legal on SALU, and needs to be broken into 32-bit elements in
// RegBankSelect.
auto &SextInReg = getActionDefinitionsBuilder(G_SEXT_INREG)
- .legalFor({{S32}, {S64}});
+ .legalFor({{S32}, {S64}})
+ .widenScalarIf(typeIs(0, S16), widenScalarOrEltToNextPow2(0, 32));
if (ST.hasVOP3PInsts()) {
SextInReg.lowerFor({{V2S16}})
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/ashr.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/ashr.ll
index 493e8cef63890..f81d7f1c300b8 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/ashr.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/ashr.ll
@@ -17,8 +17,7 @@ define i8 @v_ashr_i8(i8 %value, i8 %amount) {
; GFX8-LABEL: v_ashr_i8:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX8-NEXT: v_lshlrev_b16_e32 v0, 8, v0
-; GFX8-NEXT: v_ashrrev_i16_sdwa v0, v1, sext(v0) dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:BYTE_0 src1_sel:BYTE_1
+; GFX8-NEXT: v_ashrrev_i16_sdwa v0, v1, sext(v0) dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:BYTE_0 src1_sel:BYTE_0
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: v_ashr_i8:
@@ -49,8 +48,8 @@ define i8 @v_ashr_i8_7(i8 %value) {
; GFX8-LABEL: v_ashr_i8_7:
; GFX8: ; %bb.0:
; GFX8-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX8-NEXT: v_lshlrev_b16_e32 v0, 8, v0
-; GFX8-NEXT: v_ashrrev_i16_e32 v0, 15, v0
+; GFX8-NEXT: v_mov_b32_e32 v1, 7
+; GFX8-NEXT: v_ashrrev_i16_sdwa v0, v1, sext(v0) dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:DWORD src1_sel:BYTE_0
; GFX8-NEXT: s_setpc_b64 s[30:31]
;
; GFX9-LABEL: v_ashr_i8_7:
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-abs.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-abs.mir
index a9fe80eb47e76..2b911b2dce697 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-abs.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-abs.mir
@@ -144,11 +144,9 @@ body: |
; VI: liveins: $vgpr0
; VI-NEXT: {{ $}}
; VI-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
- ; VI-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
- ; VI-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
- ; VI-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C]](s16)
- ; VI-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C]](s16)
- ; VI-NEXT: [[ABS:%[0-9]+]]:_(s16) = G_ABS [[ASHR]]
+ ; VI-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
+ ; VI-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
+ ; VI-NEXT: [[ABS:%[0-9]+]]:_(s16) = G_ABS [[TRUNC]]
; VI-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ABS]](s16)
; VI-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
;
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ashr.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ashr.mir
index f4aaab745e03b..53905a2f49dd0 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ashr.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-ashr.mir
@@ -319,12 +319,10 @@ body: |
; VI-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; VI-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
; VI-NEXT: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
- ; VI-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
- ; VI-NEXT: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
- ; VI-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C1]](s16)
- ; VI-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C1]](s16)
- ; VI-NEXT: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[ASHR]], [[AND]](s16)
- ; VI-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ASHR1]](s16)
+ ; VI-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
+ ; VI-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
+ ; VI-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[TRUNC1]], [[AND]](s16)
+ ; VI-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ASHR]](s16)
; VI-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
;
; GFX9PLUS-LABEL: name: test_ashr_i8_i8
@@ -374,12 +372,10 @@ body: |
; VI-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
; VI-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 127
; VI-NEXT: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
- ; VI-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
- ; VI-NEXT: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 9
- ; VI-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C1]](s16)
- ; VI-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C1]](s16)
- ; VI-NEXT: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[ASHR]], [[AND]](s16)
- ; VI-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ASHR1]](s16)
+ ; VI-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 7
+ ; VI-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
+ ; VI-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[TRUNC1]], [[AND]](s16)
+ ; VI-NEXT: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ASHR]](s16)
; VI-NEXT: $vgpr0 = COPY [[ANYEXT]](s32)
;
; GFX9PLUS-LABEL: name: test_ashr_s7_s7
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-sext-inreg.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-sext-inreg.mir
index 40c48e10f933f..1ab84eb08abf6 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-sext-inreg.mir
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-sext-inreg.mir
@@ -426,11 +426,9 @@ body: |
; GFX8: liveins: $vgpr0
; GFX8-NEXT: {{ $}}
; GFX8-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
- ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
- ; GFX8-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 15
- ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C]](s16)
- ; GFX8-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C]](s16)
- ; GFX8-NEXT: S_ENDPGM 0, implicit [[ASHR]](s16)
+ ; GFX8-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 1
+ ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
+ ; GFX8-NEXT: S_ENDPGM 0, implicit [[TRUNC]](s16)
;
; GFX6-LABEL: name: test_sext_inreg_s16_1
; GFX6: liveins: $vgpr0
@@ -464,11 +462,9 @@ body: |
; GFX8: liveins: $vgpr0
; GFX8-NEXT: {{ $}}
; GFX8-NEXT: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
- ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
- ; GFX8-NEXT: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 1
- ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C]](s16)
- ; GFX8-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C]](s16)
- ; GFX8-NEXT: S_ENDPGM 0, implicit [[ASHR]](s16)
+ ; GFX8-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 15
+ ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[SEXT_INREG]](s32)
+ ; GFX8-NEXT: S_ENDPGM 0, implicit [[TRUNC]](s16)
;
; GFX6-LABEL: name: test_sext_inreg_s16_15
; GFX6: liveins: $vgpr0
@@ -821,19 +817,15 @@ body: |
; GFX8-NEXT: {{ $}}
; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
- ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 15
- ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[C1]](s16)
- ; GFX8-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR]](s16)
- ; GFX8-NEXT: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR1]](s16)
- ; GFX8-NEXT: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
- ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL2]]
+ ; GFX8-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST]], 1
+ ; GFX8-NEXT: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 1
+ ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+ ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG]], [[C1]]
+ ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG1]], [[C1]]
+ ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
+ ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; GFX8-NEXT: $vgpr0 = COPY [[BITCAST1]](<2 x s16>)
;
@@ -907,38 +899,31 @@ body: |
; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<6 x s16>) = COPY $vgpr0_vgpr1_vgpr2
; GFX8-NEXT: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>), [[UV2:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<6 x s16>)
; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
- ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 15
- ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL2:%[0-9]+]]:_(s16) = G_SHL [[TRUNC2]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR2:%[0-9]+]]:_(s16) = G_ASHR [[SHL2]], [[C1]](s16)
+ ; GFX8-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST]], 1
+ ; GFX8-NEXT: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 1
+ ; GFX8-NEXT: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST1]], 1
; GFX8-NEXT: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; GFX8-NEXT: [[UV3:%[0-9]+]]:_(<2 x s16>), [[UV4:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<4 x s16>)
; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
; GFX8-NEXT: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV4]](<2 x s16>)
- ; GFX8-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR]](s16)
- ; GFX8-NEXT: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR1]](s16)
- ; GFX8-NEXT: [[SHL3:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
- ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL3]]
+ ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+ ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG]], [[C1]]
+ ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG1]], [[C1]]
+ ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
+ ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX8-NEXT: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
- ; GFX8-NEXT: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR2]](s16)
- ; GFX8-NEXT: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
- ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[BITCAST2]], [[C2]]
- ; GFX8-NEXT: [[SHL4:%[0-9]+]]:_(s32) = G_SHL [[AND]], [[C]](s32)
- ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL4]]
+ ; GFX8-NEXT: [[AND2:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG2]], [[C1]]
+ ; GFX8-NEXT: [[AND3:%[0-9]+]]:_(s32) = G_AND [[BITCAST2]], [[C1]]
+ ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C]](s32)
+ ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[AND2]], [[SHL1]]
; GFX8-NEXT: [[BITCAST5:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
- ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[BITCAST3]], [[C2]]
- ; GFX8-NEXT: [[SHL5:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
- ; GFX8-NEXT: [[OR2:%[0-9]+]]:_(s32) = G_OR [[LSHR1]], [[SHL5]]
+ ; GFX8-NEXT: [[AND4:%[0-9]+]]:_(s32) = G_AND [[BITCAST3]], [[C1]]
+ ; GFX8-NEXT: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND4]], [[C]](s32)
+ ; GFX8-NEXT: [[OR2:%[0-9]+]]:_(s32) = G_OR [[LSHR1]], [[SHL2]]
; GFX8-NEXT: [[BITCAST6:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR2]](s32)
; GFX8-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<6 x s16>) = G_CONCAT_VECTORS [[BITCAST4]](<2 x s16>), [[BITCAST5]](<2 x s16>), [[BITCAST6]](<2 x s16>)
; GFX8-NEXT: $vgpr0_vgpr1_vgpr2 = COPY [[CONCAT_VECTORS]](<6 x s16>)
@@ -1101,32 +1086,24 @@ body: |
; GFX8-NEXT: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; GFX8-NEXT: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
- ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 15
- ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL2:%[0-9]+]]:_(s16) = G_SHL [[TRUNC2]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR2:%[0-9]+]]:_(s16) = G_ASHR [[SHL2]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL3:%[0-9]+]]:_(s16) = G_SHL [[TRUNC3]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR3:%[0-9]+]]:_(s16) = G_ASHR [[SHL3]], [[C1]](s16)
- ; GFX8-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR]](s16)
- ; GFX8-NEXT: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR1]](s16)
- ; GFX8-NEXT: [[SHL4:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
- ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL4]]
+ ; GFX8-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST]], 1
+ ; GFX8-NEXT: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 1
+ ; GFX8-NEXT: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST1]], 1
+ ; GFX8-NEXT: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR1]], 1
+ ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+ ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG]], [[C1]]
+ ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG1]], [[C1]]
+ ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
+ ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
- ; GFX8-NEXT: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR2]](s16)
- ; GFX8-NEXT: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR3]](s16)
- ; GFX8-NEXT: [[SHL5:%[0-9]+]]:_(s32) = G_SHL [[ZEXT3]], [[C]](s32)
- ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL5]]
+ ; GFX8-NEXT: [[AND2:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG2]], [[C1]]
+ ; GFX8-NEXT: [[AND3:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG3]], [[C1]]
+ ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C]](s32)
+ ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[AND2]], [[SHL1]]
; GFX8-NEXT: [[BITCAST3:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
; GFX8-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BITCAST2]](<2 x s16>), [[BITCAST3]](<2 x s16>)
; GFX8-NEXT: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
@@ -1188,45 +1165,33 @@ body: |
; GFX8: [[DEF:%[0-9]+]]:_(<6 x s16>) = G_IMPLICIT_DEF
; GFX8-NEXT: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>), [[UV2:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<6 x s16>)
; GFX8-NEXT: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; GFX8-NEXT: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX8-NEXT: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; GFX8-NEXT: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; GFX8-NEXT: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
; GFX8-NEXT: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
- ; GFX8-NEXT: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
; GFX8-NEXT: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
- ; GFX8-NEXT: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
- ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 15
- ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[TRUNC]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR:%[0-9]+]]:_(s16) = G_ASHR [[SHL]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s16) = G_SHL [[TRUNC1]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR1:%[0-9]+]]:_(s16) = G_ASHR [[SHL1]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL2:%[0-9]+]]:_(s16) = G_SHL [[TRUNC2]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR2:%[0-9]+]]:_(s16) = G_ASHR [[SHL2]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL3:%[0-9]+]]:_(s16) = G_SHL [[TRUNC3]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR3:%[0-9]+]]:_(s16) = G_ASHR [[SHL3]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL4:%[0-9]+]]:_(s16) = G_SHL [[TRUNC4]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR4:%[0-9]+]]:_(s16) = G_ASHR [[SHL4]], [[C1]](s16)
- ; GFX8-NEXT: [[SHL5:%[0-9]+]]:_(s16) = G_SHL [[TRUNC5]], [[C1]](s16)
- ; GFX8-NEXT: [[ASHR5:%[0-9]+]]:_(s16) = G_ASHR [[SHL5]], [[C1]](s16)
- ; GFX8-NEXT: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR]](s16)
- ; GFX8-NEXT: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR1]](s16)
- ; GFX8-NEXT: [[SHL6:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
- ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL6]]
+ ; GFX8-NEXT: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST]], 1
+ ; GFX8-NEXT: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 1
+ ; GFX8-NEXT: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST1]], 1
+ ; GFX8-NEXT: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR1]], 1
+ ; GFX8-NEXT: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST2]], 1
+ ; GFX8-NEXT: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR2]], 1
+ ; GFX8-NEXT: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
+ ; GFX8-NEXT: [[AND:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG]], [[C1]]
+ ; GFX8-NEXT: [[AND1:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG1]], [[C1]]
+ ; GFX8-NEXT: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
+ ; GFX8-NEXT: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX8-NEXT: [[BITCAST3:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
- ; GFX8-NEXT: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR2]](s16)
- ; GFX8-NEXT: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR3]](s16)
- ; GFX8-NEXT: [[SHL7:%[0-9]+]]:_(s32) = G_SHL [[ZEXT3]], [[C]](s32)
- ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL7]]
+ ; GFX8-NEXT: [[AND2:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG2]], [[C1]]
+ ; GFX8-NEXT: [[AND3:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG3]], [[C1]]
+ ; GFX8-NEXT: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C]](s32)
+ ; GFX8-NEXT: [[OR1:%[0-9]+]]:_(s32) = G_OR [[AND2]], [[SHL1]]
; GFX8-NEXT: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
- ; GFX8-NEXT: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR4]](s16)
- ; GFX8-NEXT: [[ZEXT5:%[0-9]+]]:_(s32) = G_ZEXT [[ASHR5]](s16)
- ; GFX8-NEXT: [[SHL8:%[0-9]+]]:_(s32) = G_SHL [[ZEXT5]], [[C]](s32)
- ; GFX8-NEXT: [[OR2:%[0-9]+]]:_(s32) = G_OR [[ZEXT4]], [[SHL8]]
+ ; GFX8-NEXT: [[AND4:%[0-9]+]]:_(s32) = G_AND [[SEXT_INREG4]], [[C1]]
+ ; GFX8-NEXT: [[AND5:%[0-9]+]]:_(s32) = G_AND [[...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/131308
More information about the llvm-branch-commits
mailing list